כתבה
arXiv cs.AI ·
AdvSynGNN: רשתות נוירונים גרפיות מתגברות: סטרוקטור-אדפטיבי
AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation
Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. AdvSynGNN, a comprehensive architecture designed for resilient node-level representation learning, addresses these systemic vulnerabilities.
תקציר מקורי באנגליתarXiv:2602.17071v4 Announce Type: replace-cross Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. To address these systemic vulnerabilities, we present AdvSynGNN, a comprehensive architecture designed for resilient node-level representation learning. The proposed framework orchestrates multi-resolution structural synthesis alongside contrastive objectives to establish geometry-sensitive initializations. We develop a transformer backbone that adaptively accommodates heterophily by modulating attention mechanisms through learned topological signals. Central to our contribution is an integrated adversarial propagation engine, where a generative component identifies potential connectivit
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית