PHAGE improves patent classification, retrieval, and clustering by modeling heterogeneous claim dependencies with a typed graph, connectivity mask, and dual-granularity contrastive learning.
arXiv preprint arXiv:2505.19347 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Multi-task evaluation of 22 patent embedding models finds task-specific fine-tuning benefits and significant cross-landscape retrieval degradation that cannot be fixed by hybrid fusion.
citing papers explorer
-
Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning
PHAGE improves patent classification, retrieval, and clustering by modeling heterogeneous claim dependencies with a typed graph, connectivity mask, and dual-granularity contrastive learning.
-
Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering
Multi-task evaluation of 22 patent embedding models finds task-specific fine-tuning benefits and significant cross-landscape retrieval degradation that cannot be fixed by hybrid fusion.