Graph Neural Networks frequently exhibit significant performance degradation in the out-of-distribution test scenario. While test-time training (TTT) offers a promising solution, existing Parameter Finetuning (PaFT) paradigm suffer from catastrophic forgetting, hindering their real-world applicability. We propose TTReFT, a novel Test-Time Representation FineTuning framework that transitions the adaptation target from model parameters to latent representations. Specifically, TTReFT achieves this through three key innovations: (1) uncertainty-guided node selection for specific interventions, (2) low-rank representation interventions that preserve pre-trained knowledge, and (3) an intervention-aware masked autoencoder that dynamically adjust masking strategy to accommodate the node selection scheme. Theoretically, we establish guarantees for TTReFT in OOD settings. Empirically, extensive experiments across five benchmark datasets demonstrate that TTReFT achieves consistent and superior performance. Our work establishes representation finetuning as a new paradigm for graph TTT, offering both theoretical grounding and immediate practical utility for real-world deployment.
@article{arxiv.2601.21615,
title = {Beyond Parameter Finetuning: Test-Time Representation Refinement for Node Classification},
author = {Jiaxin Zhang and Yiqi Wang and Siwei Wang and Xihong Yang and Yu Shi and Xinwang Liu and En Zhu},
journal= {arXiv preprint arXiv:2601.21615},
year = {2026}
}