# Efficient Node Selection in Private Personalized Decentralized Learning

arXiv: https://arxiv.org/abs/2301.12755 · HTML: https://mlsanity.com/paper/2301.12755/

## 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 (most cited first, 21 of 21)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [Three Approaches for Personalization with Applications to Federated Learning](https://mlsanity.com/paper/2002.10619/) (2020)
- [Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits](https://mlsanity.com/paper/1807.07623/) (2018)
- [Decentralized Collaborative Learning of Personalized Models over Networks](https://mlsanity.com/paper/1610.05202/) (2016)
- [LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning](https://mlsanity.com/paper/2109.14236/) (2021)
- [Multi-Armed Bandit Based Client Scheduling for Federated Learning](https://mlsanity.com/paper/2007.02315/) (2020)
- [Stochastic Client Selection for Federated Learning with Volatile Clients](https://mlsanity.com/paper/2011.08756/) (2020)
- [Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs](https://mlsanity.com/paper/1901.08460/) (2019)
- [Gossip training for deep learning](https://mlsanity.com/paper/1611.09726/) (2016)
- [Multi-Armed Bandits with Correlated Arms](https://mlsanity.com/paper/1911.03959/) (2019)
- [Data Leakage in Federated Averaging](https://mlsanity.com/paper/2206.12395/) (2022)
- [Decentralized federated learning of deep neural networks on non-iid data](https://mlsanity.com/paper/2107.08517/) (2021)
- [Multi-Armed Bandits with Dependent Arms](https://mlsanity.com/paper/2010.09478/) (2020)
- [Find Your Friends: Personalized Federated Learning with the Right Collaborators](https://mlsanity.com/paper/2210.06597/) (2022)
- [Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits](https://mlsanity.com/paper/2012.03270/) (2020)
- [Decentralized adaptive clustering of deep nets is beneficial for client collaboration](https://mlsanity.com/paper/2206.08839/) (2022)
- [Privacy in Distributed Computations based on Real Number Secret Sharing](https://mlsanity.com/paper/2107.00911/) (2021)

## Built on by (most cited first, 4 of 4)

- [On the effects of similarity metrics in decentralized deep learning under distributional shift](https://mlsanity.com/paper/2409.10720/) (2024)
- [Client-Conditional Federated Learning via Local Training Data Statistics](https://mlsanity.com/paper/2603.11307/) (2026)
- [When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning](https://mlsanity.com/paper/2609.08476/) (2026)
- [Adaptive Bayesian Partner Selection for Federated Clinical Centers](https://mlsanity.com/paper/2609.16446/) (2026)

## 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.