Graph Relation Aware Continual Learning
Not on the map. Why?
Abstract (arXiv)
Continual graph learning (CGL) studies the problem of learning from an infinite stream of graph data, consolidating historical knowledge, and generalizing it to the future task. At once, only current graph data are available. Although some recent attempts have been made to handle this task, we still face two potential challenges: 1) most of existing works only manipulate on the intermediate graph embedding and ignore intrinsic properties of graphs. It is non-trivial to differentiate the transferred information across graphs. 2) recent attempts take a parameter-sharing policy to transfer knowledge across time steps or progressively expand new architecture given shifted graph distribution. Learning a single model could loss discriminative information for each graph task while the model expansion scheme suffers from high model complexity. In this paper, we point out that latent relations behind graph edges can be attributed as an invariant factor for the evolving graphs and the statistical information of latent relations evolves. Motivated by this, we design a relation-aware adaptive model, dubbed as RAM-CG, that consists of a relation-discovery modular to explore latent relations behind edges and a task-awareness masking classifier to accounts for the shifted. Extensive experiments show that RAM-CG provides significant 2.2%, 6.9% and 6.6% accuracy improvements over the state-of-the-art results on CitationNet, OGBN-arxiv and TWITCH dataset, respective.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 58 references that are in the map. First posted on arXiv 16 Aug 2023.
Builds on
37 of 58 references.
References · 37
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2017Gradient Episodic Memory for Continual Learningcited by 1,871
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2017Continual Learning with Deep Generative Replaycited by 1,152
- 2018Progress & Compress: A scalable framework for continual learningcited by 516
- 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
- 2018Task-Free Continual Learningcited by 219
- 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
- 2018Reinforced Continual Learningcited by 186
- 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
25 more
- 2019Uncertainty-based Continual Learning with Adaptive Regularizationcited by 144
- 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
- 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
- 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 93
- 2022Adaptive Trajectory Prediction via Transferable GNNcited by 51
- 2021Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddingscited by 48
- 2021Effective Sparsification of Neural Networks with Global Sparsity Constraintcited by 45
- 2020Reliable Graph Neural Networks via Robust Aggregationcited by 43
- 2022Non-IID Transfer Learning on Graphscited by 43
- 2021TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learningcited by 42
- 2021FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Predictioncited by 26
- 2022Reinforced Continual Learning for Graphscited by 24
- 2022Exploring Edge Disentanglement for Node Classificationcited by 23
- 2020Lifelong Learning of Graph Neural Networks for Open-World Node Classificationcited by 22
- 2021Semi-Supervised Graph-to-Graph Translationcited by 18
- 2019Graph Neural Networks Exponentially Lose Expressive Power for Node Classificationcited by 16
- 2022Towards Faithful and Consistent Explanations for Graph Neural Networkscited by 13
- 2022TopoImb: Toward Topology-level Imbalance in Learning from Graphscited by 12
- 2022Explanation Guided Contrastive Learning for Sequential Recommendationcited by 11
- 2022Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspectivecited by 11
- 2022Semi-supervised Drifted Stream Learning with Short Lookbackcited by 7
- 2022Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networkscited by 6
- 2023Faithful and Consistent Graph Neural Network Explanations with Rationale Alignmentcited by 6
- 2023Skill Disentanglement for Imitation Learning from Suboptimal Demonstrationscited by 5
- 2022Ego-graph Replay based Continual Learning for Misinformation Engagement Predictioncited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.