TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
Jun Dan, Weiming Liu, Chunfeng Xie, Hua Yu, Shunjie Dong, Yanchao Tan
Abstract
Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods.
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.
8 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
- SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation cites Graph Contrastive Learning with Augmentations
- Graph Contrastive Learning with Augmentations cites Invariant Information Clustering for Unsupervised Image Classification and Segmentation
- Graph Contrastive Learning with Augmentations cites GPT-GNN: Generative Pre-Training of Graph Neural Networks
- Graph Contrastive Learning with Augmentations cites GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
Cited by top-tier papers8
- Learning Structure-Semantic Evolution Trajectories for Graph Domain AdaptationWei Chen, Xingyu Guo, Shuang Li, Yan Zhong et al.ICLR 2026 · 8 citations
- Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation LearningYingxu Wang, Mengzhu Wang, Zhichao Huang, Suyu Liu et al.AAAI 2026 · 7 citations
- SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic AugmentationJunhua Shi, Qingyun Sun, Haonan Yuan, Xingcheng FuAAAI 2026 · 3 citations
- Gains: Fine-grained Federated Domain Adaptation in Open SetZhengyi Zhong, Wenzheng Jiang, Weidong Bao, Ji Wang et al.NeurIPS 2025 · 3 citations
- Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier RegularizationWeiming Liu, Xinting Liao, Jun Dan, Fan Wang et al.NeurIPS 2025 · 2 citations
Builds on33
- Graph Contrastive Learning with AugmentationsYuning You, Tianlong Chen, Yongduo Sui, Ting Chen et al.NeurIPS 2020 · 3,042 citations
- Invariant Information Clustering for Unsupervised Image Classification and SegmentationXu Ji, Andrea Vedaldi, João F. HenriquesICCV 2019 · 956 citations
- GCC: Graph Contrastive Coding for Graph Neural Network Pre-TrainingJiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang et al.KDD 2020 · 755 citations
- Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain AdaptationRuijia Xu, Guanbin Li, Jihan Yang, Liang LinICCV 2019 · 563 citations
- GPT-GNN: Generative Pre-Training of Graph Neural NetworksZiniu Hu, Yuxiao Dong, Kuansan Wang, Kai-Wei Chang et al.KDD 2020 · 438 citations
Related papers
- HOGDA: Boosting Semi-supervised Graph Domain Adaptation via High-Order Structure-Guided Adaptive Feature AlignmentJun Dan, Weiming Liu, Mushui Liu, Chunfeng Xie et al.ACM MM 2024 · 9 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
- Open-Set Graph Domain Adaptation via Separate Domain AlignmentYu Wang, Ronghang Zhu, Pengsheng Ji, Sheng LiAAAI 2024 · 15 citations
- Multi-source Unsupervised Domain Adaptation on Graphs with Transferability ModelingTianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang WangKDD 2024 · 5 citations
- Structure Preserving Generative Cross-Domain LearningHaifeng Xia, Zhengming DingCVPR 2020
