Mrinmay Sen
YOU?
Author Swipe
View article: FedDAF: Federated Domain Adaptation Using Model Functional Distance
FedDAF: Federated Domain Adaptation Using Model Functional Distance Open
Federated Domain Adaptation (FDA) is a federated learning (FL) approach that improves model performance at the target client by collaborating with source clients while preserving data privacy. FDA faces two primary challenges: domain shift…
View article: pFedSOP : Accelerating Training Of Personalized Federated Learning Using Second-Order Optimization
pFedSOP : Accelerating Training Of Personalized Federated Learning Using Second-Order Optimization Open
Personalized Federated Learning (PFL) enables clients to collaboratively train personalized models tailored to their individual objectives, addressing the challenge of model generalization in traditional Federated Learning (FL) due to high…
View article: Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Review
Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Review Open
Federated Learning (FL) is a learning mechanism that falls under the distributed training umbrella, which collaboratively trains a shared global model without disclosing the raw data from different clients. This paper presents an extensive…
View article: Accelerated Training of Federated Learning via Second-Order Methods
Accelerated Training of Federated Learning via Second-Order Methods Open
This paper explores second-order optimization methods in Federated Learning (FL), addressing the critical challenges of slow convergence and the excessive communication rounds required to achieve optimal performance from the global model. …
View article: FAGH: Accelerating Federated Learning with Approximated Global Hessian
FAGH: Accelerating Federated Learning with Approximated Global Hessian Open
In federated learning (FL), the significant communication overhead due to the slow convergence speed of training the global model poses a great challenge. Specifically, a large number of communication rounds are required to achieve the con…
View article: SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix
SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix Open
This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update …