Source Themes

Is your data relevant?: Dynamic selection of data in Federated Learning.

Using Reinforcement Learning based techniques to enable clients in Federated Learning derive updates only from relevant data.

Lokesh Nagalapatti, Ruhi Sharma Mittal, Ramasuri Narayanam

Federated machine learning based on partially secured spatio-temporal data

Federated Learning for spatio-temporal datasets.

Lokesh Nagalapatti, Ramasuri Narayanam, Ruhi Sharma Mittal, Sambaran Bandyopadhyay

Last updated on Aug 26, 2023

Training sample set generation from imbalanced data in view of user goals

Training dataset generation curtailed to user metrics.

Lokesh Nagalapatti, Ruhi Sharma Mittal, Hima Patel, Nitin Gupta

Last updated on Aug 26, 2023

Federated Learning Data Source selection

Selecting the appropriate task specific data sources in Federated Learning.

Lokesh Nagalapatti, Ruhi Sharma Mittal, Ramasuri Narayanam, Sameep Mehta

Last updated on Aug 26, 2023

Automatically detecting outliers in federated data

Detecting outlier samples in Federated Learning.

Lokesh Nagalapatti, Ramasuri Narayanam, Ruhi Sharma Mittal, Sambaran Bandyopadhyay

Last updated on Aug 26, 2023

Game of Gradients - Mitigating irrelevant clients in Federated Learning

Using Cooperative Game theory approaches to mitigate the impace of noisy clients in Federated Learning.

Lokesh Nagalapatti, Ramasuri Narayanam

Ranking Data Slices for ML Model Validation: A Shapley Value Approach

Shapley values based approach to detect slices of data that needs to be analyzed to debug the performance of a black-box ML model.

Eitan Farchi, Ramasuri Narayanam, Lokesh Nagalapatti

Outlier Resistant Unsupervised Deep Architectures for Attributed Network Embedding

Auto encoder inspired deep architectures for finding outlier robust network embedding for nodes in an attributed networks through adversarial training.

Sambaran Bandyopadhyay, Lokesh Nagalapatti, Saley Vishal Vivek (*), M N Murty

Outlier Aware Network Embedding for Attributed Networks

Finding outlier robust network embedding for nodes in an attributed network. We define outlierness for each node and learn them using closed form update rules.

Sambaran Bandyopadhyay, Lokesh Nagalapatti, M N Murty