# Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation

arXiv: https://arxiv.org/abs/2606.00808 · HTML: https://mlsanity.com/paper/2606.00808/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 30 May 2026.

## Builds on (most cited first, 30 of 37)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Weisfeiler and Lehman Go Cellular: CW Networks](https://mlsanity.com/paper/2106.12575/) (2021)
- [Self-Supervised Learning of Graph Neural Networks: A Unified Review](https://mlsanity.com/paper/2102.10757/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [A Survey of Label-noise Representation Learning: Past, Present and Future](https://mlsanity.com/paper/2011.04406/) (2020)
- [Accurate Learning of Graph Representations with Graph Multiset Pooling](https://mlsanity.com/paper/2102.11533/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Domain Adaptation without Source Data](https://mlsanity.com/paper/2007.01524/) (2020)
- [Empowering Graph Representation Learning with Test-Time Graph Transformation](https://mlsanity.com/paper/2210.03561/) (2022)
- [SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation](https://mlsanity.com/paper/2502.05424/) (2025)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [When Source-Free Domain Adaptation Meets Learning with Noisy Labels](https://mlsanity.com/paper/2301.13381/) (2023)
- [Uncertainty-guided Source-free Domain Adaptation](https://mlsanity.com/paper/2208.07591/) (2022)
- [CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification](https://mlsanity.com/paper/2306.04979/) (2023)
- [Path Neural Networks: Expressive and Accurate Graph Neural Networks](https://mlsanity.com/paper/2306.05955/) (2023)
- [Source-Free Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2202.06174/) (2022)
- [LEAD: Learning Decomposition for Source-free Universal Domain Adaptation](https://mlsanity.com/paper/2403.03421/) (2024)
- [SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentation](https://mlsanity.com/paper/2403.10834/) (2024)
- [Source Free Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2112.00955/) (2021)
- [Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation](https://mlsanity.com/paper/2403.01467/) (2024)
- [Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2412.11654/) (2024)
- [Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2407.11052/) (2024)
- [Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning](https://mlsanity.com/paper/2508.00716/) (2025)

## Abstract (arXiv)

Source-free graph domain adaptation (SF-GDA) aims to adapt source-trained graph models to unlabeled target graphs when source graphs are no longer accessible. A central obstacle is pseudo-label reliability: under feature and topological shifts, source-induced predictions may become confidently wrong, and indiscriminate self-training can amplify systematic errors through graph message passing. This paper studies SF-GDA from a selective pseudo-labeling perspective. Instead of assuming globally bounded pseudo-label noise over the entire target domain, we identify a confidence-consistent safe subspace on which pseudo-label noise can be controlled under restricted posterior discrepancy, and derive a target-risk decomposition that separates safe-subspace fitting error, selected-label noise, and uncertain-set risk. Guided by this analysis, we propose SafeSubspace Pseudo-Label Refinement (S2PLR), a source-free graph adaptation framework that applies hard pseudo-label supervision only to target graphs supported by both semantic and structural evidence. Specifically, S2PLR estimates semantic reliability using source-committee confidence and disagreement, learns a targetintrinsic structural representation via graph contrastive learning, verifies pseudo-labels through neighborhood consistency, and exploits the remaining uncertain samples with noise-tolerant soft regularization rather than unreliable hard labels. Experiments on image and real-world graph benchmarks under different domain shifts demonstrate that S2PLR achieves robust and competitive performance across diverse source-free transfer settings.