Disentangled Graph Spectral Domain Adaptation
Liang Yang, Xin Chen, Jiaming Zhuo, Di Jin, Chuan Wang, Xiaochun Cao, Zhen Wang, Yuanfang Guo
Abstract
The distribution shifts and the scarcity of labels prevent graph learning methods, especially graph neural networks (GNNs), from generalizing across domains. Compared to Unsupervised Domain Adaptation (UDA) with embedding alignment, Unsupervised Graph Domain Adaptation (UGDA) becomes more challenging in light of the attribute and topology entanglement in the representation. Beyond embedding alignment, UGDA turns to topology alignment but is limited by the ability of the employed topology model and the estimation of pseudo labels. To alleviate this issue, this paper proposed a Disentangled Graph Spectral Domain adaptation (DGSDA) by disentangling attribute and topology alignments and directly aligning flexible graph spectral filters beyond topology. Specifically, Bernstein polynomial approximation, which mimics the behavior of the function to be approximated to a remarkable degree, is employed to capture complicated topology characteristics and avoid the expensive eigenvalue decomposition. Theoretical analysis reveals the tight GDA bound of DGSDA and the rationality of polynomial coefficient regularization. Quantitative and qualitative experiments justify the superiority of the proposed DGSDA.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
9 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Source-Free Graph Foundation Model Adaptation via Pseudo-Source Reconstruction cites Adversarial Deep Network Embedding for Cross-Network Node Classification
- Source-Free Graph Foundation Model Adaptation via Pseudo-Source Reconstruction cites Unsupervised Domain Adaptive Graph Convolutional Networks
- Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation cites Unsupervised Domain Adaptive Graph Convolutional Networks
- Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited cites How Powerful are Spectral Graph Neural Networks
- Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited cites Open Graph Benchmark: Datasets for Machine Learning on Graphs
- Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation cites Unsupervised Domain Adaptive Graph Convolutional Networks
Cited by top-tier papers9
- Learning Structure-Semantic Evolution Trajectories for Graph Domain AdaptationWei Chen, Xingyu Guo, Shuang Li, Yan Zhong et al.ICLR 2026 · 8 citations
- Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain AdaptationWei Chen, Xingyu Guo, Shuang Li, Zhao Zhang et al.ICLR 2026 · 3 citations
- Heterogeneity-Aware Knowledge Sharing for Graph Federated LearningWentao Yu, Sheng Wan, Shuo Chen, Bo Han et al.ICML 2026 · 1 citation
- PhenoBrain: Phenotype-Conditioned Long-Range Communication for Multi-Modal Brain Network AnalysisLingyuan Meng, KE LIANG, Hao Li, Meng Liu et al.ICML 2026
- Source-Free Graph Foundation Model Adaptation via Pseudo-Source ReconstructionLiang Yang, Hui Ning, Jiaming Zhuo, Ziyi Ma et al.AAAI 2026
Builds on18
- Open Graph Benchmark: Datasets for Machine Learning on GraphsWeihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong et al.NeurIPS 2020 · 3,935 citations
- How Powerful are Spectral Graph Neural NetworksXiyuan Wang, Muhan ZhangICML 2022 · 309 citations
- Unsupervised Domain Adaptive Graph Convolutional NetworksMan Wu, Shirui Pan, Chuan Zhou, Xiaojun Chang et al.WWW 2020 · 221 citations
- Convolutional Neural Networks on Graphs with Chebyshev Approximation, RevisitedMingguo He, Zhewei Wei, Ji-Rong WenNeurIPS 2022 · 220 citations
- Adversarial Deep Network Embedding for Cross-Network Node ClassificationXiao Shen, Quanyu Dai, Fu-Lai Chung, Wei Lu et al.AAAI 2020 · 99 citations
Related papers
- Can Modifying Data Address Graph Domain Adaptation?Renhong Huang, Jiarong Xu, Xin Jiang, Ruichuan An et al.KDD 2024 · 1 citation
- SA-GDA: Spectral Augmentation for Graph Domain AdaptationJinhui Pang, Zixuan Wang, Jiliang Tang, Mingyan Xiao et al.ACM MM 2023 · 14 citations
- Multi-source Unsupervised Domain Adaptation on Graphs with Transferability ModelingTianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang WangKDD 2024 · 5 citations
- Rethinking Propagation for Unsupervised Graph Domain AdaptationMeihan Liu, Zeyu Fang, Zhen Zhang, Ming Gu et al.AAAI 2024 · 45 citations
- Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain AdaptationWei Chen, Guo Ye, Yakun Wang, Zhao Zhang et al.AAAI 2025 · 13 citations
