mlsanityData to 14 Oct 2026

DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning

arXiv 2402.13711 ↗First posted 21 Feb 2024cs.LG cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

We investigate the replay buffer in rehearsal-based approaches for graph continual learning (GCL) methods. Existing rehearsal-based GCL methods select the most representative nodes for each class and store them in a replay buffer for later use in training subsequent tasks. However, we discovered that considering only the class representativeness of each replayed node makes the replayed nodes to be concentrated around the center of each class, incurring a potential risk of overfitting to nodes residing in those regions, which aggravates catastrophic forgetting. Moreover, as the rehearsal-based approach heavily relies on a few replayed nodes to retain knowledge obtained from previous tasks, involving the replayed nodes that have irrelevant neighbors in the model training may have a significant detrimental impact on model performance. In this paper, we propose a GCL model named DSLR, specifically, we devise a coverage-based diversity (CD) approach to consider both the class representativeness and the diversity within each class of the replayed nodes. Moreover, we adopt graph structure learning (GSL) to ensure that the replayed nodes are connected to truly informative neighbors. Extensive experimental results demonstrate the effectiveness and efficiency of DSLR. Our source code is available at https://github.com/seungyoon-Choi/DSLR_official.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 32 of its 49 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

32 of 49 references.

References · 32

  1. 2017Graph Attention Networkscited by 8,923
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2016Learning without Forgettingcited by 2,496
  5. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  6. 2017Continual Learning with Deep Generative Replaycited by 1,158
  7. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  8. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  9. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  10. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  11. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  12. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
20 more
  1. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  2. 2020Data Augmentation for Graph Neural Networkscited by 203
  3. 2019Scalable and Order-robust Continual Learning with Additive Parameter Decompositioncited by 125
  4. 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 117
  5. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 110
  6. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 95
  7. 2021Representational Continuity for Unsupervised Continual Learningcited by 95
  8. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 71
  9. 2020Streaming Graph Neural Networks via Continual Learningcited by 64
  10. 2023Dynamically Expandable Graph Convolution for Streaming Recommendationcited by 26
  11. 2022Reinforced Continual Learning for Graphscited by 24
  12. 2022Self-Supervised Graph Structure Refinement for Graph Neural Networkscited by 20
  13. 2024Towards Robust Graph Incremental Learning on Evolving Graphscited by 18
  14. 2021Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classificationcited by 13
  15. 2023RDGSL: Dynamic Graph Representation Learning with Structure Learningcited by 13
  16. 2023Homophily-enhanced Structure Learning for Graph Clusteringcited by 9
  17. 2022Self-organization Preserved Graph Structure Learning with Principle of Relevant Informationcited by 8
  18. 2023Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classificationcited by 7
  19. 2023Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender Systemcited by 7
  20. 2023Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 6.

14 papers.

Sort:

By area:

  1. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  2. 2024Federated Continual Graph Learningcited by 5
  3. 2025Toward Scalable Graph Unlearning: A Node Influence Maximization based Approachcited by 2
  4. 2025Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embeddingcited by 2
  5. 2025When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertaintycited by 1
  6. 2025HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learningcited by 1
  7. 2024E-CGL: An Efficient Continual Graph Learnercited by 0
  8. 2025Condensation-Concatenation Framework for Dynamic Graph Continual Learningcited by 0
  9. 2026When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learningcited by 0
  10. 2026UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learningcited by 0
  11. 2026Informative Graph Structure Learningcited by 0
  12. 2026UNIT: Unleash Large Language Models Potential for Graph Continual Learningcited by 0
2 more
  1. 2026CA-DGCL: Dynamic Graph Continual Learning via Condensation and Attachmentcited by 0
  2. 2026DSETA: A Dual-Stage Continual Learning Framework for Travel Time Prediction in Dynamic Traffic Environmentscited by 0