mlsanityData to 14 Oct 2026

SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

arXiv 2607.00377 ↗First posted 1 Jul 2026cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce stability of individual node (or node-pair) embeddings. Due to optimizing nodes in isolation, these methods fail to maintain global relational structure, causing inter-node correspondences to progressively distort under continual learning. To this end, we propose a novel Structure-Aware Optimal Transport (SAOT) framework that explicitly captures and preserves relational structure within graph representations across sequential tasks. Specifically, SAOT leverages optimal transport theory to capture global inter-node correspondences, thereby facilitating and enhancing graph representation learning. Simultaneously, SAOT incorporates a cross-task knowledge distillation mechanism to preserve the previous structural knowledge. Extensive experiments on four CGL benchmark datasets demonstrate that SAOT outperforms existing self-supervised baselines. In particular, SAOT achieves significant performance gains, improving average accuracy by up to 5% on CoraFull-CL and over 15% on Products-CL compared with state-of-the-art methods in the Class-IL setting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 35 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

27 of 35 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2016Variational Graph Auto-Encoderscited by 1,382
  7. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  8. 2018Deep Graph Infomaxcited by 1,106
  9. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
  10. 2021Co2L: Contrastive Continual Learningcited by 244
  11. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 186
  12. 2020When Does Self-Supervision Help Graph Convolutional Networks?cited by 121
15 more
  1. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  2. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 95
  3. 2021Augmentation-Free Self-Supervised Learning on Graphscited by 94
  4. 2021Graph Barlow Twins: A self-supervised representation learning framework for graphscited by 85
  5. 2020Streaming Graph Neural Networks via Continual Learningcited by 64
  6. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
  7. 2024Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networkscited by 43
  8. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  9. 2021Continually Learning Self-Supervised Representations with Projected Functional Regularizationcited by 38
  10. 2022Self-Supervised Continual Graph Learning in Adaptive Riemannian Spacescited by 32
  11. 2021Hierarchical Prototype Networks for Continual Graph Representation Learningcited by 28
  12. 2023Plasticity-Optimized Complementary Networks for Unsupervised Continual Learningcited by 14
  13. 2024Topology-aware Embedding Memory for Continual Learning on Expanding Networkscited by 14
  14. 2024A Topology-aware Graph Coarsening Framework for Continual Graph Learningcited by 11
  15. 2023PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensationcited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning
  2. 2025Task-Aware Adaptive Modulation: A Replay-Free and Resource-Efficient Approach For Continual Graph Learning
  3. 2023Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
  4. 2024GraphEdit: Large Language Models for Graph Structure Learning
  5. 2026MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning
  6. 2024Efficient and Robust Continual Graph Learning for Graph Classification in Biology
  7. 2022Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation
  8. 2025SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs