{"ID":2883278,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08954","arxiv_id":"2508.08954","title":"GRAVITY: A Controversial Graph Representation Learning for Vertex Classification","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.","short_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...","url_abs":"https://arxiv.org/abs/2508.08954","url_pdf":"https://arxiv.org/pdf/2508.08954v1","authors":"[\"Etienne Gael Tajeuna\",\"Jean Marie Tshimula\"]","published":"2025-08-12T14:12:51Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}