Efficient Nearest Neighbor Search For Cross-encoder Models Using Matrix Factorization

Abstract

Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. When the similarity is measured by dot-product between dual-encoder vectors or \(ℓ₂\)-distance, there already exist many scalable and efficient search methods. But not so when similarity is measured by more accurate and expensive black-box neural similarity models, such as cross-encoders, which jointly encode the query and candidate neighbor. The cross-encoders' high computational cost typically limits their use to reranking candidates retrieved by a cheaper model, such as dual encoder or TF-IDF. However, the accuracy of such a two-stage approach is upper-bounded by the recall of the initial candidate set, and potentially requires additional training to align the auxiliary retrieval model with the cross-encoder model. In this paper, we present an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoder. Retrieval is made efficient with CUR decomposi

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyyadav2022efficient

Related papers

• Efficient K-nn Search With Cross-encoders Using Adaptive Multi-round CUR Decomposition (2023)0.00
• Adaptive Retrieval And Scalable Indexing For K-nn Search With Cross-encoders (2024)0.00
• Predicting Pairwise Relations With Neural Similarity Encoders (2017)0.00
• Neural Collaborative Filtering Vs. Matrix Factorization Revisited (2020)19.18
• How To Make Cross Encoder A Good Teacher For Efficient Image-text Retrieval? (2024)5.24
• Comparing Neighbors Together Makes It Easy: Jointly Comparing Multiple Candidates For Efficient And Effective Retrieval (2024)4.52
• MICE: Minimal Interaction Cross-encoders For Efficient Re-ranking (2026)0.00
• Efficient Neural Ranking Using Forward Indexes And Lightweight Encoders (2023)5.24