Graph Force Learning

TL;DR

GForce is a novel force-based graph learning model inspired by physics, which effectively preserves structural information during feature embedding, outperforming existing methods on benchmark datasets.

Contribution

The paper introduces GForce, a physics-inspired graph learning model that better preserves structural information compared to previous approaches.

Findings

GForce outperforms baseline methods on benchmark datasets.

The model effectively captures structural information in feature learning.

Physics-inspired forces improve node representation quality.

Abstract

Features representation leverages the great power in network analysis tasks. However, most features are discrete which poses tremendous challenges to effective use. Recently, increasing attention has been paid on network feature learning, which could map discrete features to continued space. Unfortunately, current studies fail to fully preserve the structural information in the feature space due to random negative sampling strategy during training. To tackle this problem, we study the problem of feature learning and novelty propose a force-based graph learning model named GForce inspired by the spring-electrical model. GForce assumes that nodes are in attractive forces and repulsive forces, thus leading to the same representation with the original structural information in feature learning. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of the proposed framework. Furthermore, GForce opens up opportunities to use physics models to model node interaction for graph learning.