Unifying Generation and Prediction on Graphs with Latent Graph Diffusion

作     者：Zhou, Cai Wang, Xiyuan Zhang, Muhan 

作者机构：Department of Automation Tsinghua University China Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States Institute for Artificial Intelligence Peking University China School of Intelligence Science and Technology Peking University China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Prediction models 

摘      要：In this paper, we propose the first framework that enables solving graph learning tasks of all levels (node, edge and graph) and all types (generation, regression and classification) using one formulation. We first formulate prediction tasks including regression and classification into a generic (conditional) generation framework, which enables diffusion models to perform deterministic tasks with provable guarantees. We then propose Latent Graph Diffusion (LGD), a generative model that can generate node, edge, and graph-level features of all categories simultaneously. We achieve this goal by embedding the graph structures and features into a latent space leveraging a powerful encoder and decoder, then training a diffusion model in the latent space. LGD is also capable of conditional generation through a specifically designed cross-attention mechanism. Leveraging LGD and the all tasks as generation formulation, our framework is capable of solving graph tasks of various levels and types. We verify the effectiveness of our framework with extensive experiments, where our models achieve state-of-the-art or highly competitive results across a wide range of generation and regression tasks. © 2024, CC BY.