CN112990972A - Recommendation method based on heterogeneous graph neural network - Google Patents
Recommendation method based on heterogeneous graph neural network Download PDFInfo
- Publication number
- CN112990972A CN112990972A CN202110296182.1A CN202110296182A CN112990972A CN 112990972 A CN112990972 A CN 112990972A CN 202110296182 A CN202110296182 A CN 202110296182A CN 112990972 A CN112990972 A CN 112990972A
- Authority
- CN
- China
- Prior art keywords
- node
- graph
- user
- embedding vector
- heterogeneous
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 57
- 239000013598 vector Substances 0.000 claims abstract description 111
- 230000004927 fusion Effects 0.000 claims abstract description 59
- 238000005070 sampling Methods 0.000 claims abstract description 35
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000003993 interaction Effects 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000014509 gene expression Effects 0.000 claims description 4
- 230000006883 memory enhancing effect Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000001914 filtration Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明属于推荐系统技术领域，涉及一种基于异构图神经网络的推荐方法，包括：收集带有用户间社交关系、用户‑商品交互历史数据及商品类别信息的数据集，并过滤无效数据以及进行负采样；随机选取用户集合及相关商品集合，并进行多阶图采样与建图；结点特征提取：将构建的图输入到异构图神经网络中进行处理，得到结点的融合结点嵌入向量；对于不需要经过重校准步骤的商品结点而言，商品结点的融合结点嵌入向量即为商品融合嵌入向量；重校准：对用户融合结点嵌入向量进行重校准，得到用户最终表示嵌入向量；使用用户最终表示嵌入向量和商品融合嵌入向量进行偏好预测，并得到推荐顺序。本发明解决了数据稀疏和数据缺失的问题，具有推荐精准等优点。
The invention belongs to the technical field of recommendation systems, and relates to a recommendation method based on a heterogeneous graph neural network. Perform negative sampling; randomly select user sets and related product sets, and perform multi-level graph sampling and mapping; node feature extraction: input the constructed graph into the heterogeneous graph neural network for processing, and obtain the fusion node of the nodes Embedding vector; for commodity nodes that do not need to go through the recalibration step, the fusion node embedding vector of commodity nodes is the commodity fusion embedding vector; recalibration: recalibrate the user fusion node embedding vector to obtain the final user Representation embedding vector; use the final user representation embedding vector and the product fusion embedding vector for preference prediction, and get the recommendation order. The invention solves the problems of data sparse and missing data, and has the advantages of accurate recommendation and the like.
Description
Technical Field
The invention belongs to the technical field of recommendation systems, and relates to a recommendation method based on a heterogeneous graph neural network.
Background
In the current information explosion era, the information received by users every day exceeds the range which can be processed by individuals, and the selection of the needed relevant useful information by the users is seriously interfered by massive irrelevant redundant information. The recommendation system is an application for recommending commodities to a target user according to user historical behaviors and personal preferences, and can provide personalized more useful related information for the user, so that the problem of information overload is effectively relieved.
In recent years, with the explosive growth of the internet and smart mobile devices, recommendation systems have been widely applied to various network services such as e-commerce websites, online forums, advertisement platforms, and video websites. The quality of the recommendation method directly determines whether the personalized recommendation of the recommendation system is accurate or not. However, the conventional recommendation method based on the collaborative filtering model has the problems of data sparseness and the like, so that some long-tail commodities are difficult to recommend to users in need, and the requirement of the users for rapidly and accurately acquiring the needed commodities is greatly limited. Therefore, in order to alleviate the problem caused by data sparseness, other information besides the interaction between the user and the commodity is introduced, and it is increasingly critical to research the recommendation method under the heterogeneous relationship.
Current recommendation methods can be simply divided into three categories: collaborative filtering methods, content-based methods, and hybrid methods. The collaborative filtering method not only utilizes the historical behaviors of the target user to model the user, but also utilizes other users and commodities to predict the target user-commodity interaction. User-commodity interaction history data can generally provide better prediction results and is easy to acquire, and therefore is generally regarded as core information of a recommendation method. Although the collaborative filtering method has a good prediction performance, the problem of data sparsity inevitably exists in the interaction history data of the user and the commodity, so that the collaborative filtering method cannot fundamentally deal with the recommendation and cold start problems of the long-tailed commodity. The content-based approach models using data describing the user or the good, such as the user's age, gender, or category of the good, textual description, etc., such data primarily describing features of the user or the good itself, rather than focusing on the user's interaction with the good, and is therefore referred to as content data. The data can not be scarce due to new users or the use frequency of the users and the like, and the data sparseness problem can be effectively avoided. The mixing method is to fuse the collaborative filtering method and the content-based method, not only use the user-commodity interaction historical data more fitting the recommendation scene, but also use the characteristics of the abundant users and commodities, and generally obtain more accurate recommendation effect.
With the rapid development of deep learning technology, deep learning methods have been widely applied to various new recommendation methods. The method for recommending Neural network performance by Wang et al shows a high concern as the collaborative filtering model NGCF (detailed document: Wang, Xiang, et al, "Neural graph collaborative filtering." Proceedings of the 42nd interactive ACM SIGER linkage Research and depth in Information retrieval.2019.) is widely applied and how many of the proposed LightGCN (detailed document: He, Xiang, et al, "Lightgcn: Simplicity and position mapping convention for retrieval.) are applied to the mainstream network service method. Although the graph neural network can achieve excellent achievement on the collaborative filtering method, the graph neural network still suffers from the data sparseness problem of the collaborative filtering method. Therefore, in order to reduce the problems caused by data sparseness, it is necessary to merge more content information and user-related social information into the graph model.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a recommendation method based on a heterogeneous graph neural network.
The invention is realized by adopting the following technical scheme:
a recommendation method based on a heterogeneous graph neural network comprises the following steps:
collecting a data set with the social relationship among users, user-commodity interaction historical data and commodity category information, filtering invalid data and carrying out negative sampling;
randomly selecting a user set and a related commodity set from the data set, and carrying out multi-level graph sampling and graph building;
and (3) node feature extraction: inputting the constructed graph into a heterogeneous graph neural network comprising a plurality of layers of heterogeneous graph memory network layers for processing to obtain a fusion node embedded vector of nodes; for the commodity nodes which do not need to be subjected to the recalibration step, the fusion node embedded vectors of the commodity nodes are the commodity fusion embedded vectors;
recalibration: recalibrating the user fusion node embedded vector to obtain a user final representation embedded vector;
and (4) recommendation and prediction: and performing preference prediction by using the user final representation embedding vector and the commodity fusion embedding vector, and obtaining a recommendation sequence.
Preferably, the multi-level graph sampling and mapping process includes:
(1) randomly selecting a user commodity pair of the data set, if the commodity pair is not subjected to negative sampling, further performing commodity negative sampling, and taking the user, the commodity and the negative sampling commodity in the selected set as seed nodes of graph sampling;
(2) and carrying out multi-order graph sampling on the seed nodes, determining the order and the number of sampling points of each order, and then carrying out graph sampling.
Preferably, the heterogeneous neural network comprises a multi-layer hopping junction neural network and a user-embedded vector recalibration network, wherein:
the multi-layer jump connection neural network uses a multi-layer jump structure, and each layer of the network layer of the layer diagram has a jump connection to the final output;
and the user embedded vector recalibration network is used for recalibrating the user fusion node embedded vectors.
Preferably, the step of extracting the fusion node embedding vector of the node comprises:
(1) inputting the graph constructed in the step S2 into a neural network of a heterogeneous graph, and obtaining an initial embedded vector of a node through an initial embedded vector table;
(2) obtaining node output embedded vectors of each layer of heterogeneous graph memory network layer of the nodes through a plurality of layers of heterogeneous graph memory network layers;
(3) and fusing the initial embedded vectors of the nodes and the node output embedded vectors of each layer of the heteromorphic image memory network layer to obtain fused node embedded vectors of the nodes.
Preferably, the processing procedure of the heterogeneous graph memory network layer comprises the following steps:
1) extracting the characteristics of an edge end point of each edge in the graph by using a memory enhanced heterogeneous relation encoder;
2) fusing the messages received by each node to obtain node output embedded vectors;
3) directly taking the output embedded vector after fusing each node message as a node output embedded vector output by a heterogeneous graph memory network layer; or, using Layernorm for standardization and adding the output of the memory enhanced heterogeneous relation encoder using the self-loop as the node output embedded vector of the final output of the heterogeneous graph memory network layer.
Preferably, the memory-enhanced heterogeneous relationship encoder comprises the operations of:
a) obtaining the coefficient of each memory unit of the memory-enhanced heterogeneous relation encoder of the lower end point of the corresponding relation of the edges by using the bias linear transformation of the learnable band after the activation function is activated;
b) and performing linear transformation on the embedded vector of the lower starting point of the corresponding relation of the sides by using the sum of the products of all the memory units and the corresponding coefficients thereof as a transformation matrix.
Preferably, the representation form of the message fusion function for fusing the messages received by each node is different among different types of nodes, and the representation form includes:
for the user node, the message fusion function is expressed as the sum of the normalized social relationship of the user node and the messages obtained by the user-commodity interaction history through the memory enhanced heterogeneous relationship encoder;
for the commodity node, the message fusion function is expressed as the sum of the normalized user-commodity interaction history of the commodity node and the normalized commodity generic relation obtained by the memory enhanced heterogeneous relation encoder;
for the commodity category node, the message fusion function is expressed as the sum of the messages of the normalized commodity category node commodity generic relationship obtained by the memory enhanced heterogeneous relationship encoder.
Preferably, the method for obtaining the fusion node embedding vector of the node comprises the following steps: and splicing the node initial embedded vector with the output of each layer of the heteromorphic graph memory network layer, and normalizing by using Layernorm.
Preferably, the recalibration method comprises: and adding the user fusion node embedded vector and the result of the self-looping first-order graph convolution of the user node on the social relationship to obtain a user final representation embedded vector.
Preferably, the recommendation method further comprises:
the heterogeneous graph neural network training phase uses BPRLoss as a loss function to supervise and then backpropagate the gradient into the heterogeneous graph neural network.
Compared with the prior art, the invention has the following advantages:
1. according to the method and the device, the social relationship among users, the characteristics of commodities and the interaction historical data of the users and the commodities are considered at the same time, so that the recommendation method is ensured to achieve the excellent performance of the collaborative filtering recommendation method, the advantage of avoiding data sparseness based on the content recommendation method is achieved, the influence of the social relationship on the preference of the users is considered, more accurate recommendation is achieved, and the problem of data overload is solved.
2. The method can well deal with the data sparsity problem encountered by the collaborative filtering method. For users and commodities with rare interaction historical data, the depiction of the objects by the traditional collaborative filtering method is limited to the neighbors of the target object, but the quantity of the rare neighbors can bring deviation to the depiction of the objects. The social information and the category information are introduced, so that the characteristics of the target object can be depicted in the angles of the user and the commodity, and the problems of data sparseness and data loss in the collaborative filtering method are solved.
3. The invention introduces a jump connection mode to overcome the gradient disappearance problem in the traditional graph neural network architecture, and each graph neural network layer is provided with a jump connection to the final output layer, so that the gradient disappearance problem can be avoided when the network deepens.
4. The heterogeneous graph neural network layer of the invention adopts a memory-enhanced relationship encoder to capture heterogeneous relationship features. Different memory parameters are adopted among different types of connections, and parameter level differentiation is provided for message transmission of the neural network of the heterogeneous graph, so that mutual information among different types of messages is less, and the information quantity of message transmission is increased, and therefore, the heterogeneous relationships of user social information, commodity category information and the like can be better utilized to recommend commodities to users.
5. The invention adopts a user embedded vector recalibration mechanism, the characteristic component sources of the user node embedded vectors output by the graph neural network are complex, and the recalibration can enable the user fusion node embedded vectors to be greatly influenced by social connection, so that the user finally shows that the embedded vectors have stronger character feature description capacity.
Drawings
FIG. 1 is a flow diagram of a recommendation method in one embodiment;
FIG. 2 is a diagram illustrating node feature extraction according to an embodiment;
FIG. 3 is a diagram of a heteromorphic neural network architecture in one embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments.
The working principle of the invention comprises: firstly, preprocessing a data set to obtain social relations among users, user-commodity interaction historical data and commodity category data, sampling a multi-level graph and constructing a heterogeneous graph, and inputting the constructed heterogeneous graph into a trained heterogeneous graph network for recommendation and prediction.
A recommendation method based on a heterogeneous graph neural network comprises the following steps:
s1, constructing a data set, collecting the data set with the social relationship among users, the user-commodity interaction historical data and the commodity category information in the scenes of E-commerce, comment websites and the like, filtering invalid data and carrying out negative sampling.
Most of the currently disclosed recommendation methods are based on collaborative filtering methods, but in real e-commerce, comment and video network services, a service provider usually has other information besides user-commodity interaction history information such as social relations among users and commodity categories. Therefore, if the additional information can be utilized, the characteristics of the user and the commodity can be accurately described, so that more accurate user preference can be obtained, the time spent by the user on the commodity which is not interested is reduced, and the interaction willingness of the user is improved. While many neural network methods based on collaborative filtering perform graph neural network reasoning according to a user-commodity interaction bipartite graph, the homograph method based on a single relationship is not applicable to the invention containing multiple relationships. Therefore, if such additional information is to be utilized, there is a need for the collection of data sets that, in addition to the historical data of user-item interactions, also contain user social relationships and item category data, as used in common collaborative filtering methods. The collection of data sets is thus critical to network training.
When the data set is constructed, the data set with the social relationship among users, the user-commodity interaction historical data and the commodity category information in the scenes of a merchant website, a comment website and the like can be collected. Several review data sets, Ciao, eponions, Yelp, that have been published so far, can be used as candidate data sets for model training and validation tests. In addition to this, a data set having more relationships, such as a data set containing personal characteristics of the user or a data set containing interrelationships between commodities, may also be used as the model target data set. According to work that has been done so far, the collection of data sets can be done as follows:
(1) the existing public data sets, such as Ciao, Epionins, Yelp data sets and the like, are directly collected, the data sets comprise the relations, and the data sets can be directly used in the neural network of the heterogeneous graph after simple preprocessing.
(2) The data set is collected or generated by the network service provider, the data can be collected by the network service provider, and the user social relationship or commodity category relationship can be generated by other data such as user-commodity interaction data and the like by a general user.
After data collection, if no cold start requirement exists, users and commodities without user-commodity interaction are removed from the data set when the data set is constructed, and effective data can be prevented from being polluted to a certain extent. And then sequencing the user-commodity interaction historical data according to time, wherein the last two interaction records of each user are respectively used as a verification set and a test set, and the rest interaction historical records are used as training sets. And for users with the user-commodity interaction quantity less than three, the user-commodity interaction quantity can not be put into the verification set or the test set. For the validation set and the test set, negative sampling is performed while constructing the data set to ensure reproducibility of subsequent results.
S2, preprocessing, randomly selecting a user set and a related commodity set from the data set, sampling and drawing a multi-level graph, and taking the graph as the input of the neural network of the heterogeneous graph.
The input of the heteromorphic graph neural network is a graph containing social relations among users, user-commodity interaction history and commodity category information, so that a sample is required to be sampled and mapped, and the method mainly comprises the following two steps:
(1) and randomly selecting user commodity pairs of the data set, if the commodity pairs are not subjected to negative sampling, further performing commodity negative sampling, and taking the users, the commodities and the negative sampling commodities in the selected set as seed nodes of the graph sampling.
(2) And carrying out multi-order graph sampling on the seed nodes, determining the order and the number of sampling points of each order, and then carrying out graph sampling. And finally, taking a graph constructed by the sampled nodes and the edges with the relations involved in the sampling process as an input graph of the heterogeneous graph neural network.
And S3, extracting node characteristics, inputting the constructed graph into a heterogeneous graph neural network comprising a plurality of heterogeneous graph memory network layers for processing, and obtaining a fusion node embedded vector of the nodes.
And (4) node feature extraction, namely firstly obtaining an initial embedded matrix by all nodes on the graph constructed by preprocessing according to an initial embedded vector table. And then inputting the initial embedded matrix into a heterogeneous graph memory network layer, and obtaining an output node embedded matrix. Repeating the process for several times to obtain node embedded matrixes under different levels, wherein the output of each layer of heterogeneous graph memory network layer corresponds to different node characteristics. The shallow features better describe the nodes themselves and the neighbor features directly connected to the nodes, while the deep features derive the high-level abstract features of the nodes. And the output of the final heterogeneous graph neural network of a certain node is subjected to fusion by standardizing the initial embedded vector of the node and the embedded vector output by each layer of heterogeneous graph memory network layer to obtain a fusion node embedded vector of the node.
In a preferred embodiment, as shown in FIG. 3, the heterogeneous neural network comprises a multi-layer hopping junction neural network and a user-embedded vector recalibration network, connected in series.
The multi-layer hopping nodes used by the multi-layer hopping connection neural network are connected, each layer of graph network layer (heterogeneous graph memory network layer) is connected with the final output in a hopping mode, the problem that the gradient of the network disappears can be avoided, and meanwhile, more layers of information can be reserved by the output of the multi-layer graph neural network. The output of each layer of the graph neural network corresponds to the aggregation information of a plurality of orders of neighbors, the low-order features describe more features of the user or the commodity object, the difference between the features of the nodes of the same type is larger, the distinction between the objects is stronger, the high-order features describe more common features of the nodes in the certain order of the neighborhood of the object, the difference between the features of the nodes of the same type is relatively smaller, and certain class of features and features of the user or the commodity object can be better described. And finally, the input features, the low-order features and the high-order features are fused, and the fused features can better describe the features of the user and the commodity and make the features of the user and the commodity more distinctive.
Specifically, the node features are extracted, and as shown in fig. 2, an initial embedding matrix H is obtained by first passing all the nodes on the graph through an initial embedding vector table(0)Then input it into the containerThe graph neural networks of a plurality of layers are processed, each layer of the graph neural networks is correspondingly embedded with the feature representation in the neighborhood of different orders, the features of lower orders describe more the features of the user or the commodity object, the features of higher orders describe more the common features of nodes in the neighborhood of certain orders of the user or the commodity object, and the final output features are the fusion of the multi-order graph neural network output, so the multi-order features of different orders can be obtained through the graph neural network output.
Specifically, the step of extracting the fusion node embedding vector of the node includes:
(1) inputting the graph constructed in the step S2 into a neural network of a heterogeneous graph, and obtaining an initial embedded vector of a node through an initial embedded vector table;
(2) through a plurality of layers of heterogeneous graph memory network layers, the operation of each layer of heterogeneous graph memory network layer comprises the following steps:
1) and performing feature extraction of the edge end point on each edge in the graph by using a memory enhanced heterogeneous relation encoder. Wherein the memory-enhanced heterogeneous relationship encoder comprises the operations of:
a) obtaining the coefficient of each memory unit of the memory-enhanced heterogeneous relation encoder of the lower end point of the corresponding relation of the edges by using the bias linear transformation of the learnable band after the activation function is activated;
b) and performing linear transformation on the embedded vector of the lower starting point of the corresponding relation of the sides by using the sum of the products of all the memory units and the corresponding coefficients thereof as a transformation matrix.
2) And fusing the messages received by each node, wherein the expression form of the message fusion function in different types of nodes is as follows:
for the user node, the message fusion function is expressed as the sum of the normalized social relationship of the user node and the messages obtained by the user-commodity interaction history through the memory enhanced heterogeneous relationship encoder.
For the commodity node, the message fusion function is expressed as the sum of the normalized user-commodity interaction history of the commodity node and the normalized commodity generic relation obtained by the memory enhanced heterogeneous relation encoder.
For the commodity category node, the message fusion function is expressed as the sum of the messages of the normalized commodity category node commodity generic relationship obtained by the memory enhanced heterogeneous relationship encoder.
3) The output embedded vector after the fusion of each node message can be directly used as the node output embedded vector output by the heterogeneous graph memory network layer. Or, further, Layernorm can be used for standardization, and the output of a memory-enhanced heterogeneous relation encoder using a self-loop is added to be used as a node output embedded vector of the final output of the memory network layer of the heterogeneous graph, so that the stability of the model during training is enhanced.
(3) And after the node output embedded vectors of each layer of the heteromorphic image memory network layer are obtained, fusing the node output embedded vectors to obtain fusion node embedded vectors of the nodes. The fusion method comprises the following steps: and splicing the node initial embedded vector with the output of each layer of the heteromorphic graph memory network layer, and normalizing by using Layernorm.
The specific structure of each layer of the neural network is as follows (taking the l-th layer as an example):
(1) input graph G ═ V, E, a, B), and input graph node embedding matrix H(l-1). Where each node V ∈ V and each edge E ∈ E are associated with its mapping function V → A and E → B, which are a set of point types and a set of edge relationships, respectively. The input graph node embedded matrix is the output of the previous layer of the graph neural network, and the first layer is the initial embedded matrix obtained through the initial embedded vector table.
(2) For a certain node t of the graph, the vector H is embedded in the output of the ith layer of the graph neural network(l)[t]Can be described by the following formula:
wherein: n (t) represents the (starting) neighbor set of node t, es，tAn edge connecting node s and node t is represented,
for memory-enhancing heterogeneous relation encoders, Aggre (.)Then it is a message fusion function; h(l-1)[t]Embedding a vector for the input of node t, H(l-1)[s]To pass through the edge es，tThe input of the start point s embeds a vector.
The memory-enhanced heterogeneous relation encoder is used for capturing heterogeneous relation characteristics, and different memory units are introduced into heterogeneous relations determined by different node types and edge types to achieve heterogeneous relation characteristic capture. Given the number of memory units M for a particular type of relationship, the memory-enhanced heterogeneous relationship encoder can be described by the following equation:
wherein: eta (-) represents specific coefficient function of target node, and has the structure of activation value and parameter of activation function of target node after mathematical tape bias linear transformation
And bmAll are parameters that can be learned. Memory unit of memory enhanced heterogeneous relation encoder
Are also mathematical parameters.
The output of the memory-enhanced heterogeneous relation encoder is obtained by the product of the sum of the output products of each memory unit and the corresponding target node specific coefficient function and the embedded vector of the given specific type relation starting point. In practice, the activation function σ () may be freely selected, and in this embodiment, taking LeakyReLU as an example, σ (x) ═ max (x, α x) may be selected as the activation function, where the negative slope α may take any value within the interval [0, 1 ].
The message fusion function Aggre (-) is also different for different types of nodes:
in a preferred embodimentIn an embodiment, for user node uiAnd its social relation S corresponds to
And the corresponding neighbors of the user on the user-commodity interaction history Y
The message fusion function can be described by the following formula:
wherein:
for user node uiThe number of social neighbors of (a),
for user node uiThe number of interaction histories.
For commodity node vjThe message includes two parts from the user and from the category relationship, and the message fusion function can be expressed as the following formula:
wherein:
is a commodity vjR is the commodity vjAnd associating certain category relation nodes.
The node r of the category relationship between the commodities can be described by the following formula:
wherein: n is a radical ofrRepresenting the neighbors of the class relationship node r.
Preferably, the output of the fused message is embedded into a vector, and normalization through Layernorm can be selected and a self-loop is added to enhance the stability of the model during training. For a certain point t of the graph, this process can be expressed as the following equation:
wherein: w is a1And w2For learnable scaling and bias parameters, μ and σ represent the output embedding vector H, respectively(l)[t]Mean and variance of.
(3) And after the node output embedded vectors of each layer of the graph neural network are obtained, fusing the node output embedded vectors to obtain fusion node embedded vectors of the nodes.
For a certain node t of the graph, the fusion node embedding vector can be described by the following formula:
wherein H(0)[t]Representing the node initial embedded vector.
If Layernorm is not selected for use in (2), the fusion process can be described using the following equation:
H*[t]＝Layernorm(H(0)[t]||H(1)[t]||…||H(l)[t])
for the commodity nodes which do not need to be subjected to the recalibration step, the fusion node embedded vectors of the commodity nodes are the commodity fusion embedded vectors in the prediction stage.
And S4, recalibrating the user fusion node embedded vector obtained in the feature extraction stage to obtain a user final representation embedded vector.
The user fusion node embedded vector obtained by the multilayer jump connection neural network needs to be recalibrated by a user embedded vector recalibration network to obtain the user final representation embedded vector. The recalibration method is to add the user fusion node embedded vector and the convolution result of the user node containing the self-loop first-order graph in the social relation to obtain the user final representation embedded vector.
And recalibrating the embedded vector of the user fusion node, namely performing pooling operation on the user and the social relation connection node of the user, wherein recalibration output is the user final representation embedded vector.
The user fusion node embedded vector is recalibrated, so that the user embedded vector is influenced by social friends of the user more greatly, and the final recommendation effect can be improved in the actual process. User uiThe recalibration result of (a) can be described by the following formula:
and S5, recommending and predicting, performing preference prediction by using the user final expression embedded vector and the commodity fusion embedded vector, and obtaining a recommendation sequence.
In the recommendation prediction stage, the embedded vectors of the nodes corresponding to the target users and the target commodities are used for prediction, and the logic value prediction can be performed in the simplest inner product mode. And the commodity recommendation sequence is arranged according to the logic value descending order.
The result of the network prediction is determined by the inner product of the user final expression embedded vector and the commodity fusion embedded vector after recalibration, and the larger the value is, the higher the preference degree of the user to the commodity is, and vice versa. And finally, determining the result of the recommendation sequence according to the value in a descending order, wherein the commodity corresponding to the prediction result with the maximum value is the commodity with the strongest preference of the user. For a data set with negative sampling, the forecast commodity set is a union set of a positive sample set and a negative sample set, and the final recommendation result is determined according to the recommendation value of the set.
Recommending a prediction stage to a target user uiAnd target commodity vjThe prediction function is defined as follows:
ξ(ui,vj)＝τ(H*[ui])·H*[vj]
the larger the predicted value is, the larger the user uiFor commodity vjThe stronger the preference degree of (2), the recommended commodity sequence is in descending order according to the size of the predicted value.
In one embodiment, the method further comprises:
and S6, monitoring the prediction result in a heterogeneous graph neural network training stage so as to optimize network parameters.
The heterogeneous neural network training phase uses BPRLoss as a loss function to supervise and then backpropagate the gradient into the network.
Training phase, for user uiAnd a sample commodity vj+And a negative sample commodity vj-And the output predicted value needs to be supervised and trained, and the loss of training can be defined as follows:
wherein the training data set O { (i, j)+,j-)|(i,j+)∈Y+,(i,j-)∈Y-I.e. user uiAnd history of user-goods interactions Y occurring in the data set+Middle sample commodity vj+And user-goods interaction history Y not present in the dataset-Commodity of medium load sample vj-Subscripts corresponding to the constituent triplets. Theta is a training parameter, delta (-) is a sigmoid function, and lambda is a regularization adjustment factor, and a suitable value can be selected according to actual conditions.
The optimization goal is to minimize the loss of training, and the process can be optimized by calculating the gradient of the loss to each parameter and then using a back propagation algorithm to perform model optimization.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, simplifications, substitutions, and combinations which do not depart from the spirit and principle of the present invention should be regarded as equivalent substitutions and are included in the scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110296182.1A CN112990972B (en) | 2021-03-19 | 2021-03-19 | A Recommendation Method Based on Heterogeneous Graph Neural Network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110296182.1A CN112990972B (en) | 2021-03-19 | 2021-03-19 | A Recommendation Method Based on Heterogeneous Graph Neural Network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112990972A true CN112990972A (en) | 2021-06-18 |
| CN112990972B CN112990972B (en) | 2022-11-18 |
Family
ID=76333501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110296182.1A Active CN112990972B (en) | 2021-03-19 | 2021-03-19 | A Recommendation Method Based on Heterogeneous Graph Neural Network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990972B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392334A (en) * | 2021-06-29 | 2021-09-14 | 长沙理工大学 | False comment detection method in cold start environment |
| CN113409121A (en) * | 2021-06-29 | 2021-09-17 | 南京财经大学 | Cross-border e-commerce recommendation method based on heterogeneous graph expression learning |
| CN113609398A (en) * | 2021-08-17 | 2021-11-05 | 石家庄铁道大学 | A social recommendation method based on heterogeneous graph neural network |
| CN113688574A (en) * | 2021-09-08 | 2021-11-23 | 北京邮电大学 | Post-processing confidence correction method applied to GNN (GNN-based topological perception) |
| CN113849725A (en) * | 2021-08-19 | 2021-12-28 | 齐鲁工业大学 | A social recommendation method and system based on graph attention adversarial network |
| CN114036382A (en) * | 2021-11-09 | 2022-02-11 | 胜斗士(上海)科技技术发展有限公司 | Method and system for generating recommendation information |
| CN114037473A (en) * | 2021-11-04 | 2022-02-11 | 东南大学 | Shop site selection recommendation method under instant distribution scene |
| CN114169938A (en) * | 2021-12-13 | 2022-03-11 | 平安国际智慧城市科技股份有限公司 | Information push method, device, device and storage medium |
| CN114265978A (en) * | 2021-12-15 | 2022-04-01 | 上海电力大学 | A new method for combining knowledge graph hierarchical information with recommendation system |
| CN114417161A (en) * | 2022-01-21 | 2022-04-29 | 杭州碧游信息技术有限公司 | Virtual article time sequence recommendation method, device, medium and equipment based on special-purpose map |
| CN114925268A (en) * | 2022-04-29 | 2022-08-19 | 华南理工大学 | Recommendation method and system based on graph neural network, electronic device and computer readable medium |
| CN115082147A (en) * | 2022-06-14 | 2022-09-20 | 华南理工大学 | Sequence recommendation method and device based on hypergraph neural network |
| CN115082142A (en) * | 2022-05-10 | 2022-09-20 | 华南理工大学 | Recommendation method, device and medium based on heterogeneous relational graph neural network |
| CN115099886A (en) * | 2022-05-25 | 2022-09-23 | 华南理工大学 | Long and short interest sequence recommendation method and device and storage medium |
| CN115115404A (en) * | 2022-06-28 | 2022-09-27 | 支付宝(杭州)信息技术有限公司 | A method and device for processing user characterization |
| CN116662676A (en) * | 2023-06-09 | 2023-08-29 | 北京华品博睿网络技术有限公司 | Online recruitment bidirectional reciprocity recommendation system and method based on multi-behavior modeling |
| CN117390266A (en) * | 2023-10-08 | 2024-01-12 | 宁夏大学 | Project recommendation method based on high-order neighbor generation algorithm and heterogeneous graph neural network |
| CN119149832A (en) * | 2024-11-15 | 2024-12-17 | 杭州心智医联科技有限公司 | Next destination recommending method, system and medium based on co-occurrence pattern mining |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150149484A1 (en) * | 2013-11-22 | 2015-05-28 | Here Global B.V. | Graph-based recommendations service systems and methods |
| US20190278378A1 (en) * | 2018-03-09 | 2019-09-12 | Adobe Inc. | Utilizing a touchpoint attribution attention neural network to identify significant touchpoints and measure touchpoint contribution in multichannel, multi-touch digital content campaigns |
| CN110610715A (en) * | 2019-07-29 | 2019-12-24 | 西安工程大学 | A Noise Reduction Method Based on CNN-DNN Hybrid Neural Network |
| CN111428147A (en) * | 2020-03-25 | 2020-07-17 | 合肥工业大学 | Social recommendation method of heterogeneous graph volume network combining social and interest information |
| CN111523047A (en) * | 2020-04-13 | 2020-08-11 | 中南大学 | Multi-relational collaborative filtering algorithm based on graph neural network |
| US20210027146A1 (en) * | 2018-10-23 | 2021-01-28 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for determining interest of user for information item |
-
2021
- 2021-03-19 CN CN202110296182.1A patent/CN112990972B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150149484A1 (en) * | 2013-11-22 | 2015-05-28 | Here Global B.V. | Graph-based recommendations service systems and methods |
| US20190278378A1 (en) * | 2018-03-09 | 2019-09-12 | Adobe Inc. | Utilizing a touchpoint attribution attention neural network to identify significant touchpoints and measure touchpoint contribution in multichannel, multi-touch digital content campaigns |
| US20210027146A1 (en) * | 2018-10-23 | 2021-01-28 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for determining interest of user for information item |
| CN110610715A (en) * | 2019-07-29 | 2019-12-24 | 西安工程大学 | A Noise Reduction Method Based on CNN-DNN Hybrid Neural Network |
| CN111428147A (en) * | 2020-03-25 | 2020-07-17 | 合肥工业大学 | Social recommendation method of heterogeneous graph volume network combining social and interest information |
| CN111523047A (en) * | 2020-04-13 | 2020-08-11 | 中南大学 | Multi-relational collaborative filtering algorithm based on graph neural network |
Non-Patent Citations (1)
| Title |
|---|
| 蒋宗礼等: "基于融合元路径的图神经网络协同过滤算法", 《计算机系统应用》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392334B (en) * | 2021-06-29 | 2024-03-08 | 长沙理工大学 | False comment detection method in cold start environment |
| CN113409121A (en) * | 2021-06-29 | 2021-09-17 | 南京财经大学 | Cross-border e-commerce recommendation method based on heterogeneous graph expression learning |
| CN113392334A (en) * | 2021-06-29 | 2021-09-14 | 长沙理工大学 | False comment detection method in cold start environment |
| CN113409121B (en) * | 2021-06-29 | 2022-02-15 | 南京财经大学 | Cross-border e-commerce recommendation method based on heterogeneous graph expression learning |
| CN113609398A (en) * | 2021-08-17 | 2021-11-05 | 石家庄铁道大学 | A social recommendation method based on heterogeneous graph neural network |
| CN113609398B (en) * | 2021-08-17 | 2023-09-19 | 石家庄铁道大学 | Social recommendation method based on heterogeneous graph neural network |
| CN113849725A (en) * | 2021-08-19 | 2021-12-28 | 齐鲁工业大学 | A social recommendation method and system based on graph attention adversarial network |
| CN113688574A (en) * | 2021-09-08 | 2021-11-23 | 北京邮电大学 | Post-processing confidence correction method applied to GNN (GNN-based topological perception) |
| CN114037473B (en) * | 2021-11-04 | 2025-02-21 | 东南大学 | Store location recommendation method in instant delivery scenario |
| CN114037473A (en) * | 2021-11-04 | 2022-02-11 | 东南大学 | Shop site selection recommendation method under instant distribution scene |
| CN114036382A (en) * | 2021-11-09 | 2022-02-11 | 胜斗士(上海)科技技术发展有限公司 | Method and system for generating recommendation information |
| CN114169938A (en) * | 2021-12-13 | 2022-03-11 | 平安国际智慧城市科技股份有限公司 | Information push method, device, device and storage medium |
| CN114265978A (en) * | 2021-12-15 | 2022-04-01 | 上海电力大学 | A new method for combining knowledge graph hierarchical information with recommendation system |
| CN114417161A (en) * | 2022-01-21 | 2022-04-29 | 杭州碧游信息技术有限公司 | Virtual article time sequence recommendation method, device, medium and equipment based on special-purpose map |
| CN114925268A (en) * | 2022-04-29 | 2022-08-19 | 华南理工大学 | Recommendation method and system based on graph neural network, electronic device and computer readable medium |
| CN114925268B (en) * | 2022-04-29 | 2024-12-03 | 华南理工大学 | Recommendation method, system, electronic device and computer-readable medium based on graph neural network |
| CN115082142A (en) * | 2022-05-10 | 2022-09-20 | 华南理工大学 | Recommendation method, device and medium based on heterogeneous relational graph neural network |
| CN115082142B (en) * | 2022-05-10 | 2024-04-30 | 华南理工大学 | A recommendation method, device and medium based on heterogeneous relationship graph neural network |
| CN115099886A (en) * | 2022-05-25 | 2022-09-23 | 华南理工大学 | Long and short interest sequence recommendation method and device and storage medium |
| CN115099886B (en) * | 2022-05-25 | 2024-04-19 | 华南理工大学 | A method, device and storage medium for recommending long and short interest sequences |
| CN115082147B (en) * | 2022-06-14 | 2024-04-19 | 华南理工大学 | A sequence recommendation method and device based on hypergraph neural network |
| CN115082147A (en) * | 2022-06-14 | 2022-09-20 | 华南理工大学 | Sequence recommendation method and device based on hypergraph neural network |
| CN115115404A (en) * | 2022-06-28 | 2022-09-27 | 支付宝(杭州)信息技术有限公司 | A method and device for processing user characterization |
| CN116662676A (en) * | 2023-06-09 | 2023-08-29 | 北京华品博睿网络技术有限公司 | Online recruitment bidirectional reciprocity recommendation system and method based on multi-behavior modeling |
| CN117390266A (en) * | 2023-10-08 | 2024-01-12 | 宁夏大学 | Project recommendation method based on high-order neighbor generation algorithm and heterogeneous graph neural network |
| CN117390266B (en) * | 2023-10-08 | 2024-04-30 | 宁夏大学 | Project recommendation method based on high-order neighbor generation algorithm and heterogeneous graph neural network |
| CN119149832A (en) * | 2024-11-15 | 2024-12-17 | 杭州心智医联科技有限公司 | Next destination recommending method, system and medium based on co-occurrence pattern mining |
| CN119149832B (en) * | 2024-11-15 | 2025-02-07 | 杭州心智医联科技有限公司 | Next destination recommendation method, system and medium based on co-occurrence pattern mining |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112990972B (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112990972A (en) | Recommendation method based on heterogeneous graph neural network | |
| CN115082142B (en) | A recommendation method, device and medium based on heterogeneous relationship graph neural network | |
| Lima et al. | Domain knowledge integration in data mining using decision tables: case studies in churn prediction | |
| CN112131480A (en) | Personalized product recommendation method and system based on multi-layer heterogeneous attribute network representation learning | |
| CN113314231B (en) | Infectious disease propagation prediction system and device integrating spatio-temporal information | |
| CN115358809B (en) | A multi-intention recommendation method and device based on graph contrast learning | |
| CN114780831A (en) | Sequence recommendation method and system based on Transformer | |
| CN115982467A (en) | Multi-interest recommendation method and device for depolarized user and storage medium | |
| CN116308685B (en) | Product recommendation method and system based on aspect emotion prediction and collaborative filtering | |
| CN117633371B (en) | Recommendation method, device and readable storage medium based on multi-attention mechanism | |
| WO2024114034A1 (en) | Content recommendation method and apparatus, device, medium, and program product | |
| CN118917929A (en) | Gift recommending method and system based on user portrait | |
| CN116069921A (en) | News Recommendation Method Combining Activation Diffusion Theory and Ebbinghaus Forgetting Theory | |
| Byeon et al. | Deep learning model for recommendation system using web of things based knowledge graph mining | |
| CN118313446B (en) | Causal meta-learning multi-view graph learning method and device for cold start scenarios | |
| CN112052995B (en) | Social network user influence prediction method based on fusion emotion tendency theme | |
| WO2024114618A1 (en) | Method for detecting abnormal event, and method and apparatus for constructing abnormal-event detection model | |
| CN116933049A (en) | Feature selection method, device, electronic equipment and storage medium | |
| CN115203557A (en) | Method, device, equipment, storage medium and product for generating content recommendation model | |
| Prasad et al. | Bilinear diffusion graph convolutional network model for social recommendation | |
| Wang et al. | A spatio-temporal graph wavelet neural network (ST-GWNN) for association mining in timely social media data | |
| CN116628310B (en) | Content recommendation method, device, equipment, medium and computer program product | |
| CN114943588B (en) | Commodity recommendation method based on neural network noise data | |
| EP4156046A1 (en) | Operation prediction device, model training method for same, and operation prediction method | |
| CN119939015A (en) | Graph convolutional network recommendation method and device integrating multiple behaviors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |