mlsanityData to 14 Oct 2026

Universal Graph Continual Learning

arXiv 2308.13982 ↗First posted 27 Aug 2023cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We address catastrophic forgetting issues in graph learning as incoming data transits from one to another graph distribution. Whereas prior studies primarily tackle one setting of graph continual learning such as incremental node classification, we focus on a universal approach wherein each data point in a task can be a node or a graph, and the task varies from node to graph classification. We propose a novel method that enables graph neural networks to excel in this universal setting. Our approach perseveres knowledge about past tasks through a rehearsal mechanism that maintains local and global structure consistency across the graphs. We benchmark our method against various continual learning baselines in real-world graph datasets and achieve significant improvement in average performance and forgetting across tasks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 31 of its 49 references that are in the map. First posted on arXiv 27 Aug 2023.

Builds on

31 of 49 references.

References · 31

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2016Learning without Forgettingcited by 2,496
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  9. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  10. 2016Progressive Neural Networkscited by 1,361
  11. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  12. 2018Experience Replay for Continual Learningcited by 1,095
19 more
  1. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,077
  2. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  3. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  4. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 424
  5. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 356
  6. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  7. 2021ICDAR2019 Competition on Scanned Receipt OCR and Information Extractioncited by 256
  8. 2018Selective Experience Replay for Lifelong Learningcited by 241
  9. 2018Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselinescited by 228
  10. 2020Distilling Knowledge from Graph Convolutional Networkscited by 129
  11. 2020Streaming Graph Neural Networks via Continual Learningcited by 64
  12. 2021Graph-Free Knowledge Distillation for Graph Neural Networkscited by 46
  13. 2018GraphIE: A Graph-Based Framework for Information Extractioncited by 45
  14. 2021Spatial Dual-Modality Graph Reasoning for Key Information Extractioncited by 43
  15. 2020Lifelong Graph Learningcited by 31
  16. 2022Graph Lifelong Learning: A Surveycited by 30
  17. 2020Lifelong Learning of Graph Neural Networks for Open-World Node Classificationcited by 22
  18. 2021Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classificationcited by 13
  19. 2021Robust Deep Reinforcement Learning for Extractive Legal Summarizationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 4; 2026: 2.

9 papers.

  1. 2024Continual Learning on Graphs: Challenges, Solutions, and Opportunitiescited by 21
  2. 2023PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensationcited by 9
  3. 2024Efficient and Robust Continual Graph Learning for Graph Classification in Biologycited by 3
  4. 2025Online Continual Graph Learningcited by 3
  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. 2025The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learningcited by 1
  8. 2026Continual Fine-Tuning of Large Language Models via Program Memorycited by 1
  9. 2026Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replaycited by 0