mlsanityData to 7 Oct 2026

On the Benefits of Attribute-Driven Graph Domain Adaptation

arXiv 2502.06808 ↗First posted 4 Feb 2025cs.LG cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

Graph Domain Adaptation (GDA) addresses a pressing challenge in cross-network learning, particularly pertinent due to the absence of labeled data in real-world graph datasets. Recent studies attempted to learn domain invariant representations by eliminating structural shifts between graphs. In this work, we show that existing methodologies have overlooked the significance of the graph node attribute, a pivotal factor for graph domain alignment. Specifically, we first reveal the impact of node attributes for GDA by theoretically proving that in addition to the graph structural divergence between the domains, the node attribute discrepancy also plays a critical role in GDA. Moreover, we also empirically show that the attribute shift is more substantial than the topology shift, which further underscores the importance of node attribute alignment in GDA. Inspired by this finding, a novel cross-channel module is developed to fuse and align both views between the source and target graphs for GDA. Experimental results on a variety of benchmarks verify the effectiveness of our method.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 32 of its 49 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

32 of 49 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2022Continual Test-Time Domain Adaptationcited by 520
  4. 2017struc2vec: Learning Node Representations from Structural Identitycited by 214
  5. 2021Generalized Source-free Domain Adaptationcited by 175
  6. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  7. 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
  8. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  9. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  10. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  11. 2019DANE: Domain Adaptive Network Embeddingcited by 43
  12. 2022Non-IID Transfer Learning on Graphscited by 43
20 more
  1. 2024Rethinking Propagation for Unsupervised Graph Domain Adaptationcited by 31
  2. 2023Revisiting Link Prediction: A Data Perspectivecited by 29
  3. 2023PC-Conv: Unifying Homophily and Heterophily with Two-fold Filteringcited by 28
  4. 2023Semi-supervised Domain Adaptation in Graph Transfer Learningcited by 27
  5. 2024Pairwise Alignment Improves Graph Domain Adaptationcited by 25
  6. 2022Graph-Relational Domain Adaptationcited by 19
  7. 2022Structure-Preserving Graph Representation Learningcited by 17
  8. 2022Weakly Supervised Object Localization as Domain Adaptioncited by 16
  9. 2024SA-GDA: Spectral Augmentation for Graph Domain Adaptationcited by 16
  10. 2024CDC: A Simple Framework for Complex Data Clusteringcited by 15
  11. 2023Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clusteringcited by 12
  12. 2023ALEX: Towards Effective Graph Transfer Learning with Noisy Labelscited by 11
  13. 2024Graph Domain Adaptation: Challenges, Progress and Prospectscited by 11
  14. 2023Domain-adaptive Message Passing Graph Neural Networkcited by 10
  15. 2020Towards Fair Knowledge Transfer for Imbalanced Domain Adaptationcited by 7
  16. 2024One Node One Model: Featuring the Missing-Half for Graph Clusteringcited by 7
  17. 2024Provable Filter for Real-world Graph Clusteringcited by 5
  18. 2019Network Together: Node Classification via Cross network Deep Network Embeddingcited by 3
  19. 2023Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptationcited by 3
  20. 2024Simplified PCNet with Robustnesscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 16.

19 papers.

Sort:

By area:

  1. 2025Homophily Enhanced Graph Domain Adaptationcited by 9
  2. 2025Understanding and Mitigating Under-Confidence in GNNs from the Final Layercited by 6
  3. 2026When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretrainingcited by 5
  4. 2026Structure-Centric Graph Foundation Model via Geometric Basescited by 5
  5. 2026DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptationcited by 4
  6. 2026Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptationcited by 4
  7. 2026Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structurecited by 3
  8. 2026Full spectrum Unlearnable Examples via Spectral Equalizationcited by 3
  9. 2026DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptationcited by 2
  10. 2026Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understandingcited by 1
  11. 2026Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptationcited by 1
  12. 2026DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recoverycited by 1
7 more
  1. 2026Cross-Resolution Semantic Learning for Graph Domain Adaptationcited by 1
  2. 2025Empowering GNNs for Domain Adaptation via Denoising Target Graphcited by 0
  3. 2026Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype Learningcited by 0
  4. 2026Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transportcited by 0
  5. 2026ARM: Attention with Routed-Memory for Learnable Sparse Controlcited by 0
  6. 2026Graph Domain Adaptation Does Not End with Representation Learningcited by 0
  7. 2026Spectral Reversal: Counteracting Singular Value Bias for Graph Promptingcited by 0