Patent Representation Learning via Self-supervision

arXiv:2511.10657 · cs.CL, cs.AI, cs.LG · Submitted 2025-11-03 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2025-11-03

Updated: 2026-09-07

Comments: v3: corrects a subset of dropout-only baseline results affected by an implementation error, and aligns the methodology description with the released implementation; conclusions unchanged

Journal ref: ICTIR 2026 - International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval, Jul 2026, Melbourne, Australia. pp.436-445

Code: https://github.com/ZoeYou/patentmapv0

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embeddings — 27× in this paper · explained in 2 episodes
• Calibration — 19× in this paper · explained in 7 episodes
• Representation Learning — 18× in this paper · explained in 2 episodes
• Alignment — 15× in this paper · explained in 1 episode
• Benchmark — 15× in this paper · explained in 2 episodes
• Contrastive Learning — 11× in this paper · explained in 5 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Self-Supervised Learning — 3× in this paper · explained in 7 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Domain Adaptation — 2× in this paper · explained in 5 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Harvard USPTO Patent Dataset — 2× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment Problem — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Local Invariance — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• DAPFAM: A Domain-Aware Family-level Dataset to benchmark cross domain patent retrieval
• Clustering-Aware Negative Sampling for Unsupervised Sentence Representation
• Citation-Driven Multi-View Training for Patent Embeddings: QaECTER and Sophia-Bench
• CERT: Contrastive Self-supervised Learning for Language Understanding
• SimCSE: Simple Contrastive Learning of Sentence Embeddings
• PaECTER: Patent-level Representation Learning using Citation-informed Transformers
• Towards General Text Embeddings with Multi-stage Contrastive Learning
• PatentMatch: A Dataset for Matching Patent Claims & Prior Art
• SciRepEval: A Multi-Format Benchmark for Scientific Document Representations
• The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications
• Qwen3 Technical Report
• Smoothed Contrastive Learning for Unsupervised Sentence Embedding
• CLEAR: Contrastive Learning for Sentence Representation
• SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives
• ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer
• Patent Language Model Pretraining with ModernBERT
• Debiased Contrastive Learning of Unsupervised Sentence Representations

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering