activity
20202022
most citedBlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learning

10 citations · 26 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CR20223 cited

Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy

David Byrd, Vaikkunth Mugunthan, Antigoni Polychroniadou +1

Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted…

cs.LG20216 cited

Multi-VFL: A Vertical Federated Learning System for Multiple Data and Label Owners

Vaikkunth Mugunthan, Pawan Goyal, Lalana Kagal

Vertical Federated Learning (VFL) refers to the collaborative training of a model on a dataset where the features of the dataset are split among multiple data owners, while label i…

cs.LG20217 cited

Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets

Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal +1

Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive tr…

cs.LG2021

Prior-Independent Auctions for the Demand Side of Federated Learning

Andreas Haupt, Vaikkunth Mugunthan

Federated learning (FL) is a paradigm that allows distributed clients to learn a shared machine learning model without sharing their sensitive training data. While largely decentra…

cs.LG2020

DPD-InfoGAN: Differentially Private Distributed InfoGAN

Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal +1

Generative Adversarial Networks (GANs) are deep learning architectures capable of generating synthetic datasets. Despite producing high-quality synthetic images, the default GAN ha…

cs.LG202010 cited

BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learning

Vaikkunth Mugunthan, Ravi Rahman, Lalana Kagal

Federated learning enables the development of a machine learning model among collaborating agents without requiring them to share their underlying data. However, malicious agents w…