mlsanityData to 14 Oct 2026

FEL: High Capacity Learning for Recommendation and Ranking via Federated Ensemble Learning

arXiv 2206.03852 ↗First posted 7 Jun 2022cs.IR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has emerged as an effective approach to address consumer privacy needs. FL has been successfully applied to certain machine learning tasks, such as training smart keyboard models and keyword spotting. Despite FL's initial success, many important deep learning use cases, such as ranking and recommendation tasks, have been limited from on-device learning. One of the key challenges faced by practical FL adoption for DL-based ranking and recommendation is the prohibitive resource requirements that cannot be satisfied by modern mobile systems. We propose Federated Ensemble Learning (FEL) as a solution to tackle the large memory requirement of deep learning ranking and recommendation tasks. FEL enables large-scale ranking and recommendation model training on-device by simultaneously training multiple model versions on disjoint clusters of client devices. FEL integrates the trained sub-models via an over-arch layer into an ensemble model that is hosted on the server. Our experiments demonstrate that FEL leads to 0.43-2.31% model quality improvement over traditional on-device federated learning - a significant improvement for ranking and recommendation system use cases.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 40 of its 61 references that are in the map. First posted on arXiv 7 Jun 2022.

Builds on

40 of 61 references.

References · 40

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  2. 2016Wide & Deep Learning for Recommender Systemscited by 747
  3. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  4. 2020The Future of Digital Health with Federated Learningcited by 633
  5. 2017Deep Interest Network for Click-Through Rate Predictioncited by 544
  6. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  8. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  9. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  10. 2017Deep & Cross Network for Ad Click Predictionscited by 393
  11. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
  12. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
28 more
  1. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  2. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  3. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  4. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  5. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 163
  6. 2019One-Shot Federated Learningcited by 125
  7. 2020FedVision: An Online Visual Object Detection Platform Powered by Federated Learningcited by 124
  8. 2021Deep Learning with Label Differential Privacycited by 117
  9. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
  10. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 90
  11. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
  12. 2020Privacy-preserving Traffic Flow Prediction: A Federated Learning Approachcited by 83
  13. 2022Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learningcited by 81
  14. 2019Split Learning for collaborative deep learning in healthcarecited by 73
  15. 2020Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systemscited by 60
  16. 2019Practical Federated Gradient Boosting Decision Treescited by 54
  17. 2021Antipodes of Label Differential Privacy: PATE and ALIBIcited by 52
  18. 2020Understanding Training Efficiency of Deep Learning Recommendation Models at Scalecited by 43
  19. 2021AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learningcited by 39
  20. 2021RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inferencecited by 35
  21. 2020Understanding Capacity-Driven Scale-Out Neural Recommendation Inferencecited by 29
  22. 2019Federated Learning for Ranking Browser History Suggestionscited by 24
  23. 2021Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learningcited by 23
  24. 2022Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneitycited by 17
  25. 2021FedXGBoost: Privacy-Preserving XGBoost for Federated Learningcited by 9
  26. 2021Flatee: Federated Learning Across Trusted Execution Environmentscited by 5
  27. 2021FedSEAL: Semi-Supervised Federated Learning with Self-Ensemble Learning and Negative Learningcited by 4
  28. 2021Masked LARk: Masked Learning, Aggregation and Reporting worKflowcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2023GPU-based Private Information Retrieval for On-Device Machine Learning Inferencecited by 5
  2. 2022FedGPO: Heterogeneity-Aware Global Parameter Optimization for Efficient Federated Learningcited by 3
  3. 2023Evaluating Privacy Leakage in Split Learningcited by 3
  4. 2024HeteroSwitch: Characterizing and Taming System-Induced Data Heterogeneity in Federated Learningcited by 1