mlsanityData to 14 Oct 2026

The Architectural Implications of Facebook's DNN-based Personalized Recommendation

arXiv 1906.03109 ↗First posted 6 Jun 2019cs.DC cs.LGcited by 83

Not on the map. Why?

Abstract (arXiv)

The widespread application of deep learning has changed the landscape of computation in the data center. In particular, personalized recommendation for content ranking is now largely accomplished leveraging deep neural networks. However, despite the importance of these models and the amount of compute cycles they consume, relatively little research attention has been devoted to systems for recommendation. To facilitate research and to advance the understanding of these workloads, this paper presents a set of real-world, production-scale DNNs for personalized recommendation coupled with relevant performance metrics for evaluation. In addition to releasing a set of open-source workloads, we conduct in-depth analysis that underpins future system design and optimization for at-scale recommendation: Inference latency varies by 60% across three Intel server generations, batching and co-location of inferences can drastically improve latency-bounded throughput, and the diverse composition of recommendation models leads to different optimization strategies.

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 21; 2022: 21; 2023: 17; 2024: 13; 2025: 6; 2026: 5.

83 papers.

Sort:

By area:

  1. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  2. 2022Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Trainingcited by 79
  3. 2021Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Modelscited by 78
  4. 2021TT-Rec: Tensor Train Compression for Deep Learning Recommendation Modelscited by 58
  5. 2021RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inferencecited by 35
  6. 2021Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Trainingcited by 28
  7. 2022RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendationcited by 28
  8. 2021Accelerating Recommendation System Training by Leveraging Popular Choicescited by 22
  9. 2021CoSA: Scheduling by Constrained Optimization for Spatial Acceleratorscited by 22
  10. 2021Post-Training Sparsity-Aware Quantizationcited by 17
  11. 2022Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneitycited by 17
  12. 2022AutoShard: Automated Embedding Table Sharding for Recommender Systemscited by 17
38 more
  1. 2022MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platformscited by 16
  2. 2021HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environmentscited by 15
  3. 2022DreamShard: Generalizable Embedding Table Placement for Recommender Systemscited by 14
  4. 2023MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systemscited by 14
  5. 2022Learning Compressed Embeddings for On-Device Inferencecited by 13
  6. 2022Heterogeneous Acceleration Pipeline for Recommendation System Trainingcited by 13
  7. 2022Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwardscited by 11
  8. 2022BagPipe: Accelerating Deep Recommendation Model Trainingcited by 10
  9. 2021Looper: An end-to-end ML platform for product decisionscited by 9
  10. 2023MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendationcited by 9
  11. 2021RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performancecited by 8
  12. 2022HammingMesh: A Network Topology for Large-Scale Deep Learningcited by 8
  13. 2024Beyond Efficiency: Scaling AI Sustainablycited by 8
  14. 2021Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systemscited by 7
  15. 2021Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scalecited by 7
  16. 2023CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Modelscited by 7
  17. 2021Differentiable NAS Framework and Application to Ads CTR Predictioncited by 6
  18. 2021GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processingcited by 6
  19. 2022TEE-based decentralized recommender systems: The raw data sharing redemptioncited by 6
  20. 2021Supporting Massive DLRM Inference Through Software Defined Memorycited by 5
  21. 2022Learning to Collide: Recommendation System Model Compression with Learned Hash Functionscited by 5
  22. 2022Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloudcited by 5
  23. 2022Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarkscited by 5
  24. 2023GPU-based Private Information Retrieval for On-Device Machine Learning Inferencecited by 5
  25. 2023Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Modelscited by 5
  26. 2023MOSEL: Inference Serving Using Dynamic Modality Selectioncited by 5
  27. 2021Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000× Compression and 3.1× Faster Inferencecited by 4
  28. 2023FlexShard: Flexible Sharding for Industry-Scale Sequence Recommendation Modelscited by 4
  29. 2024Accelerating Distributed Deep Learning using Lossless Homomorphic Compressioncited by 4
  30. 2024UpDLRM: Accelerating Personalized Recommendation using Real-World PIM Architecturecited by 4
  31. 2021Alternate Model Growth and Pruning for Efficient Training of Recommendation Systemscited by 3
  32. 2022KAIROS: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resourcescited by 3
  33. 2023AttMEMO : Accelerating Transformers with Memoization on Big Memory Systemscited by 3
  34. 2023Mem-Rec: Memory Efficient Recommendation System using Alternative Representationcited by 3
  35. 2023InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Modelscited by 3
  36. 2023Ad-Rec: Advanced Feature Interactions to Address Covariate-Shifts in Recommendation Networkscited by 3
  37. 2023ACCL+: an FPGA-Based Collective Engine for Distributed Applicationscited by 3
  38. 2021Synthetic Data and Simulators for Recommendation Systems: Current State and Future Directionscited by 2

50 most cited of 83 All 83 (JSON)