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

arXiv:2404.13571v1 Announce Type: new
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 …

abstract arxiv challenge challenges cs.ai cs.lg data distribution fields gnns graph graph neural networks graphs however language language models large language large language models llms multimedia networks neural networks shift success test training type