Graffe: Graph Representation Learning via Diffusion Probabilistic Models
By: Dingshuo Chen , Shuchen Xue , Liuji Chen and more
Potential Business Impact:
Teaches computers to understand complex connections.
Diffusion probabilistic models (DPMs), widely recognized for their potential to generate high-quality samples, tend to go unnoticed in representation learning. While recent progress has highlighted their potential for capturing visual semantics, adapting DPMs to graph representation learning remains in its infancy. In this paper, we introduce Graffe, a self-supervised diffusion model proposed for graph representation learning. It features a graph encoder that distills a source graph into a compact representation, which, in turn, serves as the condition to guide the denoising process of the diffusion decoder. To evaluate the effectiveness of our model, we first explore the theoretical foundations of applying diffusion models to representation learning, proving that the denoising objective implicitly maximizes the conditional mutual information between data and its representation. Specifically, we prove that the negative logarithm of the denoising score matching loss is a tractable lower bound for the conditional mutual information. Empirically, we conduct a series of case studies to validate our theoretical insights. In addition, Graffe delivers competitive results under the linear probing setting on node and graph classification tasks, achieving state-of-the-art performance on 9 of the 11 real-world datasets. These findings indicate that powerful generative models, especially diffusion models, serve as an effective tool for graph representation learning.
Similar Papers
Graph Diffusion that can Insert and Delete
Machine Learning (CS)
Designs new molecules by adding or removing atoms.
Graph Conditioned Diffusion for Controllable Histopathology Image Generation
CV and Pattern Recognition
Makes fake medical pictures for training doctors.
Automated Learning of Semantic Embedding Representations for Diffusion Models
Machine Learning (CS)
Makes computers understand pictures better for learning.