GRAVITY: A Controversial Graph Representation Learning for Vertex Classification

TL;DR

GRAVITY introduces a physics-inspired graph representation learning framework that models vertex interactions as forces, enabling dynamic, context-aware embeddings that improve vertex classification accuracy.

Contribution

It proposes a novel force-based approach for graph embedding that adaptively modulates receptive fields, enhancing class separation and semantic coherence.

Findings

Achieves competitive results on real-world benchmarks.

Excels in both transductive and inductive classification tasks.

Demonstrates improved class boundary delineation.

Abstract

In the quest of accurate vertex classification, we introduce GRAVITY (Graph-based Representation leArning via Vertices Interaction TopologY), a framework inspired by physical systems where objects self-organize under attractive forces. GRAVITY models each vertex as exerting influence through learned interactions shaped by structural proximity and attribute similarity. These interactions induce a latent potential field in which vertices move toward energy efficient positions, coalescing around class-consistent attractors and distancing themselves from unrelated groups. Unlike traditional message-passing schemes with static neighborhoods, GRAVITY adaptively modulates the receptive field of each vertex based on a learned force function, enabling dynamic aggregation driven by context. This field-driven organization sharpens class boundaries and promotes semantic coherence within latent clusters. Experiments on real-world benchmarks show that GRAVITY yields competitive embeddings, excelling in both transductive and inductive vertex classification tasks.