mlsanityData to 7 Oct 2026

Multi-perspective Feedback-attention Coupling Model for Continuous-time Dynamic Graphs

arXiv 2312.07983 ↗First posted 13 Dec 2023cs.LG cs.AI cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, representation learning over graph networks has gained popularity, with various models showing promising results. Despite this, several challenges persist: 1) most methods are designed for static or discrete-time dynamic graphs; 2) existing continuous-time dynamic graph algorithms focus on a single evolving perspective; and 3) many continuous-time dynamic graph approaches necessitate numerous temporal neighbors to capture long-term dependencies. In response, this paper introduces the Multi-Perspective Feedback-Attention Coupling (MPFA) model. MPFA incorporates information from both evolving and raw perspectives, efficiently learning the interleaved dynamics of observed processes. The evolving perspective employs temporal self-attention to distinguish continuously evolving temporal neighbors for information aggregation. Through dynamic updates, this perspective can capture long-term dependencies using a small number of temporal neighbors. Meanwhile, the raw perspective utilizes a feedback attention module with growth characteristic coefficients to aggregate raw neighborhood information. Experimental results on a self-organizing dataset and seven public datasets validate the efficacy and competitiveness of our proposed model.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 13 Dec 2023.

Builds on

25 of 40 references.

References · 25

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  5. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  6. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  7. 2018Link Prediction Based on Graph Neural Networkscited by 829
  8. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
  9. 2020Inductive Representation Learning on Temporal Graphscited by 454
  10. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  11. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  12. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
13 more
  1. 2019Time2Vec: Learning a Vector Representation of Timecited by 208
  2. 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 188
  3. 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 154
  4. 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 141
  5. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 120
  6. 2018Streaming Graph Neural Networkscited by 91
  7. 2018dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learningcited by 88
  8. 2019Variational Graph Recurrent Neural Networkscited by 86
  9. 2017Dynamic Graph Convolutional Networkscited by 83
  10. 2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 65
  11. 2019Predicting Path Failure In Time-Evolving Graphscited by 54
  12. 2016subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphscited by 19
  13. 2019Generative Adversarial Networks in Computer Vision: A Survey and Taxonomycited by 12

Built on by

Not cited yet.