Newest papers

Efficient Edge-aware Attention Network for Graph Generation

Vincent Jung, Alba Carballo-Castro, Yiming Qin, Lonneke van der Plas, Pascal Frossard · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28618 · open-access PDF

Portuguese

Os modelos geradores de gráficos geralmente usam arquiteturas Transformer específicas de gráficos para atualizar conjuntamente os recursos de nó e borda. No entanto, essas arquiteturas não se beneficiam diretamente das recentes implementações de atenção consciente do hardware, limitando sua escalabilidade. A adaptação é, no entanto, não trivial: os recursos de borda e nível de gráfico devem ser injetados em pontuações de atenção em pares, as máscaras de gráficos devem ser respeitadas e as atualizações de borda dinâmicas continuam a ser uma grande fonte de uso de memória quadrática.

Machine translation (Meta M2M100); the English original follows.

Abstract

Graph generative models commonly use graph-specific Transformer architectures to jointly update node and edge features. However, these architectures do not directly benefit from recent hardware-aware attention implementations, limiting their scalability. The adaptation is, however, non-trivial: edge and graph-level features must be injected into pairwise attention scores, graph masks must be respected, and dynamic edge updates remain a major source of quadratic memory usage. We propose an edge-aware attention layer for graph generation that incorporates structural information through head-wise

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28618, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange