Comparing Neighbors Together Makes It Easy: Jointly Comparing Multiple Candidates For Efficient And Effective Retrieval
2024 · Jonghyun Song, Cheyon Jin, Wenlong Zhao, et al.
Abstract
A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on this small subset is often susceptible to error propagation from the bi-encoders, which limits the overall performance. To address these issues, we propose the Comparing Multiple Candidates (CMC) framework. CMC compares a query and multiple embeddings of similar candidates (i.e., neighbors) through shallow self-attention layers, delivering rich representations contextualized to each other. Furthermore, CMC is scalable enough to handle multiple comparisons simultaneously. For example, comparing ~10K candidates with CMC takes a similar amount of time as comparing 16 candidates with CE. Experimental results on the ZeSHEL dataset demonstrate that CMC, when plugged in between bi-encoders and cross-encoders as a seamless intermediate reranker (BE-CMC-CE), can
Authors
(none)
Tags
Stats
Related papers
- Candidate Set Re-ranking For Composed Image Retrieval With Dual Multi-modal Encoder (2023)2.64
- CODER: An Efficient Framework For Improving Retrieval Through Contextual Document Embedding Reranking (2021)7.16
- Adaptive Retrieval And Scalable Indexing For K-nn Search With Cross-encoders (2024)0.00
- Retrieve Fast, Rerank Smart: Cooperative And Joint Approaches For Improved Cross-modal Retrieval (2021)10.97
- Knn-embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrieval (2022)3.58
- Moving Towards Centers: Re-ranking With Attention And Memory For Re-identification (2021)8.09
- CSMF: Cascaded Selective Mask Fine-tuning For Multi-objective Embedding-based Retrieval (2025)0.00
- Efficient K-nn Search With Cross-encoders Using Adaptive Multi-round CUR Decomposition (2023)0.00