mlsanityData to 7 Oct 2026

Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs

arXiv 1901.08460 ↗First posted 24 Jan 2019cs.LG cs.AI cs.DCcited by 34

Not on the map. Why?

Abstract (arXiv)

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models that leverage a collaboration graph describing the relationships between user personal tasks, which we learn jointly with the models. Our fully decentralized optimization procedure alternates between training nonlinear models given the graph in a greedy boosting manner, and updating the collaboration graph (with controlled sparsity) given the models. Throughout the process, users exchange messages only with a small number of peers (their direct neighbors when updating the models, and a few random users when updating the graph), ensuring that the procedure naturally scales with the number of users. Overall, our approach is communication-efficient and avoids exchanging personal data. We provide an extensive analysis of the convergence rate, memory and communication complexity of our approach, and demonstrate its benefits compared to competing techniques on synthetic and real datasets.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 7; 2024: 9; 2025: 5; 2026: 4.

34 papers.

Sort:

By area:

  1. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  2. 2021Personalized Federated Learning through Local Memorizationcited by 57
  3. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  4. 2022Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Datacited by 31
  5. 2023Personalized Decentralized Federated Learning with Knowledge Distillationcited by 21
  6. 2023FedBone: Towards Large-Scale Federated Multi-Task Learningcited by 14
  7. 2024Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Datacited by 14
  8. 2021D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learningcited by 12
  9. 2022Vertical Federated Principal Component Analysis and Its Kernel Extension on Feature-wise Distributed Datacited by 9
  10. 2022FedDAR: Federated Domain-Aware Representation Learningcited by 8
  11. 2024Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clientscited by 7
  12. 2023Distributed Learning over Networks with Graph-Attention-Based Personalizationcited by 6
22 more
  1. 2024Worldwide Federated Training of Language Modelscited by 5
  2. 2024CoBo: Collaborative Learning via Bilevel Optimizationcited by 5
  3. 2022Clustered Federated Learning based on Nonconvex Pairwise Fusioncited by 4
  4. 2023Efficient Node Selection in Private Personalized Decentralized Learningcited by 4
  5. 2023Topology-Based Reconstruction Prevention for Decentralised Learningcited by 4
  6. 2024Low-Cost Privacy-Preserving Decentralized Learningcited by 4
  7. 2025Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environmentcited by 3
  8. 2022A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacycited by 2
  9. 2024Leveraging Federated Learning and Edge Computing for Recommendation Systems within Cloud Computing Networkscited by 2
  10. 2023Structured Cooperative Learning with Graphical Model Priorscited by 1
  11. 2024ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learningcited by 1
  12. 2025Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneitycited by 1
  13. 2022Federated Latent Class Regression for Hierarchical Datacited by 0
  14. 2024MAPL: Model Agnostic Peer-to-peer Learningcited by 0
  15. 2024P4: Towards private, personalized, and Peer-to-Peer learningcited by 0
  16. 2025Controlled privacy leakage propagation throughout overlapping grouped learningcited by 0
  17. 2025SPIRE: Conditional Personalization for Federated Diffusion Generative Modelscited by 0
  18. 2025Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learningcited by 0
  19. 2026Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approachcited by 0
  20. 2026Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddingscited by 0
  21. 2026On Gossip Algorithms for Machine Learning with Pairwise Objectivescited by 0
  22. 2026Decentralized Multitask Learning over Learned Task Graphscited by 0