# From Noisy to Native: LLM-driven Graph Restoration for Test-Time Graph Domain Adaptation

arXiv: https://arxiv.org/abs/2510.07762 · HTML: https://mlsanity.com/paper/2510.07762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://mlsanity.com/paper/2207.08208/) (2022)
- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE](https://mlsanity.com/paper/2103.10022/) (2021)
- [A Survey of Large Language Models for Graphs](https://mlsanity.com/paper/2405.08011/) (2024)
- [Empowering Graph Representation Learning with Test-Time Graph Transformation](https://mlsanity.com/paper/2210.03561/) (2022)
- [Adversarial Deep Network Embedding for Cross-network Node Classification](https://mlsanity.com/paper/2002.07366/) (2020)
- [TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation](https://mlsanity.com/paper/2303.09870/) (2023)
- [Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation](https://mlsanity.com/paper/2403.01467/) (2024)
- [Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs](https://mlsanity.com/paper/2402.11153/) (2024)
- [Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropy](https://mlsanity.com/paper/2309.07402/) (2023)

## Abstract (arXiv)

Graph domain adaptation (GDA) has achieved great attention due to its effectiveness in addressing the domain shift between train and test data. A significant bottleneck in existing graph domain adaptation methods is their reliance on source-domain data, which is often unavailable due to privacy or security concerns. This limitation has driven the development of Test-Time Graph Domain Adaptation (TT-GDA), which aims to transfer knowledge without accessing the source examples. Inspired by the generative power of large language models (LLMs), we introduce a novel framework that reframes TT-GDA as a generative graph restoration problem, "restoring the target graph to its pristine, source-domain-like state". There are two key challenges: (1) We need to construct a reasonable graph restoration process and design an effective encoding scheme that an LLM can understand, bridging the modality gap. (2) We need to devise a mechanism to ensure the restored graph acquires the intrinsic features of the source domain, even without access to the source data. To ensure the effectiveness of graph restoration, we propose GRAIL, that restores the target graph into a state that is well-aligned with the source domain. Specifically, we first compress the node representations into compact latent features and then use a graph diffusion process to model the graph restoration process. Then a quantization module encodes the restored features into discrete tokens. Building on this, an LLM is fine-tuned as a generative restorer to transform a "noisy" target graph into a "native" one. To further improve restoration quality, we introduce a reinforcement learning process guided by specialized alignment and confidence rewards. Extensive experiments demonstrate the effectiveness of our approach across various datasets.