Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning

ArXi:2605.10073v2 Announce Type: replace Pre-trained language models advance patent classification and retrieval via encoding claims as flat token sequences, yet overlooking the dependency hierarchy among claims. Incorporating the hierarchy into self-attention poses two challenges. First, claim dependencies involve relation types with varying reliability: treating them indiscriminately allows noisy technical relations to corrupt cleaner legal citation signals.