MA65752A1 - Use of a graph attention network with edge characteristics for the analysis of temporal and spatial data in telecommunications - Google Patents

Use of a graph attention network with edge characteristics for the analysis of temporal and spatial data in telecommunications

Info

Publication number
MA65752A1
MA65752A1 MA65752A MA65752A MA65752A1 MA 65752 A1 MA65752 A1 MA 65752A1 MA 65752 A MA65752 A MA 65752A MA 65752 A MA65752 A MA 65752A MA 65752 A1 MA65752 A1 MA 65752A1
Authority
MA
Morocco
Prior art keywords
edge
graph attention
featured
attention network
sites
Prior art date
Application number
MA65752A
Other languages
French (fr)
Inventor
Maaloum Jawad
Original Assignee
Mlnetworks Sarl
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 Mlnetworks Sarl filed Critical Mlnetworks Sarl
Priority to MA65752A priority Critical patent/MA65752A1/en
Publication of MA65752A1 publication Critical patent/MA65752A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Telecommunication networks can be represented in the form of a graph, where the nodes are the telecommunication sites and the edges are the connections between two telecommunication sites. This patent covers the use of edge graph attention networks in Machine Learning to analyse telecommunication networks. The inputs to the Edge-Featured Graph attention network are past information on key performance indicators for each site and each connection between two sites. This information is processed in plunges (typically by a linear layer or some type of recurrent neural network), where it is passed to the Edge-Featured Graph attention networks. The output of the Edge-Featured Graph attention network will propagate the information into each node and edge integration. These plunges are then processed by a linear layer or recurrent neural network, giving future predictions of key performance indicators for each site (node in the Edge-Featured Graph attention network) and connection between sites (edge in the Edge-Featured Graph attention network). 
MA65752A 2024-05-10 2024-05-10 Use of a graph attention network with edge characteristics for the analysis of temporal and spatial data in telecommunications MA65752A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
MA65752A MA65752A1 (en) 2024-05-10 2024-05-10 Use of a graph attention network with edge characteristics for the analysis of temporal and spatial data in telecommunications

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
MA65752A MA65752A1 (en) 2024-05-10 2024-05-10 Use of a graph attention network with edge characteristics for the analysis of temporal and spatial data in telecommunications

Publications (1)

Publication Number Publication Date
MA65752A1 true MA65752A1 (en) 2025-11-28

Family

ID=98218033

Family Applications (1)

Application Number Title Priority Date Filing Date
MA65752A MA65752A1 (en) 2024-05-10 2024-05-10 Use of a graph attention network with edge characteristics for the analysis of temporal and spatial data in telecommunications

Country Status (1)

Country Link
MA (1) MA65752A1 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210081717A1 (en) * 2018-05-18 2021-03-18 Benevolentai Technology Limited Graph neutral networks with attention
CN117763400A (en) * 2024-02-22 2024-03-26 福建理工大学 A method for classifying social network graph nodes based on dual attention

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210081717A1 (en) * 2018-05-18 2021-03-18 Benevolentai Technology Limited Graph neutral networks with attention
CN117763400A (en) * 2024-02-22 2024-03-26 福建理工大学 A method for classifying social network graph nodes based on dual attention

Similar Documents

Publication Publication Date Title
Karamchandani et al. Rumor source detection under probabilistic sampling
Salama et al. Introduction to image processing via neutrosophic techniques
US7965643B1 (en) Method and apparatus for using histograms to produce data summaries
CN111885040A (en) Distributed network situation perception method, system, server and node equipment
Taherian et al. Trust inference in web-based social networks using resistive networks
GIOVANARDI et al. Criteria to design chaotic self-similar traffic generators
Nahman Minimal paths and cuts of networks exposed to common-cause failures
Li et al. An effective reliability evaluation method for power communication network based on community structure
MA65752A1 (en) Use of a graph attention network with edge characteristics for the analysis of temporal and spatial data in telecommunications
Xie et al. Gaussian Rate–Distortion–Perception Coding and Entropy-Constrained Scalar Quantization
Ruj Zero-knowledge proofs for blockchains
Gupta et al. Information-theoretic privacy in distributed average consensus
US7177282B1 (en) Method and apparatus for using histograms to produce data summaries
Lobel et al. Rate of convergence of learning in social networks
Xia et al. Products of generalized stochastic Sarymsakov matrices
Iutzeler Distributed estimation and optimization in asynchronous networks
Miao et al. Simplification, merging and division of fuzzy cognitive maps
Alsan et al. A simple proof of polarization and polarization for non-stationary channels
Amiri et al. Performance of quantum preprocessing under phase noise
He et al. Construction of security attribute portraits for power Internet of Things
CN115865727A (en) Branch correlation risk assessment method based on credibility and credibility inference graph
Jonsson et al. On structured robustness analysis for feedback interconnections of unstable systems
Nisha et al. Sequential event-based detection of network attacks on CSE CIC IDS 2018 data set–application of GSP and IPAM Algorithm
Abdolmaleki et al. Unbounded Simulation-Sound Subversion Resistant Quasi-Adaptive NIZK Proofs and Applications to Modular zk-SNARKs.
Akbarzadeh et al. Multicast optimization: Operational research theory and applications