CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous models
Federated Learning (FL) enables collaborative optimization of machine learning models across decentralized data by aggregating model parameters. Our approach extends this concept by aggregating "knowledge" derived from models, instead of model parameters. We present a novel framework called CoDream, where clients collaboratively optimize randomly initialized data using federated optimization in the input data space, similar to how randomly initialized model parameters are optimized in FL. Our key insight is that jointly optimizing this data can effectively capture the properties of the global data distribution. Sharing knowledge in data space offers numerous benefits: (1) model-agnostic collaborative learning, i.e., different clients can have different model architectures; (2) communication that is independent of the model size, eliminating scalability concerns with model parameters; (3) compatibility with secure aggregation, thus preserving the privacy benefits of federated learning; (4) allowing of adaptive optimization of knowledge shared for personalized learning. We empirically validate CoDream on standard FL tasks, demonstrating competitive performance despite not sharing model parameters. Our code: https://mitmedialab.github.io/codream.github.io/
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Federated style aware transformer aggregation of representations
Personalized Federated Learning (PFL) faces persistent challenges, including domain heterogeneity from diverse client data, data imbalance due to skewed participation, and strict communication constraints. Traditional fe…
Personalized Federated LearningCoDreamer: Communication-Based Decentralised World Models
Sample efficiency is a critical challenge in reinforcement learning. Model-based RL has emerged as a solution, but its application has largely been confined to single-agent scenarios. In this work, we introduce CoDreamer…
V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection
Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services. Federated learning (FL) overcomes privacy constraints by training ML models in distributed systems,…
Autonomous DrivingClusteringFederated LearningCurriculum Guided Personalized Subgraph Federated Learning
Subgraph Federated Learning (FL) aims to train Graph Neural Networks (GNNs) across distributed private subgraphs, but it suffers from severe data heterogeneity. To mitigate data heterogeneity, weighted model aggregation …
Federated LearningSecure Forward Aggregation for Vertical Federated Neural Networks
Vertical federated learning (VFL) is attracting much attention because it enables cross-silo data cooperation in a privacy-preserving manner. While most research works in VFL focus on linear and tree models, deep models …
Federated LearningPrivacy PreservingVertical Federated Learning