arXiv：cs.AI· Sujith Subramanian, P N Bhargav Teja, Susen Sarkar, Rajasekhara Reddy Duvvuru Muni·· 11 小时前
专利权利要求无监督分类的嵌入几何与聚类算法基准测试
Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification
AI 导读
研究在 45,000 件美国专利上训练了双曲与欧氏 VAE（96 次运行、6 个种子），双曲模型在 3,000 次查询的 top-10 结果中跨类别检索现有技术的比例为 18.76%，比欧氏模型的 12.34% 高出 52%。
正文
Abstract:Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult. This paper asks if an unsupervised representation trained on patent text can recover relevant connections that code-restricted search cannot, and if hyperbolic space helps. We trained a hyperbolic and a matched Euclidean Variational Autoencoder (VAE) on 45,000 US patents (96 runs, 6 seeds). The hyperbolic model retrieves genuinely cross-category prior art 52% more often than the Euclidean model (18.76% vs. 12.34% of top-10 results, 3,000 queries). This represents a practical gain for the motivating search problem. The hyperbolic model agrees less with official classification (NMI 0.2392 vs. 0.3206), which we explain geometrically: the two measures capture different goals, and only one aligns with prior-art search needs. In a study of 10 technology domains (50,000 more patents), we find that a domain's classification breadth--the number of distinct CPC subgroups spanned--predicts approach performance (Pearson r=-0.642, p=0.045, N=10), and that patents per subgroup is an even stronger predictor (r=0.715, p=0.020). This provides a checkable signal for practitioners to determine where the method is most valuable. We report all findings with statistical transparency and release a complete, 91-test automated implementation.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.12997 [cs.AI] |
| (or arXiv:2610.12997v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12997 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Susen Sarkar [view email]
[v1]
Fri, 9 Oct 2026 05:02:37 UTC (2,168 KB)
来源：arXiv：cs.AI · arxiv.org