paper-with-me

Papers

CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous models

2024-02-25 · Abhishek Singh, Gauri Gupta, Ritvik Kapila, Yichuan Shi, Alex Dang, Sheshank Shankar, Mohammed Ehab, Ramesh Raskar

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/

📄 PDF Abstract BibTeX arXiv:2402.15968

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Federated style aware transformer aggregation of representations

2025-11-24 · Mincheol Jeon, Euinam Huh arxiv

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 Learning

CoDreamer: Communication-Based Decentralised World Models

2024-06-19 · Edan Toledo, Amanda Prorok

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

2023-05-19 · Rui Song, Lingjuan Lyu, Wei Jiang, Andreas Festag 외

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 Learning

Curriculum Guided Personalized Subgraph Federated Learning

2025-08-30 · Minku Kang, Hogun Park arxiv

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 Learning

Secure Forward Aggregation for Vertical Federated Neural Networks

2022-06-28 · Shuowei Cai, Di Chai, Liu Yang, Junxue Zhang 외

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