Exploring Task Unification in Graph Representation Learning via Generative Approach

arXiv:2403.14340v1 Announce Type: new
Abstract: Graphs are ubiquitous in real-world scenarios and encompass a diverse range of tasks, from node-, edge-, and graph-level tasks to transfer learning. However, designing specific tasks for each type of graph data is often costly and lacks generalizability. Recent endeavors under the "Pre-training + Fine-tuning" or "Pre-training + Prompt" paradigms aim to design a unified framework capable of generalizing across multiple graph tasks. Among these, graph autoencoders (GAEs), generative self-supervised models, have demonstrated their potential …

abstract arxiv cs.ai cs.lg data designing diverse edge fine-tuning generative graph graph data graph representation graphs however node pre-training representation representation learning specific tasks tasks training transfer transfer learning type unification via world