# Mem-Rec: Memory Efficient Recommendation System using Alternative Representation

arXiv: https://arxiv.org/abs/2305.07205 · HTML: https://mlsanity.com/paper/2305.07205/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 22 references that are in the map.
- First posted on arXiv 12 May 2023.

## Builds on (most cited first, 17 of 17)

- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [Compressing Neural Networks with the Hashing Trick](https://mlsanity.com/paper/1504.04788/) (2015)
- [The Architectural Implications of Facebook's DNN-based Personalized Recommendation](https://mlsanity.com/paper/1906.03109/) (2019)
- [Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems](https://mlsanity.com/paper/1909.02107/) (2019)
- [TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models](https://mlsanity.com/paper/2101.11714/) (2021)
- [DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference](https://mlsanity.com/paper/2001.02772/) (2020)
- [RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing](https://mlsanity.com/paper/1912.12953/) (2019)
- [Understanding Training Efficiency of Deep Learning Recommendation Models at Scale](https://mlsanity.com/paper/2011.05497/) (2020)
- [Learnable Embedding Sizes for Recommender Systems](https://mlsanity.com/paper/2101.07577/) (2021)
- [Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems](https://mlsanity.com/paper/1909.11810/) (2019)
- [Learning to Embed Categorical Features without Embedding Tables for Recommendation](https://mlsanity.com/paper/2010.10784/) (2020)
- [Optimizing Deep Learning Recommender Systems' Training On CPU Cluster Architectures](https://mlsanity.com/paper/2005.04680/) (2020)
- [Getting deep recommenders fit: Bloom embeddings for sparse binary input/output networks](https://mlsanity.com/paper/1706.03993/) (2017)
- [Learning Compressed Embeddings for On-Device Inference](https://mlsanity.com/paper/2203.10135/) (2022)
- [Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems](https://mlsanity.com/paper/2103.06124/) (2021)
- [Training with Multi-Layer Embeddings for Model Reduction](https://mlsanity.com/paper/2006.05623/) (2020)
- [Efficient Mixed Dimension Embeddings for Matrix Factorization](https://mlsanity.com/paper/2205.11248/) (2022)

## Built on by (most cited first, 3 of 3)

- [Two-dimensional Sparse Parallelism for Large Scale Deep Learning Recommendation Model Training](https://mlsanity.com/paper/2508.03854/) (2025)
- [Pushing the Performance Envelope of DNN-based Recommendation Systems Inference on GPUs](https://mlsanity.com/paper/2410.22249/) (2024)
- [KVCrush: Key value cache size-reduction using similarity in head-behaviour](https://mlsanity.com/paper/2503.00022/) (2025)

## Abstract (arXiv)

Deep learning-based recommendation systems (e.g., DLRMs) are widely used AI models to provide high-quality personalized recommendations. Training data used for modern recommendation systems commonly includes categorical features taking on tens-of-millions of possible distinct values. These categorical tokens are typically assigned learned vector representations, that are stored in large embedding tables, on the order of 100s of GB. Storing and accessing these tables represent a substantial burden in commercial deployments. Our work proposes MEM-REC, a novel alternative representation approach for embedding tables. MEM-REC leverages bloom filters and hashing methods to encode categorical features using two cache-friendly embedding tables. The first table (token embedding) contains raw embeddings (i.e. learned vector representation), and the second table (weight embedding), which is much smaller, contains weights to scale these raw embeddings to provide better discriminative capability to each data point. We provide a detailed architecture, design and analysis of MEM-REC addressing trade-offs in accuracy and computation requirements, in comparison with state-of-the-art techniques. We show that MEM-REC can not only maintain the recommendation quality and significantly reduce the memory footprint for commercial scale recommendation models but can also improve the embedding latency. In particular, based on our results, MEM-REC compresses the MLPerf CriteoTB benchmark DLRM model size by 2900x and performs up to 3.4x faster embeddings while achieving the same AUC as that of the full uncompressed model.