mlsanityData to 14 Oct 2026

Homophily Enhanced Graph Domain Adaptation

arXiv 2505.20089 ↗First posted 26 May 2025cs.SI cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. In this paper, we highlight the significance of graph homophily, a pivotal factor for graph domain alignment, which, however, has long been overlooked in existing approaches. Specifically, our analysis first reveals that homophily discrepancies exist in benchmarks. Moreover, we also show that homophily discrepancies degrade GDA performance from both empirical and theoretical aspects, which further underscores the importance of homophily alignment in GDA. Inspired by this finding, we propose a novel homophily alignment algorithm that employs mixed filters to smooth graph signals, thereby effectively capturing and mitigating homophily discrepancies between graphs. Experimental results on a variety of benchmarks verify the effectiveness of our method.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 52 of its 80 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

52 of 80 references.

References · 52

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2020Simple and Deep Graph Convolutional Networkscited by 860
  4. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  5. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  6. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  7. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  8. 2017struc2vec: Learning Node Representations from Structural Identitycited by 215
  9. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  10. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  11. 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
  12. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
38 more
  1. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  2. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  3. 2023Cluster-guided Contrastive Graph Clustering Networkcited by 60
  4. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  5. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  6. 2022Non-IID Transfer Learning on Graphscited by 43
  7. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  8. 2024Rethinking Propagation for Unsupervised Graph Domain Adaptationcited by 31
  9. 2023PC-Conv: Unifying Homophily and Heterophily with Two-fold Filteringcited by 28
  10. 2023Semi-supervised Domain Adaptation in Graph Transfer Learningcited by 27
  11. 2024Pairwise Alignment Improves Graph Domain Adaptationcited by 25
  12. 2023CONVERT:Contrastive Graph Clustering with Reliable Augmentationcited by 23
  13. 2022Mixed Graph Contrastive Network for Semi-Supervised Node Classificationcited by 21
  14. 2022Graph-Relational Domain Adaptationcited by 19
  15. 2025On the Benefits of Attribute-Driven Graph Domain Adaptationcited by 19
  16. 2022Structure-Preserving Graph Representation Learningcited by 17
  17. 2023Robust Mid-Pass Filtering Graph Convolutional Networkscited by 17
  18. 2024SA-GDA: Spectral Augmentation for Graph Domain Adaptationcited by 16
  19. 2024CDC: A Simple Framework for Complex Data Clusteringcited by 15
  20. 2024Generalizing across Temporal Domains with Koopman Operatorscited by 13
  21. 2023Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clusteringcited by 12
  22. 2024Graph Domain Adaptation: Challenges, Progress and Prospectscited by 11
  23. 2022GraphLearner: Graph Node Clustering with Fully Learnable Augmentationcited by 10
  24. 2023Domain-adaptive Message Passing Graph Neural Networkcited by 10
  25. 2024Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptationcited by 10
  26. 2024Balanced Multi-Relational Graph Clusteringcited by 10
  27. 2025ZETA: Leveraging Z-order Curves for Efficient Top-k Attentioncited by 9
  28. 2024One Node One Model: Featuring the Missing-Half for Graph Clusteringcited by 7
  29. 2024Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detectioncited by 5
  30. 2024Provable Filter for Real-world Graph Clusteringcited by 5
  31. 2024Rethinking Independent Cross-Entropy Loss For Graph-Structured Datacited by 5
  32. 2024Intersectional Unfairness Discoverycited by 5
  33. 2025Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Spacecited by 4
  34. 2019Network Together: Node Classification via Cross network Deep Network Embeddingcited by 3
  35. 2024Simplified PCNet with Robustnesscited by 3
  36. 2024Object Style Diffusion for Generalized Object Detection in Urban Scenecited by 3
  37. 2025Unveiling Mode Connectivity in Graph Neural Networkscited by 3
  38. 2025PyGDA: A Python Library for Graph Domain Adaptationcited by 2

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 9.

9 papers.

  1. 2026When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretrainingcited by 5
  2. 2026Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptationcited by 4
  3. 2026Full spectrum Unlearnable Examples via Spectral Equalizationcited by 3
  4. 2026DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptationcited by 2
  5. 2026Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understandingcited by 1
  6. 2026Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptationcited by 1
  7. 2026DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillationcited by 0
  8. 2026Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype Learningcited by 0
  9. 2026Graph Domain Adaptation Does Not End with Representation Learningcited by 0