# LiNR: Model Based Neural Retrieval on GPUs at LinkedIn

arXiv: https://arxiv.org/abs/2407.13218 · HTML: https://mlsanity.com/paper/2407.13218/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 13 of 13)

- [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)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Embedding-based Retrieval in Facebook Search](https://mlsanity.com/paper/2006.11632/) (2020)
- [PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest](https://mlsanity.com/paper/2007.03634/) (2020)
- [LiGNN: Graph Neural Networks at LinkedIn](https://mlsanity.com/paper/2402.11139/) (2024)
- [Monolith: Real Time Recommendation System With Collisionless Embedding Table](https://mlsanity.com/paper/2209.07663/) (2022)
- [CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs](https://mlsanity.com/paper/2308.15136/) (2023)
- [Revisiting Neural Retrieval on Accelerators](https://mlsanity.com/paper/2306.04039/) (2023)
- [OPORP: One Permutation + One Random Projection](https://mlsanity.com/paper/2302.03505/) (2023)
- [NxtPost: User to Post Recommendations in Facebook Groups](https://mlsanity.com/paper/2202.03645/) (2022)
- [End-to-End Retrieval with Learned Dense and Sparse Representations Using Lucene](https://mlsanity.com/paper/2311.18503/) (2023)
- [Learning to Retrieve for Job Matching](https://mlsanity.com/paper/2402.13435/) (2024)

## Built on by (most cited first, 2 of 2)

- [Large Scale Retrieval for the LinkedIn Feed using Causal Language Models](https://mlsanity.com/paper/2510.14223/) (2025)
- [Retrieval with Learned Similarities](https://mlsanity.com/paper/2407.15462/) (2024)

## Abstract (arXiv)

This paper introduces LiNR, LinkedIn's large-scale, GPU-based retrieval system. LiNR supports a billion-sized index on GPU models. We discuss our experiences and challenges in creating scalable, differentiable search indexes using TensorFlow and PyTorch at production scale. In LiNR, both items and model weights are integrated into the model binary. Viewing index construction as a form of model training, we describe scaling our system for large indexes, incorporating full scans and efficient filtering. A key focus is on enabling attribute-based pre-filtering for exhaustive GPU searches, addressing the common challenge of post-filtering in KNN searches that often reduces system quality. We further provide multi-embedding retrieval algorithms and strategies for tackling cold start issues in retrieval. Our advancements in supporting larger indexes through quantization are also discussed. We believe LiNR represents one of the industry's first Live-updated model-based retrieval indexes. Applied to out-of-network post recommendations on LinkedIn Feed, LiNR has contributed to a 3% relative increase in professional daily active users. We envisage LiNR as a step towards integrating retrieval and ranking into a single GPU model, simplifying complex infrastructures and enabling end-to-end optimization of the entire differentiable infrastructure through gradient descent.