mlsanityData to 14 Oct 2026

GCAL: Adapting Graph Models to Evolving Domain Shifts

arXiv 2505.16860 ↗First posted 22 May 2025cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper addresses the challenge of graph domain adaptation on evolving, multiple out-of-distribution (OOD) graphs. Conventional graph domain adaptation methods are confined to single-step adaptation, making them ineffective in handling continuous domain shifts and prone to catastrophic forgetting. This paper introduces the Graph Continual Adaptive Learning (GCAL) method, designed to enhance model sustainability and adaptability across various graph domains. GCAL employs a bilevel optimization strategy. The "adapt" phase uses an information maximization approach to fine-tune the model with new graph domains while re-adapting past memories to mitigate forgetting. Concurrently, the "generate memory" phase, guided by a theoretical lower bound derived from information bottleneck theory, involves a variational memory graph generation module to condense original graphs into memories. Extensive experimental evaluations demonstrate that GCAL substantially outperforms existing methods in terms of adaptability and knowledge retention.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 50 of its 68 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

50 of 68 references.

References · 50

  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. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  6. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  7. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  8. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  9. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  10. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  11. 2019Multi-scale Attributed Node Embeddingcited by 548
  12. 2022Continual Test-Time Domain Adaptationcited by 525
38 more
  1. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  2. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  3. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  4. 2020Graph Information Bottleneckcited by 168
  5. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  6. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 151
  7. 2021Graph Condensation for Graph Neural Networkscited by 150
  8. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 148
  9. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  10. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 104
  11. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  12. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 95
  13. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 86
  14. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  15. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  16. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  17. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 67
  18. 2023Graph Prompt Learning: A Comprehensive Survey and Beyondcited by 61
  19. 2022Graph Condensation via Receptive Field Distribution Matchingcited by 60
  20. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  21. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
  22. 2023Structural Re-weighting Improves Graph Domain Adaptationcited by 45
  23. 2020GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systemscited by 42
  24. 2023Continual Learning on Dynamic Graphs via Parameter Isolationcited by 36
  25. 2022Self-Supervised Continual Graph Learning in Adaptive Riemannian Spacescited by 32
  26. 2023Graph Condensation for Inductive Node Representation Learningcited by 31
  27. 2021Hierarchical Prototype Networks for Continual Graph Representation Learningcited by 28
  28. 2023Semi-supervised Domain Adaptation in Graph Transfer Learningcited by 27
  29. 2024Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learningcited by 18
  30. 2024AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendationscited by 12
  31. 2024GC-Bench: An Open and Unified Benchmark for Graph Condensationcited by 12
  32. 2024Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approachcited by 12
  33. 2024Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysiscited by 10
  34. 2021RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Trainingcited by 9
  35. 2023Adaptive Path-Memory Network for Temporal Knowledge Graph Reasoningcited by 9
  36. 2024Towards Continuous Reuse of Graph Models via Holistic Memory Diversificationcited by 7
  37. 2024PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysiscited by 5
  38. 2024Single-View Graph Contrastive Learning with Soft Neighborhood Awarenesscited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

8 papers.

  1. 2025DP-DGAD: A Generalist Dynamic Graph Anomaly Detector with Dynamic Prototypescited by 5
  2. 2025Simple and Efficient Heterogeneous Temporal Graph Neural Networkcited by 2
  3. 2026Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directionscited by 1
  4. 2025Out-of-Distribution Graph Models Mergingcited by 0
  5. 2026CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalizationcited by 0
  6. 2026Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detectioncited by 0
  7. 2026ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural Networkscited by 0
  8. 2026Transfer Learning for Edge Classification on Dynamic Text-Attributed Graphscited by 0