6 papers
Personalized Projected Ascent for Federated Stackelberg Optimization
M Yashwanth, Sharannya Ghosh, Saikiran Bulusu +1
Federated minimax problems, such as distributionally robust optimization and adversarial training, include an inner maximization variable built from each client's local data. These…
Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation
M Yashwanth, Arunabh Singh, Ashok Nayak +2
Federated Learning (FL) algorithms implicitly assume that clients passively comply with server-side orchestration by sharing local model updates upon server request. However, this…
Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning
M Yashwanth, Gaurav Kumar Nayak, Harsh Rangwani +3
Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the…
FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation
M Yashwanth, Sampath Koti, Arunabh Singh +2
We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrain…
Mitigating Participation Imbalance Bias in Asynchronous Federated Learning
Xiangyu Chang, Manyi Yao, Srikanth V. Krishnamurthy +5
In Asynchronous Federated Learning (AFL), the central server immediately updates the global model with each arriving client's contribution. As a result, clients perform their local…
DAD++: Improved Data-free Test Time Adversarial Defense
Gaurav Kumar Nayak, Inder Khatri, Shubham Randive +2
With the increasing deployment of deep neural networks in safety-critical applications such as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness h…