Smart Sampling: Helping from Friendly Neighbors for Decentralized Federated Learning

2024-07-05 · Lin Wang, Yang Chen, Yongxin Guo, Xiaoying Tang

Federated Learning (FL) is gaining widespread interest for its ability to share knowledge while preserving privacy and reducing communication costs. Unlike Centralized FL, Decentralized FL (DFL) employs a network architecture that eliminates the need for a central server, allowing direct communication among clients and leading to significant communication resource savings. However, due to data heterogeneity, not all neighboring nodes contribute to enhancing the local client's model performance. In this work, we introduce \textbf{\emph{AFIND+}}, a simple yet efficient algorithm for sampling and aggregating neighbors in DFL, with the aim of leveraging collaboration to improve clients' model performance. AFIND+ identifies helpful neighbors, adaptively adjusts the number of selected neighbors, and strategically aggregates the sampled neighbors' models based on their contributions. Numerical results on real-world datasets with diverse data partitions demonstrate that AFIND+ outperforms other sampling algorithms in DFL and is compatible with most existing DFL optimization algorithms.

📄 PDF Abstract BibTeX arXiv:2407.04460

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

RelaySum for Decentralized Deep Learning on Heterogeneous Data

2021-10-08 · NeurIPS 2021 12 · Thijs Vogels, Lie He, Anastasia Koloskova, Tao Lin 외

In decentralized machine learning, workers compute model updates on their local data. Because the workers only communicate with few neighbors without central coordination, these updates propagate progressively over the n…

Deep Learning

Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning

2019-01-27 · NeurIPS 2019 12 · Chao Qu, Shie Mannor, Huan Xu, Yuan Qi 외

We consider the networked multi-agent reinforcement learning (MARL) problem in a fully decentralized setting, where agents learn to coordinate to achieve the joint success. This problem is widely encountered in many area…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Impermanent Loss Conditions: An Analysis of Decentralized Exchange Platforms

2024-01-15 · Matthias Hafner, Helmut Dietl

Decentralized exchanges are widely used platforms for trading crypto assets. The most common types work with automated market makers (AMM), allowing traders to exchange assets without needing to find matching counterpart…

Bayesian Algorithms for Decentralized Stochastic Bandits

2020-10-20 · Anusha Lalitha, Andrea Goldsmith

We study a decentralized cooperative multi-agent multi-armed bandit problem with $K$ arms and $N$ agents connected over a network. In our model, each arm's reward distribution is same for all agents, and rewards are draw…

Thompson Sampling

Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication

2021-10-14 · Justin Lidard, Udari Madhushani, Naomi Ehrich Leonard

A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to perf…

Multi-agent Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1