PFSL: Personalized Fair Split Learning with Data Label Privacy for thin clients

by   Manas Wadhwa, et al.
Indian Institute of Technology Bhilai

The traditional framework of federated learning (FL) requires each client to re-train their models in every iteration, making it infeasible for resource-constrained mobile devices to train deep-learning (DL) models. Split learning (SL) provides an alternative by using a centralized server to offload the computation of activations and gradients for a subset of the model but suffers from problems of slow convergence and lower accuracy. In this paper, we implement PFSL, a new framework of distributed split learning where a large number of thin clients perform transfer learning in parallel, starting with a pre-trained DL model without sharing their data or labels with a central server. We implement a lightweight step of personalization of client models to provide high performance for their respective data distributions. Furthermore, we evaluate performance fairness amongst clients under a work fairness constraint for various scenarios of non-i.i.d. data distributions and unequal sample sizes. Our accuracy far exceeds that of current SL algorithms and is very close to that of centralized learning on several real-life benchmarks. It has a very low computation cost compared to FL variants and promises to deliver the full benefits of DL to extremely thin, resource-constrained clients.


page 1

page 2

page 6


Communication and Storage Efficient Federated Split Learning

Federated learning (FL) is a popular distributed machine learning (ML) p...

New Metrics to Evaluate the Performance and Fairness of Personalized Federated Learning

In Federated Learning (FL), the clients learn a single global model (Fed...

ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries

In this work we introduce ExpertMatcher, a method for automating deep le...

A Systematic Literature Review on Client Selection in Federated Learning

With the arising concerns of privacy within machine learning, federated ...

SplitEasy: A Practical Approach for Training ML models on Mobile Devices in a split second

Modern mobile devices, although resourceful, cannot train state-of-the-a...

Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits

The ongoing 'digital transformation' fundamentally changes audit evidenc...

Please sign up or login with your details

Forgot password? Click here to reset