Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes

Yusheng Zhao, Qixin Zhang, Xiao Luo, Junyu Luo, Wei Ju, Zhiping Xiao, Ming Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78003-78022, 2025.

Abstract

Test-time adaptation aims to adapt a well-trained model using test data only, without accessing training data. It is a crucial topic in machine learning, enabling a wide range of applications in the real world, especially when it comes to data privacy. While existing works on test-time adaptation primarily focus on Euclidean data, research on non-Euclidean graph data remains scarce. Prevalent graph neural network methods could encounter serious performance degradation in the face of test-time domain shifts. In this work, we propose a novel method named Adaptive Subgraph-based Selection and Regularized Prototype Supervision (ASSESS) for reliable test-time adaptation on graphs. Specifically, to achieve flexible selection of reliable test graphs, ASSESS adopts an adaptive selection strategy based on fine-grained individual-level subgraph mutual information. Moreover, to utilize the information from both training and test graphs, ASSESS constructs semantic prototypes from the well-trained model as prior knowledge from the unknown training graphs and optimizes the posterior given the unlabeled test graphs. We also provide a theoretical analysis of the proposed algorithm. Extensive experiments verify the effectiveness of ASSESS against various baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhao25ai, title = {Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes}, author = {Zhao, Yusheng and Zhang, Qixin and Luo, Xiao and Luo, Junyu and Ju, Wei and Xiao, Zhiping and Zhang, Ming}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {78003--78022}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhao25ai/zhao25ai.pdf}, url = {https://proceedings.mlr.press/v267/zhao25ai.html}, abstract = {Test-time adaptation aims to adapt a well-trained model using test data only, without accessing training data. It is a crucial topic in machine learning, enabling a wide range of applications in the real world, especially when it comes to data privacy. While existing works on test-time adaptation primarily focus on Euclidean data, research on non-Euclidean graph data remains scarce. Prevalent graph neural network methods could encounter serious performance degradation in the face of test-time domain shifts. In this work, we propose a novel method named Adaptive Subgraph-based Selection and Regularized Prototype Supervision (ASSESS) for reliable test-time adaptation on graphs. Specifically, to achieve flexible selection of reliable test graphs, ASSESS adopts an adaptive selection strategy based on fine-grained individual-level subgraph mutual information. Moreover, to utilize the information from both training and test graphs, ASSESS constructs semantic prototypes from the well-trained model as prior knowledge from the unknown training graphs and optimizes the posterior given the unlabeled test graphs. We also provide a theoretical analysis of the proposed algorithm. Extensive experiments verify the effectiveness of ASSESS against various baselines.} }
Endnote
%0 Conference Paper %T Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes %A Yusheng Zhao %A Qixin Zhang %A Xiao Luo %A Junyu Luo %A Wei Ju %A Zhiping Xiao %A Ming Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhao25ai %I PMLR %P 78003--78022 %U https://proceedings.mlr.press/v267/zhao25ai.html %V 267 %X Test-time adaptation aims to adapt a well-trained model using test data only, without accessing training data. It is a crucial topic in machine learning, enabling a wide range of applications in the real world, especially when it comes to data privacy. While existing works on test-time adaptation primarily focus on Euclidean data, research on non-Euclidean graph data remains scarce. Prevalent graph neural network methods could encounter serious performance degradation in the face of test-time domain shifts. In this work, we propose a novel method named Adaptive Subgraph-based Selection and Regularized Prototype Supervision (ASSESS) for reliable test-time adaptation on graphs. Specifically, to achieve flexible selection of reliable test graphs, ASSESS adopts an adaptive selection strategy based on fine-grained individual-level subgraph mutual information. Moreover, to utilize the information from both training and test graphs, ASSESS constructs semantic prototypes from the well-trained model as prior knowledge from the unknown training graphs and optimizes the posterior given the unlabeled test graphs. We also provide a theoretical analysis of the proposed algorithm. Extensive experiments verify the effectiveness of ASSESS against various baselines.
APA
Zhao, Y., Zhang, Q., Luo, X., Luo, J., Ju, W., Xiao, Z. & Zhang, M.. (2025). Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:78003-78022 Available from https://proceedings.mlr.press/v267/zhao25ai.html.

Related Material