Adaptive Selection of Anchor Items for CUR-based k-NN search with Cross-Encoders

by   Nishant Yadav, et al.

Cross-encoder models, which jointly encode and score a query-item pair, are typically prohibitively expensive for k-nearest neighbor search. Consequently, k-NN search is performed not with a cross-encoder, but with a heuristic retrieve (e.g., using BM25 or dual-encoder) and re-rank approach. Recent work proposes ANNCUR (Yadav et al., 2022) which uses CUR matrix factorization to produce an embedding space for efficient vector-based search that directly approximates the cross-encoder without the need for dual-encoders. ANNCUR defines this shared query-item embedding space by scoring the test query against anchor items which are sampled uniformly at random. While this minimizes average approximation error over all items, unsuitably high approximation error on top-k items remains and leads to poor recall of top-k (and especially top-1) items. Increasing the number of anchor items is a straightforward way of improving the approximation error and hence k-NN recall of ANNCUR but at the cost of increased inference latency. In this paper, we propose a new method for adaptively choosing anchor items that minimizes the approximation error for the practically important top-k neighbors for a query with minimal computational overhead. Our proposed method incrementally selects a suitable set of anchor items for a given test query over several rounds, using anchors chosen in previous rounds to inform selection of more anchor items. Empirically, our method consistently improves k-NN recall as compared to both ANNCUR and the widely-used dual-encoder-based retrieve-and-rerank approach.


page 5

page 6

page 7

page 13

page 14

page 15

page 16


Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization

Efficient k-nearest neighbor search is a fundamental task, foundational ...

Graph Spring Network and Informative Anchor Selection for Session-based Recommendation

Session-based recommendation (SBR) aims at predicting the next item for ...

DIF Statistical Inference and Detection without Knowing Anchoring Items

Establishing the invariance property of an instrument (e.g., a questionn...

Differential item functioning via robust scaling

This paper proposes a new method for assessing differential item functio...

Relevance-based Margin for Contrastively-trained Video Retrieval Models

Video retrieval using natural language queries has attracted increasing ...

IRLI: Iterative Re-partitioning for Learning to Index

Neural models have transformed the fundamental information retrieval pro...

Please sign up or login with your details

Forgot password? Click here to reset