Neural Stochastic Block Model & Scalable Community-Based Graph Learning
This work addresses the challenge of scalable graph learning for large datasets, offering a flexible framework that simplifies integration with task models, though it appears incremental by building on existing methods like SBM and GAT.
The paper tackles the problem of efficiently leveraging underlying community structure in large graphs for learning tasks by proposing a scalable neural framework that adapts the Stochastic Block Model likelihood into a joint loss function for community detection and link prediction. The approach demonstrates effectiveness in applications like graph alignment and anomalous correlation detection, with contributions including improved designs such as GAT+ and scaled-cosine similarity.
This paper proposes a novel scalable community-based neural framework for graph learning. The framework learns the graph topology through the task of community detection and link prediction by optimizing with our proposed joint SBM loss function, which results from a non-trivial adaptation of the likelihood function of the classic Stochastic Block Model (SBM). Compared with SBM, our framework is flexible, naturally allows soft labels and digestion of complex node attributes. The main goal is efficient valuation of complex graph data, therefore our design carefully aims at accommodating large data, and ensures there is a single forward pass for efficient evaluation. For large graph, it remains an open problem of how to efficiently leverage its underlying structure for various graph learning tasks. Previously it can be heavy work. With our community-based framework, this becomes less difficult and allows the task models to basically plug-in-and-play and perform joint training. We currently look into two particular applications, the graph alignment and the anomalous correlation detection, and discuss how to make use of our framework to tackle both problems. Extensive experiments are conducted to demonstrate the effectiveness of our approach. We also contributed tweaks of classic techniques which we find helpful for performance and scalability. For example, 1) the GAT+, an improved design of GAT (Graph Attention Network), the scaled-cosine similarity, and a unified implementation of the convolution/attention based and the random-walk based neural graph models.