# Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System

arXiv: https://arxiv.org/abs/2602.16124 · HTML: https://mlsanity.com/paper/2602.16124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)](https://mlsanity.com/paper/1405.5869/) (2014)
- [Practical and Optimal LSH for Angular Distance](https://mlsanity.com/paper/1509.02897/) (2015)
- [Learning Tree-based Deep Model for Recommender Systems](https://mlsanity.com/paper/1801.02294/) (2018)
- [Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations](https://mlsanity.com/paper/2306.08121/) (2023)
- [Joint Optimization of Tree-based Index and Deep Model for Recommender Systems](https://mlsanity.com/paper/1902.07565/) (2019)
- [Generative Recommendation with Semantic IDs: A Practitioner's Handbook](https://mlsanity.com/paper/2507.22224/) (2025)
- [A Comprehensive Survey on Retrieval Methods in Recommender Systems](https://mlsanity.com/paper/2407.21022/) (2024)
- [Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation](https://mlsanity.com/paper/2202.10226/) (2022)
- [Robust Collaborative Filtering to Popularity Distribution Shift](https://mlsanity.com/paper/2310.10696/) (2023)
- [Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations](https://mlsanity.com/paper/2007.07203/) (2020)
- [Trinity: Syncretizing Multi-/Long-tail/Long-term Interests All in One](https://mlsanity.com/paper/2402.02842/) (2024)
- [Optimizing Recall or Relevance? A Multi-Task Multi-Head Approach for Item-to-Item Retrieval in Recommendation](https://mlsanity.com/paper/2506.06239/) (2025)
- [Taming the Long Tail: Denoising Collaborative Information for Robust Semantic ID Generation](https://mlsanity.com/paper/2510.25622/) (2025)
- [MERGE: Next-Generation Item Indexing Paradigm for Large-Scale Streaming Recommendation](https://mlsanity.com/paper/2601.20199/) (2026)

## Abstract (arXiv)

Approximate nearest neighbor (ANN) search is widely used in the retrieval stage of large-scale recommendation systems. In this stage, candidate items are indexed using their learned embedding vectors, and ANN search is executed for each user (or item) query to retrieve a set of relevant items. However, ANN-based retrieval has two key limitations. First, item embeddings and their indices are typically learned in separate stages: indexing is often performed offline after embeddings are trained, which can yield suboptimal retrieval quality-especially for newly created items. Second, although ANN offers sublinear query time, it must still be run for every request, incurring substantial computation cost at industry scale. In this paper, we propose MultiFaceted Learnable Index (MFLI), a scalable, real-time retrieval paradigm that learns multifaceted item embeddings and indices within a unified framework and eliminates ANN search at serving time. Specifically, we construct a multifaceted hierarchical codebook via residual quantization of item embeddings and co-train the codebook with the embeddings. We further introduce an efficient multifaceted indexing structure and mechanisms that support real-time updates. At serving time, the learned hierarchical indices are used directly to identify relevant items, avoiding ANN search altogether. Extensive experiments on real-world data with billions of users show that MFLI improves recall on engagement tasks by up to 11.8%, cold-content delivery by up to 57.29%, and semantic relevance by 13.5% compared with prior state-of-the-art methods. We also deploy MFLI in the system and report online experimental results demonstrating improved engagement, less popularity bias, and higher serving efficiency.