GRAVITY: A Controversial Graph Representation Learning for Vertex Classification

2025-08-12

AI Summary

To address the insufficient joint modeling of structural proximity and attribute similarity, as well as the static receptive field limitation in graph node classification, this paper proposes GRAVITY—a physics-inspired framework that dynamically models node interactions driven jointly by structure and attributes via learnable force functions. It constructs an optimizable potential field in latent space, guiding nodes to evolve toward energy-minimizing positions to achieve intra-class cohesion and inter-class separation. Crucially, GRAVITY abandons fixed-neighborhood message passing, enabling context-aware adaptive receptive field adjustment and semantics-aware information aggregation. Evaluated on multiple benchmark datasets, GRAVITY achieves state-of-the-art performance on both transductive and inductive node classification tasks, yielding more discriminative node embeddings.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Modeling vertex interactions via learned force functions for classification
• Adaptively modulating receptive fields for dynamic context aggregation
• Enhancing class boundaries through field-driven semantic coherence

Innovation

• Dynamic force-based vertex interaction modeling
• Adaptive receptive field modulation via learned forces
• Energy-efficient latent potential field organization