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

2025-10-09

AI Summary

Test-time graph domain adaptation (GDA) faces the practical challenge of inaccessible source-domain data, hindering conventional knowledge transfer. Method: This paper proposes the first generative graph restoration framework that inversely reconstructs the target graph structure into a source-like state—enabling source-free knowledge transfer. It reformulates GDA as a graph structural recovery problem, integrating node representation compression, graph diffusion modeling, and quantized encoding, and—novelty—introduces large language model (LLM)-driven graph generation. A dual-objective reinforcement learning strategy, guided by alignment quality and prediction confidence, fine-tunes the LLM. Results: Extensive experiments on multiple benchmark datasets demonstrate that our method significantly outperforms existing source-free GDA approaches, validating the effectiveness and generalizability of the generative paradigm for graph domain adaptation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Restoring target graphs to source-domain-like states
• Bridging modality gaps for LLM graph understanding
• Achieving domain alignment without source data access

Innovation

• LLM-driven generative graph restoration for domain adaptation
• Graph diffusion and quantization for feature encoding
• Reinforcement learning with alignment and confidence rewards