mlsanityData to 14 Oct 2026

Efficient Node Selection in Private Personalized Decentralized Learning

arXiv 2301.12755 ↗First posted 30 Jan 2023cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data. However, this approach poses significant privacy risks, as nodes may inadvertently disclose sensitive information about their data or preferences through their collaboration choices. In this paper, we propose Private Personalized Decentralized Learning (PPDL), a novel approach that combines secure aggregation and correlated adversarial multi-armed bandit optimization to protect node privacy while facilitating efficient node selection. By leveraging dependencies between different arms, represented by potential collaborators, we demonstrate that PPDL can effectively identify suitable collaborators solely based on aggregated models. Additionally, we show that PPDL surpasses previous non-private methods in model performance on standard benchmarks under label and covariate shift scenarios.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 21 of its 34 references that are in the map. First posted on arXiv 30 Jan 2023.

Builds on

21 of 34 references.

References · 21

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  4. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  5. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  6. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
  7. 2018Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Banditscited by 124
  8. 2016Decentralized Collaborative Learning of Personalized Models over Networkscited by 76
  9. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 64
  10. 2020Multi-Armed Bandit Based Client Scheduling for Federated Learningcited by 57
  11. 2020Stochastic Client Selection for Federated Learning with Volatile Clientscited by 39
  12. 2019Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphscited by 36
9 more
  1. 2016Gossip training for deep learningcited by 35
  2. 2019Multi-Armed Bandits with Correlated Armscited by 34
  3. 2022Data Leakage in Federated Averagingcited by 26
  4. 2021Decentralized federated learning of deep neural networks on non-iid datacited by 25
  5. 2020Multi-Armed Bandits with Dependent Armscited by 12
  6. 2022Find Your Friends: Personalized Federated Learning with the Right Collaboratorscited by 10
  7. 2020Accurate and Fast Federated Learning via Combinatorial Multi-Armed Banditscited by 7
  8. 2022Decentralized adaptive clustering of deep nets is beneficial for client collaborationcited by 7
  9. 2021Privacy in Distributed Computations based on Real Number Secret Sharingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 3.

4 papers.

  1. 2024On the effects of similarity metrics in decentralized deep learning under distributional shiftcited by 1
  2. 2026Client-Conditional Federated Learning via Local Training Data Statisticscited by 0
  3. 2026When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learningcited by 0
  4. 2026Adaptive Bayesian Partner Selection for Federated Clinical Centerscited by 0