mlsanityData to 7 Oct 2026

Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems

arXiv 1909.11810 ↗First posted 25 Sep 2019cs.LG stat.MLcited by 41

Not on the map. Why?

Abstract (arXiv)

Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive -- potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized memory consumption, we explore mixed dimension embeddings, an embedding layer architecture in which a particular embedding vector's dimension scales with its query frequency. Through theoretical analysis and systematic experiments, we demonstrate that using mixed dimensions can drastically reduce the memory usage, while maintaining and even improving the ML performance. Empirically, we show that the proposed mixed dimension layers improve accuracy by 0.1% using half as many parameters or maintain it using 16X fewer parameters for click-through rate prediction task on the Criteo Kaggle dataset.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 10; 2024: 5; 2025: 3; 2026: 3.

41 papers.

Sort:

By area:

  1. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 89
  2. 2026Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Modelscited by 78
  3. 2021Learnable Embedding Sizes for Recommender Systemscited by 42
  4. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  5. 2021AutoLoss: Automated Loss Function Search in Recommendationscited by 31
  6. 2022RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendationcited by 28
  7. 2021Accelerating Recommendation System Training by Leveraging Popular Choicescited by 22
  8. 2022Learning Compressed Embeddings for On-Device Inferencecited by 13
  9. 2022Heterogeneous Acceleration Pipeline for Recommendation System Trainingcited by 13
  10. 2021Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layercited by 12
  11. 2021Binary Code based Hash Embedding for Web-scale Applicationscited by 11
  12. 2023MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendationcited by 9
29 more
  1. 2021RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performancecited by 8
  2. 2023Clustered Embedding Learning for Recommender Systemscited by 8
  3. 2021Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systemscited by 7
  4. 2023Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender Systemcited by 7
  5. 2023CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Modelscited by 7
  6. 2023A Versatile Graph Learning Approach through LLM-based Agentcited by 6
  7. 2022Learning to Collide: Recommendation System Model Compression with Learned Hash Functionscited by 5
  8. 2021Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000× Compression and 3.1× Faster Inferencecited by 4
  9. 2022CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPUcited by 4
  10. 2022A Frequency-aware Software Cache for Large Recommendation System Embeddingscited by 4
  11. 2023FlexShard: Flexible Sharding for Industry-Scale Sequence Recommendation Modelscited by 4
  12. 2023Mem-Rec: Memory Efficient Recommendation System using Alternative Representationcited by 3
  13. 2025CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systemscited by 3
  14. 2022The trade-offs of model size in large recommendation models : A 10000 × compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)cited by 2
  15. 2023Proxy-based Item Representation for Attribute and Context-aware Recommendationcited by 2
  16. 2024DQRM: Deep Quantized Recommendation Modelscited by 2
  17. 2021FINT: Field-aware INTeraction Neural Network For CTR Predictioncited by 1
  18. 2022Efficient Mixed Dimension Embeddings for Matrix Factorizationcited by 1
  19. 2024Fine-Grained Embedding Dimension Optimization During Training for Recommender Systemscited by 1
  20. 2024Disaggregating Embedding Recommendation Systems with FlexEMRcited by 1
  21. 2026Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scalingcited by 1
  22. 2021ECRM: Efficient Fault Tolerance for Recommendation Model Training via Erasure Codingcited by 0
  23. 2021Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layerscited by 0
  24. 2023Enhancing Cross-Category Learning in Recommendation Systems with Multi-Layer Embedding Trainingcited by 0
  25. 2024ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation Systemcited by 0
  26. 2024Unified Low-rank Compression Framework for Click-through Rate Predictioncited by 0
  27. 2025Ember: A Compiler for Efficient Embedding Operations on Decoupled Access-Execute Architecturescited by 0
  28. 2025DimGrow: Memory-Efficient Field-level Embedding Dimension Searchcited by 0
  29. 2026Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenderscited by 0