DeepAI AI Chat
Log In Sign Up

Improving Accuracy of Federated Learning in Non-IID Settings

by   Mustafa Safa Ozdayi, et al.
The University of Texas at Dallas

Federated Learning (FL) is a decentralized machine learning protocol that allows a set of participating agents to collaboratively train a model without sharing their data. This makes FL particularly suitable for settings where data privacy is desired. However, it has been observed that the performance of FL is closely tied with the local data distributions of agents. Particularly, in settings where local data distributions vastly differ among agents, FL performs rather poorly with respect to the centralized training. To address this problem, we hypothesize the reasons behind the performance degradation, and develop some techniques to address these reasons accordingly. In this work, we identify four simple techniques that can improve the performance of trained models without incurring any additional communication overhead to FL, but rather, some light computation overhead either on the client, or the server-side. In our experimental analysis, combination of our techniques improved the validation accuracy of a model trained via FL by more than 12 with respect to our baseline. This is about 5 model trained on centralized data.


The Impact of Data Distribution on Fairness and Robustness in Federated Learning

Federated Learning (FL) is a distributed machine learning protocol that ...

Mixed Federated Learning: Joint Decentralized and Centralized Learning

Federated learning (FL) enables learning from decentralized privacy-sens...

BlockFLA: Accountable Federated Learning via Hybrid Blockchain Architecture

Federated Learning (FL) is a distributed, and decentralized machine lear...

Federated Survival Analysis with Discrete-Time Cox Models

Building machine learning models from decentralized datasets located in ...

Guiding The Last Layer in Federated Learning with Pre-Trained Models

Federated Learning (FL) is an emerging paradigm that allows a model to b...

CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning

Since random initial models in Federated Learning (FL) can easily result...

Towards More Efficient Federated Learning with Better Optimization Objects

Federated Learning (FL) is a privacy-protected machine learning paradigm...