Learning recourse on the environment that generates data instances.
Using Reinforcement Learning based techniques to enable clients in Federated Learning derive updates only from relevant data.
Using Cooperative Game theory approaches to mitigate the impace of noisy clients in Federated Learning.
Shapley values based approach to detect slices of data that needs to be analyzed to debug the performance of a black-box ML model.
Auto encoder inspired deep architectures for finding outlier robust network embedding for nodes in an attributed networks through adversarial training.
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.