Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective

arXiv:2402.13556v1 Announce Type: new
Abstract: The "Graph pre-training and fine-tuning" paradigm has significantly improved Graph Neural Networks(GNNs) by capturing general knowledge without manual annotations for downstream tasks. However, due to the immense gap of data and tasks between the pre-training and fine-tuning stages, the model performance is still limited. Inspired by prompt fine-tuning in Natural Language Processing(NLP), many endeavors have been made to bridge the gap in graph domain. But existing methods simply reformulate the form of fine-tuning tasks to …

abstract alignment annotations arxiv cs.ai cs.lg data fine-tuning gap general gnns graph graph neural networks inductive knowledge networks neural networks paradigm perspective pre-training prompt tasks training type