Log In Sign Up

Federated Learning with Personalization Layers

by   Manoj Ghuhan Arivazhagan, et al.

The emerging paradigm of federated learning strives to enable collaborative training of machine learning models on the network edge without centrally aggregating raw data and hence, improving data privacy. This sharply deviates from traditional machine learning and necessitates the design of algorithms robust to various sources of heterogeneity. Specifically, statistical heterogeneity of data across user devices can severely degrade the performance of standard federated averaging for traditional machine learning applications like personalization with deep learning. This paper pro-posesFedPer, a base + personalization layer approach for federated training of deep feedforward neural networks, which can combat the ill-effects of statistical heterogeneity. We demonstrate effectiveness ofFedPerfor non-identical data partitions ofCIFARdatasetsand on a personalized image aesthetics dataset from Flickr.


page 1

page 2

page 3

page 4


Modular Federated Learning

Federated learning is an approach to train machine learning models on th...

Siloed Federated Learning for Multi-Centric Histopathology Datasets

While federated learning is a promising approach for training deep learn...

Fast Deep Autoencoder for Federated learning

This paper presents a novel, fast and privacy preserving implementation ...

IBM Federated Learning: an Enterprise Framework White Paper V0.1

Federated Learning (FL) is an approach to conduct machine learning witho...

Towards Privacy-Aware Causal Structure Learning in Federated Setting

Causal structure learning has been extensively studied and widely used i...

Non-IID data and Continual Learning processes in Federated Learning: A long road ahead

Federated Learning is a novel framework that allows multiple devices or ...

Weight Divergence Driven Divide-and-Conquer Approach for Optimal Federated Learning from non-IID Data

Federated Learning allows training of data stored in distributed devices...