Agnostic Federated Learning

Agnostic federated learning aims to overcome limitations of traditional federated learning by enabling collaborative model training across diverse devices and data types without requiring uniformity in model architectures or tasks. Current research focuses on developing model-agnostic algorithms, such as adaptations of AdaBoost, and exploring techniques like model compression and self-supervised learning to enhance privacy and efficiency, particularly within resource-constrained environments. This approach is significant because it expands the applicability of federated learning beyond deep neural networks to a wider range of machine learning models and datasets, facilitating broader collaboration and data utilization while preserving privacy.

Papers

June 25, 2024

Task-Agnostic Federated Learning
Zhengtao Yao, Hong Nguyen, Ajitesh Srivastava, Jose Luis Ambite
Medical Image Datasets Data Sharing Federated Self Supervised Learning Effective Representation Consensus Learning Agnostic Federated Learning

November 29, 2023

Addressing Membership Inference Attack in Federated Learning with Model Compression
Gergely Dániel Németh, Miguel Ángel Lozano, Novi Quadrianto, Nuria Oliver
Federated Learning Membership Inference Attack Privacy Preserving Model Compression Privacy Enhancing Technology Agnostic Federated Learning

November 23, 2023

AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems
Ruixuan Liu, Ming Hu, Zeke Xia, Jun Xia, Pengyu Zhang, Yihao Huang, Yang Liu, Mingsong Chen
Heterogeneous Federated Learning Heterogeneous Device Hadamard Adapter Agnostic Federated Learning

March 8, 2023

Model-Agnostic Federated Learning
Gianluca Mittone, Walter Riviera, Iacopo Colonnelli, Robert Birke, Marco Aldinucci
Deep Neural Network Federated Learning Deep Neural Network Training Agnostic Federated Learning

February 8, 2023

Towards Model-Agnostic Federated Learning over Networks
A. Jung, S. Abdurakhmanova, O. Kuznetsova, Y. SarcheshmehPour
Network Programming Empirical Risk Minimization Heterogeneous Data Local Model Scikit Learn Agnostic Federated Learning

February 15, 2022

Architecture Agnostic Federated Learning for Neural Networks
Disha Makhija, Xing Han, Nhat Ho, Joydeep Ghosh
Neural Network Federated Prompt Cooperation Heterogeneous Federated Learning Agnostic Federated Learning