mlsanityData to 7 Oct 2026

Device-Cloud Collaborative Learning for Recommendation

arXiv 2104.06624 ↗First posted 14 Apr 2021cs.LG cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and to capture real-time features. While quite a lot of works have explored to facilitate on-device learning and inference, most of them focus on dealing with response delay or privacy protection. Little has been done to model the collaboration between the device and the cloud modeling and benefit both sides jointly. To bridge this gap, we are among the first attempts to study the Device-Cloud Collaborative Learning (DCCL) framework. Specifically, we propose a novel MetaPatch learning approach on the device side to efficiently achieve "thousands of people with thousands of models" given a centralized cloud model. Then, with billions of updated personalized device models, we propose a "model-over-models" distillation algorithm, namely MoMoDistill, to update the centralized cloud model. Our extensive experiments over a range of datasets with different settings demonstrate the effectiveness of such collaboration on both cloud and devices, especially its superiority to model long-tailed users.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 26 of its 52 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

26 of 52 references.

References · 26

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  5. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  6. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  7. 2018Self-Attentive Sequential Recommendationcited by 1,169
  8. 2017Neural Collaborative Filteringcited by 1,108
  9. 2016HyperNetworkscited by 1,003
  10. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  11. 2016Wide & Deep Learning for Recommender Systemscited by 745
  12. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
14 more
  1. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  2. 2016Dynamic Filter Networkscited by 318
  3. 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 174
  4. 2020Survey of Personalization Techniques for Federated Learningcited by 144
  5. 2018JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Servicescited by 79
  6. 2019Meta Matrix Factorization for Federated Rating Predictionscited by 48
  7. 2021Sparse-Interest Network for Sequential Recommendationcited by 37
  8. 2019On-Device Neural Net Inference with Mobile GPUscited by 32
  9. 2020EdgeRec: Recommender System on Edge in Mobile Taobaocited by 29
  10. 2017A Berkeley View of Systems Challenges for AIcited by 15
  11. 2014The Matthew effect in empirical datacited by 10
  12. 2020A Generic Network Compression Framework for Sequential Recommender Systemscited by 10
  13. 2020Towards Equivalent Transformation of User Preferences in Cross Domain Recommendationcited by 8
  14. 2018Variational Collaborative Learning for User Probabilistic Representationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 8; 2023: 5; 2024: 7; 2025: 8; 2026: 1.

34 papers.

Sort:

By area:

  1. 2021Reliable Adversarial Distillation with Unreliable Teacherscited by 55
  2. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  3. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  4. 2022Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learningcited by 23
  5. 2023Semi-decentralized Federated Ego Graph Learning for Recommendationcited by 22
  6. 2025Secure On-Device Video OOD Detection Without Backpropagationcited by 19
  7. 2022Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-worldcited by 16
  8. 2022FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregationcited by 16
  9. 2025Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendationcited by 15
  10. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  11. 2021Why Do We Click: Visual Impression-aware News Recommendationcited by 10
  12. 2022Intelligent Request Strategy Design in Recommender Systemcited by 10
22 more
  1. 2022Device-Cloud Collaborative Recommendation via Meta Controllercited by 10
  2. 2021Click-through Rate Prediction with Auto-Quantized Contrastive Learningcited by 7
  3. 2022On-Device Learning with Cloud-Coordinated Data Augmentation for Extreme Model Personalization in Recommender Systemscited by 6
  4. 2023DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Modelscited by 6
  5. 2024A Population-to-individual Tuning Framework for Adapting Pretrained LM to On-device User Intent Predictioncited by 6
  6. 2021MC2-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendationcited by 5
  7. 2023Edge-cloud Collaborative Learning with Federated and Centralized Featurescited by 5
  8. 2024Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaborationcited by 5
  9. 2024DIET: Customized Slimming for Incompatible Networks in Sequential Recommendationcited by 3
  10. 2025Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendationcited by 3
  11. 2024Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systemscited by 2
  12. 2025Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directionscited by 2
  13. 2022Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systemscited by 1
  14. 2023Mobile Supply: The Last Piece of Jigsaw of Recommender Systemcited by 1
  15. 2023ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptationcited by 1
  16. 2024Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendationcited by 1
  17. 2025HybridServe: Efficient Serving of Large AI Models with Confidence-Based Cascade Routingcited by 1
  18. 2025Cloud-Device Collaborative Agents for Sequential Recommendationcited by 1
  19. 2024Advancements in Recommender Systems: A Comprehensive Analysis Based on Data, Algorithms, and Evaluationcited by 0
  20. 2025Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editingcited by 0
  21. 2025CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaborationcited by 0
  22. 2026CIAR: Interval-based Collaborative Decoding for Image Generation Accelerationcited by 0