CN116416655A - Theme prediction method and device based on joint learning - Google Patents

Theme prediction method and device based on joint learning Download PDF

Info

Publication number
CN116416655A
CN116416655A CN202111637178.3A CN202111637178A CN116416655A CN 116416655 A CN116416655 A CN 116416655A CN 202111637178 A CN202111637178 A CN 202111637178A CN 116416655 A CN116416655 A CN 116416655A
Authority
CN
China
Prior art keywords
participant
model
participants
joint learning
target
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.)
Pending
Application number
CN202111637178.3A
Other languages
Chinese (zh)
Inventor
张敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xinzhi I Lai Network Technology Co ltd
Original Assignee
Xinzhi I Lai Network Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xinzhi I Lai Network Technology Co ltd filed Critical Xinzhi I Lai Network Technology Co ltd
Priority to CN202111637178.3A priority Critical patent/CN116416655A/en
Publication of CN116416655A publication Critical patent/CN116416655A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The disclosure relates to the technical field of joint learning, and provides a method and a device for predicting a theme based on joint learning. The method comprises the following steps: acquiring a topic of joint learning, and training a neural network model according to the topic and training data sets of a plurality of participants to obtain a network model corresponding to each participant; obtaining model parameters of a network model corresponding to each participant; aggregating model parameters of network models corresponding to a plurality of participants to obtain global parameters; updating model parameters of the neural network model based on the global parameters to obtain a joint learning model; and predicting the data to be predicted by using the joint learning model to obtain a first prediction result. By adopting the technical means, the problem that in the prior art, in joint learning, training is directly performed by using training data sets of a plurality of participants, and the accuracy of the prediction result of the obtained model is low is solved.

Description

Theme prediction method and device based on joint learning
Technical Field
The disclosure relates to the technical field of joint learning, in particular to a method and a device for predicting a theme based on joint learning.
Background
In joint learning, a neural network model is often trained through training data sets of a plurality of participants to obtain a network model of each participant, and a joint learning model of a training center is obtained according to the network model of each participant, so that prediction is performed by using the joint learning model. The training data set of each participant is acquired by each participant, and because each participant can acquire various data during acquisition, the training data sets of a plurality of participants are directly used for training the neural network model, the acquired network model and the joint learning model of each participant have low precision, and the prediction accuracy is low.
In the process of implementing the disclosed concept, the inventor finds that at least the following technical problems exist in the related art: in joint learning, training is directly performed by using training data sets of a plurality of participants, and the accuracy of the prediction result of the obtained model is low.
Disclosure of Invention
In view of this, the embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a computer readable storage medium for predicting a topic based on joint learning, so as to solve the problem in the prior art that in joint learning, training is directly performed by using training data sets of multiple participants, and the accuracy of a prediction result of an obtained model is low.
In a first aspect of an embodiment of the present disclosure, there is provided a method for predicting a topic based on joint learning, including: acquiring a topic of joint learning, and training a neural network model according to the topic and training data sets of a plurality of participants to obtain a network model corresponding to each participant; obtaining model parameters of a network model corresponding to each participant; aggregating model parameters of network models corresponding to a plurality of participants to obtain global parameters; updating model parameters of the neural network model based on the global parameters to obtain a joint learning model; and predicting the data to be predicted by using the joint learning model to obtain a first prediction result.
In a second aspect of the embodiments of the present disclosure, there is provided a prediction apparatus based on a topic of joint learning, including: the training model is configured to acquire a topic of joint learning, train the neural network model according to the topic and training data sets of a plurality of participants, and acquire a network model corresponding to each participant; the method comprises the steps of obtaining a model, wherein the model is configured to obtain model parameters of a network model corresponding to each participant; the aggregation model is configured to aggregate model parameters of the network model corresponding to the multiple participants to obtain global parameters; the updating model is configured to update model parameters of the neural network model based on the global parameters to obtain a joint learning model; and the prediction model is configured to predict the data to be predicted by utilizing the joint learning model to obtain a first prediction result.
In a third aspect of the disclosed embodiments, an electronic device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect of the disclosed embodiments, a computer-readable storage medium is provided, which stores a computer program which, when executed by a processor, implements the steps of the above-described method.
Compared with the prior art, the embodiment of the disclosure has the beneficial effects that: acquiring a topic of joint learning, and training a neural network model according to the topic and training data sets of a plurality of participants to obtain a network model corresponding to each participant; obtaining model parameters of a network model corresponding to each participant; aggregating model parameters of network models corresponding to a plurality of participants to obtain global parameters; updating model parameters of the neural network model based on the global parameters to obtain a joint learning model; and predicting the data to be predicted by using the joint learning model to obtain a first prediction result. By adopting the technical means, the problem that in the prior art, in joint learning, the accuracy of the prediction result of the obtained model is low by directly training by using training data sets of a plurality of participants can be solved, and the accuracy of the prediction result of the model in joint learning is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required for the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic diagram of a joint learning architecture according to an embodiment of the present disclosure;
FIG. 2 is a flow diagram of a method for predicting a topic based on joint learning provided in an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a prediction apparatus based on a topic of joint learning according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.
The joint learning refers to comprehensively utilizing a plurality of AI (Artificial Intelligence ) technologies on the premise of ensuring data safety and user privacy, jointly excavating data value by combining multiparty cooperation, and promoting new intelligent business states and modes based on joint modeling. The joint learning has at least the following characteristics:
(1) The participating nodes control the weak centralized joint training mode of the own data, so that the data privacy safety in the co-creation intelligent process is ensured.
(2) Under different application scenes, a plurality of model aggregation optimization strategies are established by utilizing screening and/or combination of an AI algorithm and privacy protection calculation so as to obtain a high-level and high-quality model.
(3) On the premise of ensuring data safety and user privacy, a method for improving the efficiency of the joint learning engine is obtained based on a plurality of model aggregation optimization strategies, wherein the efficiency method can be used for improving the overall efficiency of the joint learning engine by solving the problems of information interaction, intelligent perception, exception handling mechanisms and the like under a large-scale cross-domain network with parallel computing architecture.
(4) The requirements of multiparty users in all scenes are acquired, the real contribution degree of all joint participants is determined and reasonably evaluated through a mutual trust mechanism, and distribution excitation is carried out.
Based on the mode, AI technical ecology based on joint learning can be established, the industry data value is fully exerted, and the scene of the vertical field is promoted to fall to the ground.
A prediction method and apparatus based on a joint learning topic according to an embodiment of the present disclosure will be described in detail with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a joint learning architecture according to an embodiment of the present disclosure. As shown in fig. 1, the architecture of joint learning may include a server (central node) 101, as well as participants 102, 103, and 104.
In the joint learning process, a basic model may be established by the server 101, and the server 101 transmits the model to the participants 102, 103, and 104 with which a communication connection is established. The basic model may also be uploaded to the server 101 after any party has established, and the server 101 sends the model to the other parties with whom it has established a communication connection. The participants 102, 103 and 104 construct a model according to the downloaded basic structure and model parameters, perform model training using local data, obtain updated model parameters, and encrypt and upload the updated model parameters to the server 101. Server 101 aggregates the model parameters sent by participants 102, 103, and 104 to obtain global model parameters, and transmits the global model parameters back to participants 102, 103, and 104. Participant 102, participant 103 and participant 104 iterate the respective models according to the received global model parameters until the models eventually converge, thereby enabling training of the models. In the joint learning process, the data uploaded by the participants 102, 103 and 104 are model parameters, local data is not uploaded to the server 101, and all the participants can share final model parameters, so that common modeling can be realized on the basis of ensuring data privacy. It should be noted that the number of participants is not limited to the above three, but may be set as needed, and the embodiment of the present disclosure is not limited thereto.
Fig. 2 is a flowchart of a method for predicting a topic based on joint learning according to an embodiment of the disclosure. The prediction method of the joint learning-based topic of fig. 2 may be performed by the server of fig. 1. As shown in fig. 2, the method for predicting the topic based on the joint learning includes:
s201, acquiring a topic of joint learning, and training a neural network model according to the topic and training data sets of a plurality of participants to obtain a network model corresponding to each participant;
s202, obtaining model parameters of a network model corresponding to each participant;
s203, aggregating model parameters of network models corresponding to a plurality of participants to obtain global parameters;
s204, updating model parameters of the neural network model based on the global parameters to obtain a joint learning model;
s205, predicting the data to be predicted by using the joint learning model to obtain a first prediction result.
Because various data can be collected by each participant during collection, if the neural network model is directly trained by using training data sets of a plurality of participants, the accuracy of the obtained prediction results of the network model and the joint learning model of each participant is low. To address the above-described problems, embodiments of the present disclosure train a neural network model based on a jointly learned topic and training data sets of multiple participants. The data of each participant under the topic may be selected from the training data set of each participant prior to performing the joint learning training, and the data of each participant under the topic may be formed into the target training data set of each participant. For example, the combined learning is based on face recognition, the training data set of each participant includes face samples and samples of other animals, and the data of each participant belonging to face recognition is formed into the target training data set of each participant.
According to the technical scheme provided by the embodiment of the disclosure, a topic of joint learning is obtained, and a neural network model is trained according to the topic and training data sets of a plurality of participants, so that a network model corresponding to each participant is obtained; obtaining model parameters of a network model corresponding to each participant; aggregating model parameters of network models corresponding to a plurality of participants to obtain global parameters; updating model parameters of the neural network model based on the global parameters to obtain a joint learning model; and predicting the data to be predicted by using the joint learning model to obtain a first prediction result. By adopting the technical means, the problem that in the prior art, in joint learning, the accuracy of the prediction result of the obtained model is low by directly training by using training data sets of a plurality of participants can be solved, and the accuracy of the prediction result of the model in joint learning is further improved.
In step S201, a topic of joint learning is acquired, and a neural network model is trained according to the topic and training data sets of a plurality of participants, so as to obtain a network model corresponding to each participant, including: according to the theme, determining a target training data set corresponding to each participant from the training data set of each participant; and training the neural network model according to the target training data set corresponding to each participant to obtain a network model corresponding to each participant.
It may be understood that the operations of classifying and dividing the training data set of each participant according to different topics divide the training data set of each participant into a plurality of topic data, and the target training data set of each participant is composed using the topic data in the topic data of each participant. For example, the subjects of joint learning are face recognition, and a training data set of a participant has a face sample, a cat sample and a dog sample, so that the training data set of the participant can be divided into three subjects of face subjects, cat subjects and dog subjects, and the face sample under the face subjects forms a target training data set of the participant.
After performing step S205, that is, predicting the data to be predicted by using the joint learning model, to obtain a first prediction result, the method further includes: determining a first target participant from a plurality of participants according to the theme; predicting data to be predicted by using a network model of the first target participant to obtain a second prediction result; updating the first prediction result by using the second prediction result.
In the past practice, it is found that if only a joint learning model is used to predict data to be predicted, the accuracy of the prediction result is not high, but the accuracy of the prediction result of a network model of a certain participant which is particularly in line with the subject of the joint learning is high. Updating the first prediction result by using the second prediction result. It is understood that a new prediction result is obtained using the second prediction result and the first prediction result.
According to the subject matter, determining a first target participant from a plurality of participants includes: acquiring a basic data set corresponding to a theme; calculating the similarity of the basic data set and the training data set of each participant; and determining the participant with the highest similarity as the first target participant.
The similarity may be a common similarity such as cosine similarity. The underlying data set is maintained in a training center.
After determining the first target participant from the plurality of participants according to the subject matter, the method further includes: determining a common sample of the training data set of the first target participant and the training data sets of each of the other participants through a sample alignment operation; determining the participants with the number of the public samples larger than a preset threshold corresponding to the first target participants as second target participants to obtain a plurality of second target participants; predicting data to be predicted by using a network model of the first target participant to obtain a second prediction result; predicting the data to be predicted by utilizing the network models of the plurality of second target participants to obtain a third prediction result; and updating the first prediction result by using the second prediction result and the third prediction result.
In past practice, it was found that in joint learning, a common sample would have an effect on the accuracy of the prediction results of the joint learning model. According to the method and the device, the fact that the accuracy of the prediction result of the second target participants with the number of the common samples larger than the preset threshold value with the first target participants is high is fully considered, and the network models of the plurality of second target participants are used for predicting the data to be predicted, so that a third prediction result is obtained. Updating the first predictor with the second predictor and the third predictor may be understood as using the second predictor, the third predictor and the first predictor to obtain a new predictor. The scheme of the embodiment is suitable for the situation of more participants.
After performing step S205, that is, determining a common sample of the training data set of the first target participant and the training data sets of each of the other participants by a sample alignment operation, includes: and processing training data sets of other multiple participants by using a bloom filter to obtain a processing result corresponding to each participant, wherein the multiple participants comprise: a first target participant and other participants; and traversing the processing results corresponding to the first target participant and each other participant, and determining a common sample of the training data set of the first target participant and the training data set of each other participant, wherein the sample alignment operation comprises traversing.
The bloom filter may retrieve whether an element is in a set, and the sample alignment operation may be a traversal operation for determining common samples of other participants with the first target participant. Because each sample in the sample data of each participant can correspond to an identification number, traversing the sample or element in the processing result corresponding to each participant can be traversing the identification number corresponding to one sample in the processing result corresponding to each participant, and judging whether the sample exists or not according to whether the identification number exists in the processing result corresponding to one participant. Bloom filters (Bloom filters) were proposed by Bloom (Burton Howard Bloom) in 1970. It is actually composed of a very long binary vector and a series of random mapping functions, and bloom filters can be used to retrieve whether an element is in a set.
The other participants are participants other than the first target participant among the plurality of participants.
Updating model parameters of the neural network model based on the global parameters, and after obtaining the joint learning model, the method further comprises the following steps: calculating a contribution value of each participant to improving the precision of the joint learning model according to the first precision of the network model of each participant and the second precision of the joint learning model; distributing distribution coefficients for each participant according to the contribution value corresponding to each participant; and allocating resources for each participant based on the allocation coefficient corresponding to each participant.
The resource may be an economic benefit generated by the joint learning model, or may be a result of performing face recognition through the joint learning model in a face recognition scenario, for example. Each participant is allocated resources based on the allocation coefficients corresponding to each participant, for example, the allocation coefficients of three participants A, B, C are respectively: 3. 2, 1; the proportion of allocated resources of A, B, C is 3, 2, 1.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein in detail.
The following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, please refer to the embodiments of the method of the present disclosure.
Fig. 3 is a schematic diagram of a prediction apparatus based on a topic of joint learning according to an embodiment of the present disclosure. As shown in fig. 3, the prediction apparatus based on the topic of joint learning includes:
training a model 301, configured to obtain a topic of joint learning, training a neural network model according to the topic and training data sets of a plurality of participants, and obtaining a network model corresponding to each participant;
an acquisition model 302 configured to acquire model parameters of a network model corresponding to each participant;
an aggregation model 303, configured to aggregate model parameters of network models corresponding to a plurality of participants to obtain global parameters;
an update model 304 configured to update model parameters of the neural network model based on the global parameters, resulting in a joint learning model;
and the prediction model 305 is configured to predict the data to be predicted by using the joint learning model to obtain a first prediction result.
Because various data can be collected by each participant during collection, if the neural network model is directly trained by using training data sets of a plurality of participants, the accuracy of the obtained prediction results of the network model and the joint learning model of each participant is low. To address the above-described problems, embodiments of the present disclosure train a neural network model based on a jointly learned topic and training data sets of multiple participants. The data of each participant under the topic may be selected from the training data set of each participant prior to performing the joint learning training, and the data of each participant under the topic may be formed into the target training data set of each participant. For example, the combined learning is based on face recognition, the training data set of each participant includes face samples and samples of other animals, and the data of each participant belonging to face recognition is formed into the target training data set of each participant.
According to the technical scheme provided by the embodiment of the disclosure, a topic of joint learning is obtained, and a neural network model is trained according to the topic and training data sets of a plurality of participants, so that a network model corresponding to each participant is obtained; obtaining model parameters of a network model corresponding to each participant; aggregating model parameters of network models corresponding to a plurality of participants to obtain global parameters; updating model parameters of the neural network model based on the global parameters to obtain a joint learning model; and predicting the data to be predicted by using the joint learning model to obtain a first prediction result. By adopting the technical means, the problem that in the prior art, in joint learning, the accuracy of the prediction result of the obtained model is low by directly training by using training data sets of a plurality of participants can be solved, and the accuracy of the prediction result of the model in joint learning is further improved.
Optionally, the training model 301 is further configured to determine, according to the topic, a target training data set corresponding to each participant from the training data sets of each participant; and training the neural network model according to the target training data set corresponding to each participant to obtain a network model corresponding to each participant.
It may be understood that the operations of classifying and dividing the training data set of each participant according to different topics divide the training data set of each participant into a plurality of topic data, and the target training data set of each participant is composed using the topic data in the topic data of each participant. For example, the subjects of joint learning are face recognition, and a training data set of a participant has a face sample, a cat sample and a dog sample, so that the training data set of the participant can be divided into three subjects of face subjects, cat subjects and dog subjects, and the face sample under the face subjects forms a target training data set of the participant.
Optionally, the predictive model 305 is further configured to determine a first target participant from the plurality of participants in accordance with the topic; predicting data to be predicted by using a network model of the first target participant to obtain a second prediction result; updating the first prediction result by using the second prediction result.
In the past practice, it is found that if only a joint learning model is used to predict data to be predicted, the accuracy of the prediction result is not high, but the accuracy of the prediction result of a network model of a certain participant which is particularly in line with the subject of the joint learning is high. Updating the first prediction result by using the second prediction result. It is understood that a new prediction result is obtained using the second prediction result and the first prediction result.
Optionally, the prediction model 305 is further configured to obtain a basic data set corresponding to the topic; calculating the similarity of the basic data set and the training data set of each participant; and determining the participant with the highest similarity as the first target participant.
The similarity may be a common similarity such as cosine similarity. The underlying data set is maintained in a training center.
Optionally, the predictive model 305 is further configured to determine a common sample of the training data set of the first target participant and the training data sets of each of the other participants by a sample alignment operation; determining the participants with the number of the public samples larger than a preset threshold corresponding to the first target participants as second target participants to obtain a plurality of second target participants; predicting data to be predicted by using a network model of the first target participant to obtain a second prediction result; predicting the data to be predicted by utilizing the network models of the plurality of second target participants to obtain a third prediction result; and updating the first prediction result by using the second prediction result and the third prediction result.
In past practice, it was found that in joint learning, a common sample would have an effect on the accuracy of the prediction results of the joint learning model. According to the method and the device, the fact that the accuracy of the prediction result of the second target participants with the number of the common samples larger than the preset threshold value with the first target participants is high is fully considered, and the network models of the plurality of second target participants are used for predicting the data to be predicted, so that a third prediction result is obtained. Updating the first predictor with the second predictor and the third predictor may be understood as using the second predictor, the third predictor and the first predictor to obtain a new predictor. The scheme of the embodiment is suitable for the situation of more participants.
Optionally, the prediction model 305 is further configured to process training data sets of other multiple participants by using bloom filters to obtain a processing result corresponding to each participant, where the multiple participants include: a first target participant and other participants; and traversing the processing results corresponding to the first target participant and each other participant, and determining a common sample of the training data set of the first target participant and the training data set of each other participant, wherein the sample alignment operation comprises traversing.
The bloom filter may retrieve whether an element is in a set, and the sample alignment operation may be a traversal operation for determining common samples of other participants with the first target participant. Because each sample in the sample data of each participant can correspond to an identification number, traversing the sample or element in the processing result corresponding to each participant can be traversing the identification number corresponding to one sample in the processing result corresponding to each participant, and judging whether the sample exists or not according to whether the identification number exists in the processing result corresponding to one participant. Bloom filters (Bloom filters) were proposed by Bloom (Burton Howard Bloom) in 1970. It is actually composed of a very long binary vector and a series of random mapping functions, and bloom filters can be used to retrieve whether an element is in a set.
The other participants are participants other than the first target participant among the plurality of participants.
Optionally, the prediction model 305 is further configured to calculate a contribution value of each participant to the improvement of the precision of the joint learning model according to the first precision of the network model of each participant and the second precision of the joint learning model; distributing distribution coefficients for each participant according to the contribution value corresponding to each participant; and allocating resources for each participant based on the allocation coefficient corresponding to each participant.
The resource may be an economic benefit generated by the joint learning model, or may be a result of performing face recognition through the joint learning model in a face recognition scenario, for example. Each participant is allocated resources based on the allocation coefficients corresponding to each participant, for example, the allocation coefficients of three participants A, B, C are respectively: 3. 2, 1; the proportion of allocated resources of A, B, C is 3, 2, 1.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not constitute any limitation on the implementation process of the embodiments of the disclosure.
Fig. 4 is a schematic diagram of an electronic device 4 provided by an embodiment of the present disclosure. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: a processor 401, a memory 402 and a computer program 403 stored in the memory 402 and executable on the processor 401. The steps of the various method embodiments described above are implemented by processor 401 when executing computer program 403. Alternatively, the processor 401, when executing the computer program 403, performs the functions of the modules/units in the above-described apparatus embodiments.
Illustratively, the computer program 403 may be partitioned into one or more modules/units, which are stored in the memory 402 and executed by the processor 401 to complete the present disclosure. One or more of the modules/units may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 403 in the electronic device 4.
The electronic device 4 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the electronic device 4 and is not meant to be limiting of the electronic device 4, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may also include an input-output device, a network access device, a bus, etc.
The processor 401 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or a memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the electronic device 4. Further, the memory 402 may also include both internal storage units and external storage devices of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device. The memory 402 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
In the embodiments provided in the present disclosure, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of modules or elements is merely a logical functional division, and there may be additional divisions of actual implementations, multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method of the above-described embodiments, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiments described above. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are merely for illustrating the technical solution of the present disclosure, and are not limiting thereof; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included in the scope of the present disclosure.

Claims (10)

1. A method for predicting a topic based on joint learning, comprising:
acquiring a topic of joint learning, and training a neural network model according to the topic and training data sets of a plurality of participants to obtain a network model corresponding to each participant;
obtaining model parameters of a network model corresponding to each participant;
aggregating model parameters of network models corresponding to a plurality of participants to obtain global parameters;
updating model parameters of the neural network model based on the global parameters to obtain a joint learning model;
and predicting the data to be predicted by using the joint learning model to obtain a first prediction result.
2. The method of claim 1, wherein the obtaining the topic of joint learning, training a neural network model according to the topic and training data sets of a plurality of participants, and obtaining a network model corresponding to each participant, comprises:
according to the theme, determining a target training data set corresponding to each participant from the training data set of each participant;
and training the neural network model according to the target training data set corresponding to each participant to obtain a network model corresponding to each participant.
3. The method of claim 1, wherein the predicting the data to be predicted using the joint learning model, after obtaining the first prediction result, further comprises:
determining a first target participant from a plurality of participants according to the theme;
predicting the data to be predicted by utilizing the network model of the first target participant to obtain a second prediction result;
updating the first prediction result by using the second prediction result.
4. A method according to claim 3, wherein said determining a first target participant from a plurality of said participants in accordance with said theme comprises:
acquiring a basic data set corresponding to the theme;
calculating the similarity of the basic data set and the training data set of each participant;
and determining the participant with the highest similarity as the first target participant.
5. The method of claim 3, wherein after determining a first target participant from a plurality of the participants based on the theme, the method further comprises:
determining a common sample of the training data set of the first target participant and the training data sets of each of the other participants by a sample alignment operation;
determining the participants, corresponding to the first target participants, of which the number of the public samples is greater than a preset threshold, as second target participants, so as to obtain a plurality of second target participants;
predicting the data to be predicted by utilizing the network model of the first target participant to obtain a second prediction result;
predicting the data to be predicted by utilizing network models of a plurality of second target participants to obtain a third prediction result;
updating the first prediction result by using the second prediction result and the third prediction result.
6. The method of claim 5, wherein said determining common samples of the training data set of the first target participant and the training data sets of each of the other participants by a sample alignment operation comprises:
and processing training data sets of other multiple participants by using a bloom filter to obtain a processing result corresponding to each participant, wherein the multiple participants comprise: the first target participant and the other of the participants;
and traversing the processing results corresponding to the first target participant and each other participant, and determining a common sample of the training data set of the first target participant and the training data set of each other participant, wherein the sample alignment operation comprises traversing.
7. The method of claim 1, wherein after updating the model parameters of the neural network model based on the global parameters to obtain a joint learning model, the method further comprises:
calculating a contribution value of each participant to improving the precision of the joint learning model according to the first precision of the network model of each participant and the second precision of the joint learning model;
distributing distribution coefficients to each participant according to the contribution value corresponding to each participant;
and allocating resources for each participant based on the allocation coefficient corresponding to each participant.
8. A joint learning-based topic prediction apparatus, comprising:
the training model is configured to acquire a topic of joint learning, train the neural network model according to the topic and training data sets of a plurality of participants, and obtain a network model corresponding to each participant;
an acquisition model configured to acquire model parameters of a network model corresponding to each of the participants;
the aggregation model is configured to aggregate model parameters of the network models corresponding to the multiple participants to obtain global parameters;
updating a model, wherein the model is configured to update model parameters of the neural network model based on the global parameters to obtain a joint learning model;
and the prediction model is configured to predict the data to be predicted by utilizing the joint learning model to obtain a first prediction result.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.
CN202111637178.3A 2021-12-29 2021-12-29 Theme prediction method and device based on joint learning Pending CN116416655A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111637178.3A CN116416655A (en) 2021-12-29 2021-12-29 Theme prediction method and device based on joint learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111637178.3A CN116416655A (en) 2021-12-29 2021-12-29 Theme prediction method and device based on joint learning

Publications (1)

Publication Number Publication Date
CN116416655A true CN116416655A (en) 2023-07-11

Family

ID=87049692

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111637178.3A Pending CN116416655A (en) 2021-12-29 2021-12-29 Theme prediction method and device based on joint learning

Country Status (1)

Country Link
CN (1) CN116416655A (en)

Similar Documents

Publication Publication Date Title
CN110084377B (en) Method and device for constructing decision tree
DE112018005205T5 (en) Compression of completely connected / recurring layers from one or more deep networks by enforcing spatial locality for weight matrices and effecting frequency compression
CN111368911B (en) Image classification method and device and computer readable storage medium
CN113988310A (en) Deep learning model selection method and device, computer equipment and medium
CN111935140A (en) Abnormal message identification method and device
CN116416655A (en) Theme prediction method and device based on joint learning
WO2023109246A1 (en) Method and apparatus for breakpoint privacy protection, and device and medium
CN113887495A (en) Video labeling method and device based on transfer learning
CN116402366A (en) Data contribution evaluation method and device based on joint learning
CN114219338A (en) Resource allocation method and device based on joint learning
CN116362101A (en) Data processing method based on joint learning, data model generation method and device
CN115392491A (en) Model training method and device based on knowledge distillation and federal learning
CN116484707A (en) Determination method and device of joint learning model
CN113850390A (en) Method, device, equipment and medium for sharing data in federal learning system
CN113762972A (en) Data storage control method and device, electronic equipment and storage medium
CN116050557A (en) Power load prediction method, device, computer equipment and medium
CN116485215A (en) Resource allocation method and device in joint learning
CN117077798A (en) Method and device for generating joint learning model based on semi-supervised learning
CN114897186A (en) Joint learning training method and device
CN116304652A (en) Data heterogeneous-based joint learning model acquisition method and device
CN116384501A (en) Combined learning training method and device
CN114897185A (en) Joint learning training method and device based on category heterogeneous data
CN113887745A (en) Data heterogeneous joint learning method and device
CN117313831A (en) Combined learning training method and device based on model distillation
CN116432010A (en) Training method and device for joint learning model

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