Test-Time Training on Graphs with Large Language Models (LLMs)

TL;DR

This paper introduces LLMTTT, a novel test-time training method for graphs that leverages Large Language Models as annotators, improving out-of-distribution generalization by adaptive node selection and a two-stage training process.

Contribution

The paper proposes a new test-time training pipeline using LLMs for graph data, with a hybrid node selection strategy and a tailored training approach, enhancing OOD performance.

Findings

LLMTTT outperforms existing OOD methods in experiments.

The hybrid node selection improves annotation quality.

Theoretical analysis supports the method's validity.

Abstract

Graph Neural Networks have demonstrated great success in various fields of multimedia. However, the distribution shift between the training and test data challenges the effectiveness of GNNs. To mitigate this challenge, Test-Time Training (TTT) has been proposed as a promising approach. Traditional TTT methods require a demanding unsupervised training strategy to capture the information from test to benefit the main task. Inspired by the great annotation ability of Large Language Models (LLMs) on Text-Attributed Graphs (TAGs), we propose to enhance the test-time training on graphs with LLMs as annotators. In this paper, we design a novel Test-Time Training pipeline, LLMTTT, which conducts the test-time adaptation under the annotations by LLMs on a carefully-selected node set. Specifically, LLMTTT introduces a hybrid active node selection strategy that considers not only node diversity and representativeness, but also prediction signals from the pre-trained model. Given annotations from LLMs, a two-stage training strategy is designed to tailor the test-time model with the limited and noisy labels. A theoretical analysis ensures the validity of our method and extensive experiments demonstrate that the proposed LLMTTT can achieve a significant performance improvement compared to existing Out-of-Distribution (OOD) generalization methods.