Retrieval With Learned Similarities

Abstract

Retrieval plays a fundamental role in recommendation systems, search, and natural language processing (NLP) by efficiently finding relevant items from a large corpus given a query. Dot products have been widely used as the similarity function in such tasks, enabled by Maximum Inner Product Search (MIPS) algorithms for efficient retrieval. However, state-of-the-art retrieval algorithms have migrated to learned similarities. These advanced approaches encompass multiple query embeddings, complex neural networks, direct item ID decoding via beam search, and hybrid solutions. Unfortunately, we lack efficient solutions for retrieval in these state-of-the-art setups. Our work addresses this gap by investigating efficient retrieval techniques with expressive learned similarity functions. We establish Mixture-of-Logits (MoL) as a universal approximator of similarity functions, demonstrate that MoL's expressiveness can be realized empirically to achieve superior performance on diverse retrieval

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyding2024retrieval

Related papers

• Revisiting Neural Retrieval On Accelerators (2023)9.41
• Deep Retrieval: Learning A Retrievable Structure For Large-scale Recommendations (2020)0.00
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Representation Learning For Efficient And Effective Similarity Search And Recommendation (2021)0.00
• Matching-oriented Product Quantization For Ad-hoc Retrieval (2021)2.29
• Vector Retrieval With Similarity And Diversity: How Hard Is It? (2024)0.00
• Large Reasoning Embedding Models: Towards Next-generation Dense Retrieval Paradigm (2025)0.00
• Learning Similarity Preserving Binary Codes For Recommender Systems (2022)0.00