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

• URL: http://arxiv.org/abs/2606.00808v1
• Date: Sat, 30 May 2026 16:47:21 GMT
• Title: Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation
• Abstract summary: 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.<n>This paper studies SF-GDA from a selective pseudo-labeling perspective.<n>We propose SafeSubspace Pseudo-Label Refinement (S$2$PLR), a source-free graph adaptation framework that applies hard pseudo-label supervision only to target graphs.
• Score: 41.958621280228634
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 (S$^2$PLR), a source-free graph adaptation framework that applies hard pseudo-label supervision only to target graphs supported by both semantic and structural evidence. Specifically, S$^2$PLR 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 S$^2$PLR achieves robust and competitive performance across diverse source-free transfer settings.

Related papers

• Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype Learning [7.021321989243726]
  Graph Domain Adaptation (GDA) naturally instantiates setting by transferring knowledge from labeled source graphs to unlabeled target graphs under distribution shifts.<n>Most GDA methods assume sufficient labeled source graphs, which becomes restrictive in data-efficient agentic settings.<n>We propose DEAG, a reliability-aware prototype learning framework for data-efficient GDA.
  arXiv  Detail & Related papers  (2026-09-12T16:54:53Z)
• A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning [2.436631469537453]
  We propose textbfSFT+RL, a two-stage robust UDA framework that integratesSupervised Fine Tuning and Reinforcement Learning.<n>textbfSFT+RL achieves average improvements of textbf10.2% in clean accuracy and textbf15.8% in adversarial robustness across three datasets.
  arXiv  Detail & Related papers  (2026-07-03T20:56:12Z)
• Semi-Supervised Regression with Heteroscedastic Pseudo-Labels [50.54050677867914]
  We propose an uncertainty-aware pseudo-labeling framework that dynamically adjusts pseudo-label influence from a bi-level optimization perspective.<n>We provide theoretical insights and extensive experiments to validate our approach across various benchmark SSR datasets.
  arXiv  Detail & Related papers  (2025-10-17T03:06:23Z)
• Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry [5.1511135538176]
  Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution shifts.<n>We propose Active Learning via Neural Collapse Geometry (NCAL-R), a framework that leverages the emergent geometric regularities of deep networks to counteract unreliable supervision.
  arXiv  Detail & Related papers  (2025-10-10T17:50:31Z)
• Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning [26.926061463569567]
  Nested Graph Pseudo-Label Refinement (NeGPR) is a novel framework tailored for graph-level domain adaptation with noisy labels.<n>NeGPR consistently outperforms state-of-the-art methods under severe label noise, achieving gains of up to 12.7% in accuracy.
  arXiv  Detail & Related papers  (2025-08-01T15:32:40Z)
• Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer [60.31021888394358]
  Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) We propose a SOurce-free Domain Adaptation framework for image SR (SODA-SR) to address this issue, i.e., adapt a source-trained model to a target domain with only unlabeled target data.
  arXiv  Detail & Related papers  (2023-03-31T03:14:44Z)
• Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling [56.98020855107174]
  Domain adaptation typically requires to access source domain data to utilize their distribution information for domain alignment with the target data. In many real-world scenarios, the source data may not be accessible during the model adaptation in the target domain due to privacy issue. We present a novel denoised pseudo-labeling method for this problem, which effectively makes use of the source model and unlabeled target data.
  arXiv  Detail & Related papers  (2021-09-19T06:38:21Z)
• Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation [12.716865774780704]
  State-of-the-art methods for source free domain adaptation (SFDA) are subject to strict limits. textitPR-SFDA achieves a performance of 49.0 mIoU, which is very close to that of the state-of-the-art counterparts.
  arXiv  Detail & Related papers  (2021-06-23T02:20:31Z)
• Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation [35.728603077621564]
  Existing Unsupervised Domain Adaptation (UDA) methods presumes source and target domain data to be simultaneously available during training. A pre-trained source model is always considered to be available, even though performing poorly on target due to the well-known domain shift problem. We propose a unified method to tackle adaptive noise filtering and pseudo-label refinement.
  arXiv  Detail & Related papers  (2021-03-29T22:18:34Z)
• Unsupervised Robust Domain Adaptation without Source Data [75.85602424699447]
  We study the problem of robust domain adaptation in the context of unavailable target labels and source data. We show a consistent performance improvement of over $10%$ in accuracy against the tested baselines on four benchmark datasets.
  arXiv  Detail & Related papers  (2021-03-26T16:42:28Z)
• A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data [69.091485888121]
  Unsupervised domain adaptation assumes that source and target domain data are freely available and usually trained together to reduce the domain gap. We propose a source data-free domain adaptive object detection (SFOD) framework via modeling it into a problem of learning with noisy labels.
  arXiv  Detail & Related papers  (2020-12-10T01:42:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.