mlsanityData to 7 Oct 2026

EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs

arXiv 2305.00664 ↗First posted 1 May 2023cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Non-IID transfer learning on graphs is crucial in many high-stakes domains. The majority of existing works assume stationary distribution for both source and target domains. However, real-world graphs are intrinsically dynamic, presenting challenges in terms of domain evolution and dynamic discrepancy between source and target domains. To bridge the gap, we shift the problem to the dynamic setting and pose the question: given the label-rich source graphs and the label-scarce target graphs both observed in previous T timestamps, how can we effectively characterize the evolving domain discrepancy and optimize the generalization performance of the target domain at the incoming T+1 timestamp? To answer it, we propose a generalization bound for dynamic non-IID transfer learning on graphs, which implies the generalization performance is dominated by domain evolution and domain discrepancy between source and target graphs. Inspired by the theoretical results, we introduce a novel generic framework named EvoluNet. It leverages a transformer-based temporal encoding module to model temporal information of the evolving domains and then uses a dynamic domain unification module to efficiently learn domain-invariant representations across the source and target domains. Finally, EvoluNet outperforms the state-of-the-art models by up to 12.1%, demonstrating its effectiveness in transferring knowledge from dynamic source graphs to dynamic target graphs.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 49 of its 79 references that are in the map. First posted on arXiv 1 May 2023.

Builds on

49 of 79 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  9. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  10. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  11. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  12. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
37 more
  1. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
  2. 2020Inductive Representation Learning on Temporal Graphscited by 454
  3. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  4. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
  5. 2019Representation Learning for Dynamic Graphs: A Surveycited by 260
  6. 2018Characterizing and Avoiding Negative Transfercited by 226
  7. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  8. 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 154
  9. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  10. 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 141
  11. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  12. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
  13. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 123
  14. 2021Federated Graph Classification over Non-IID Graphscited by 113
  15. 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
  16. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  17. 2019Session-based Social Recommendation via Dynamic Graph Attention Networkscited by 76
  18. 2020Continuously Indexed Domain Adaptationcited by 74
  19. 2021AFEC: Active Forgetting of Negative Transfer in Continual Learningcited by 73
  20. 2018Transfer learning for time series classificationcited by 60
  21. 2022Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysiscited by 58
  22. 2021Molecular Contrastive Learning with Chemical Element Knowledge Graphcited by 50
  23. 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
  24. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  25. 2022Non-IID Transfer Learning on Graphscited by 43
  26. 2019Transfer Learning with Dynamic Distribution Adaptationcited by 40
  27. 2019AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphscited by 32
  28. 2022Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyondcited by 32
  29. 2022Enhancing Cross-lingual Transfer by Manifold Mixupcited by 30
  30. 2022MentorGNN: Deriving Curriculum for Pre-Training GNNscited by 18
  31. 2021GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphscited by 12
  32. 2022Domain-Invariant Representation Learning from EEG with Private Encoderscited by 12
  33. 2014Graph analysis of functional brain networks: practical issues in translational neurosciencecited by 10
  34. 2020Continuous Transfer Learning with Label-informed Distribution Alignmentcited by 6
  35. 2021Dynamic Domain Adaptation for Efficient Inferencecited by 6
  36. 2022Segmenting across places: The need for fair transfer learning with satellite imagerycited by 6
  37. 2022A Unified Meta-Learning Framework for Dynamic Transfer Learningcited by 5

Built on by

Cited by year

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

7 papers.

  1. 2025LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selectioncited by 14
  2. 2023Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolboxcited by 6
  3. 2024A Primer on Temporal Graph Learningcited by 4
  4. 2025Non-exchangeable Conformal Prediction for Temporal Graph Neural Networkscited by 3
  5. 2025HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relationscited by 3
  6. 2024Exploring Consistency in Graph Representations:from Graph Kernels to Graph Neural Networkscited by 1
  7. 2025EVINET: Towards Open-World Graph Learning via Evidential Reasoning Networkcited by 0