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

Japanese

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 pairing attention scores, graph masks must be respected, and dynamic edge updates remain a major source of square memory usage. We propose a edge-aware attention layer for graph generation that incorporates structural information through head-wise. Graph generative models are commonly used to update node and edge features. しかし、これらのアーキテクチャは、最近のハードウェアに注意を向ける実現し、その拡張性を制限します。

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

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