Mem-rec: Memory Efficient Recommendation System Using Alternative Representation

Abstract

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 t

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjha2023mem

Related papers

• CAFE: Towards Compact, Adaptive, And Fast Embedding For Large-scale Recommendation Models (2023)8.09
• Semantically Constrained Memory Allocation (SCMA) For Embedding In Efficient Recommendation Systems (2021)0.00
• Mixed-precision Embeddings For Large-scale Recommendation Models (2024)0.00
• Fine-grained Embedding Dimension Optimization During Training For Recommender Systems (2024)0.00
• Learning To Collide: Recommendation System Model Compression With Learned Hash Functions (2022)0.00
• Representation Learning For Efficient And Effective Similarity Search And Recommendation (2021)0.00
• Learning Compressed Embeddings For On-device Inference (2022)0.00
• Unified Semantic And ID Representation Learning For Deep Recommenders (2025)0.00