Vincent Jung, Alba Carballo-Castro, Yiming Qin, Lonneke van der Plas, Pascal Frossard · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28618 · open-access PDF
Model generatif graf biasanya menggunakan arsitektur Transformer spesifik graf untuk secara bersama-sama memperbarui fitur node dan edge. Namun, arsitektur ini tidak secara langsung mendapat manfaat dari implementasi hardware-aware attention, membatasi skalabilitas mereka. Adaptasi ini, bagaimanapun, tidak trivial: fitur edge dan graph-level harus disuntikkan ke dalam skor perhatian berpasangan, masker graf harus dihormati, dan pembaruan dinamik edge tetap menjadi sumber utama penggunaan memori persegi.
Machine translation (Meta M2M100); the English original follows.
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
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange