mlsanityData to 7 Oct 2026

Towards Robust Graph Incremental Learning on Evolving Graphs

arXiv 2402.12987 ↗First posted 20 Feb 2024cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Incremental learning is a machine learning approach that involves training a model on a sequence of tasks, rather than all tasks at once. This ability to learn incrementally from a stream of tasks is crucial for many real-world applications. However, incremental learning is a challenging problem on graph-structured data, as many graph-related problems involve prediction tasks for each individual node, known as Node-wise Graph Incremental Learning (NGIL). This introduces non-independent and non-identically distributed characteristics in the sample data generation process, making it difficult to maintain the performance of the model as new tasks are added. In this paper, we focus on the inductive NGIL problem, which accounts for the evolution of graph structure (structural shift) induced by emerging tasks. We provide a formal formulation and analysis of the problem, and propose a novel regularization-based technique called Structural-Shift-Risk-Mitigation (SSRM) to mitigate the impact of the structural shift on catastrophic forgetting of the inductive NGIL problem. We show that the structural shift can lead to a shift in the input distribution for the existing tasks, and further lead to an increased risk of catastrophic forgetting. Through comprehensive empirical studies with several benchmark datasets, we demonstrate that our proposed method, Structural-Shift-Risk-Mitigation (SSRM), is flexible and easy to adapt to improve the performance of state-of-the-art GNN incremental learning frameworks in the inductive setting.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 39 of its 56 references that are in the map. First posted on arXiv 20 Feb 2024.

Builds on

39 of 56 references.

References · 39

  1. 2017Inductive Representation Learning on Large Graphscited by 6,284
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2016Learning without Forgettingcited by 2,465
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  7. 2016Progressive Neural Networkscited by 1,332
  8. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  9. 2017Continual Learning with Deep Generative Replaycited by 1,152
  10. 2019Large Scale Incremental Learningcited by 727
  11. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  12. 2019Gradient based sample selection for online continual learningcited by 568
27 more
  1. 2019Orthogonal Gradient Descent for Continual Learningcited by 361
  2. 2021Gradient Projection Memory for Continual Learningcited by 338
  3. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  4. 2020Supermasks in Superpositioncited by 223
  5. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  6. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
  7. 2018Contextual Stochastic Block Modelscited by 134
  8. 2019Scalable and Order-robust Continual Learning with Additive Parameter Decompositioncited by 125
  9. 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
  10. 2016Less-forgetting Learning in Deep Neural Networkscited by 97
  11. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 93
  12. 2018Streaming Graph Neural Networkscited by 91
  13. 2020Optimal Continual Learning has Perfect Memory and is NP-hardcited by 86
  14. 2020Streaming Graph Neural Networks via Continual Learningcited by 63
  15. 2020Graph Neural Networks with Continual Learning for Fake News Detection from Social Mediacited by 43
  16. 2020GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systemscited by 42
  17. 2021Graph Few-shot Class-incremental Learningcited by 40
  18. 2019A comprehensive, application-oriented study of catastrophic forgetting in DNNscited by 35
  19. 2021Continual Learning of Knowledge Graph Embeddingscited by 35
  20. 2020Lifelong Graph Learningcited by 31
  21. 2020Incremental Learning via Rate Reductioncited by 31
  22. 2021Hierarchical Prototype Networks for Continual Graph Representation Learningcited by 28
  23. 2020Disentangle-based Continual Graph Representation Learningcited by 25
  24. 2020Lifelong Learning of Graph Neural Networks for Open-World Node Classificationcited by 22
  25. 2021Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classificationcited by 13
  26. 2024PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networkscited by 10
  27. 2023On the Limitation and Experience Replay for GNNs in Continual Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 7; 2026: 5.

18 papers.

Sort:

By area:

  1. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  2. 2024DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learningcited by 14
  3. 2024Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approachcited by 12
  4. 2024Towards Continuous Reuse of Graph Models via Holistic Memory Diversificationcited by 7
  5. 2025Scalable Graph Condensation with Evolving Capabilitiescited by 6
  6. 2024Federated Continual Graph Learningcited by 5
  7. 2024Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networkscited by 5
  8. 2024On the Topology Awareness and Generalization Performance of Graph Neural Networkscited by 3
  9. 2025Online Continual Graph Learningcited by 2
  10. 2025A Selective Learning Method for Temporal Graph Continual Learningcited by 1
  11. 2026Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approachcited by 1
  12. 2025Dynamic Mixture-of-Experts for Incremental Graph Learningcited by 0
6 more
  1. 2025Task-Aware Adaptive Modulation: A Replay-Free and Resource-Efficient Approach For Continual Graph Learningcited by 0
  2. 2025The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learningcited by 0
  3. 2026TAAM:Inductive Graph-Class Incremental Learning with Task-Aware Adaptive Modulationcited by 0
  4. 2026DG-CoLearn: An Efficient Collaborative Learning Framework for Dynamic Graphscited by 0
  5. 2026FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learningcited by 0
  6. 2026Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductionscited by 0