Saec: Similarity-aware Embedding Compression In Recommendation Systems

Abstract

Production recommendation systems rely on embedding methods to represent various features. An impeding challenge in practice is that the large embedding matrix incurs substantial memory footprint in serving as the number of features grows over time. We propose a similarity-aware embedding matrix compression method called Saec to address this challenge. Saec clusters similar features within a field to reduce the embedding matrix size. Saec also adopts a fast clustering optimization based on feature frequency to drastically improve clustering time. We implement and evaluate Saec on Numerous, the production distributed machine learning system in Tencent, with 10-day worth of feature data from QQ mobile browser. Testbed experiments show that Saec reduces the number of embedding vectors by two orders of magnitude, compresses the embedding size by ~27x, and delivers the same AUC and log loss performance.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywu2019saec

Related papers

• Collaborative Similarity Embedding For Recommender Systems (2019)13.93
• 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
• CAFE: Towards Compact, Adaptive, And Fast Embedding For Large-scale Recommendation Models (2023)8.09
• SEEC: Semantic Vector Federation Across Edge Computing Environments (2020)0.00
• Mem-rec: Memory Efficient Recommendation System Using Alternative Representation (2023)0.00
• Efficient Learning Of Sparse Representations From Interactions (2026)1.57
• RECE: Reduced Cross-entropy Loss For Large-catalogue Sequential Recommenders (2024)6.77