Fedltn: Federated learning for sparse and personalized lottery ticket networks
Federated learning (FL) enables clients to collaboratively train a model, while keeping their
local training data decentralized. However, high communication costs, data heterogeneity …
local training data decentralized. However, high communication costs, data heterogeneity …
Research on Aggregation of Federated Model for Software Defect Prediction Based on Dynamic Selection
H Song, Y Li, W Zhang, Y Liu - 2023 10th International …, 2023 - ieeexplore.ieee.org
With the continuous expansion of the application scope of computer software, the standards
of software quality of various organizations are becoming more and more strict. As a testing …
of software quality of various organizations are becoming more and more strict. As a testing …
Enabling the Informed Patient Paradigm with Secure and Personalized Medical Question Answering
J Oduro-Afriyie, HM Jamil - Proceedings of the 14th ACM International …, 2023 - dl.acm.org
Quality patient care is a complex and multifaceted problem requiring the integration of data
from multiple sources. We propose Medicient, a knowledge-graph-based question …
from multiple sources. We propose Medicient, a knowledge-graph-based question …
A Practical Approach to Federated Learning
V Mugunthan - 2022 - dspace.mit.edu
Machine learning models benefit from large and diverse training datasets. However, it is
difficult for an individual organization to collect sufficiently diverse data. Additionally, the …
difficult for an individual organization to collect sufficiently diverse data. Additionally, the …
Safe and Robust Transfer Learning
J Wang, Y Chen - Introduction to Transfer Learning: Algorithms and …, 2022 - Springer
In this chapter, we discuss the safety and robustness of transfer learning. By safety, we refer
to its defense and solutions against attack and data privacy misuse. By robustness, we mean …
to its defense and solutions against attack and data privacy misuse. By robustness, we mean …
Efficient Personalized Federated Learning on Selective Model Training
Personalized Federated Learning (FL) handles the data heterogeneous problem by tailoring
local models for each distributed data owner. Previous studies first train a highly-adaptable …
local models for each distributed data owner. Previous studies first train a highly-adaptable …
Federated Learning for Personalized Healthcare
J Wang, Y Chen - Introduction to Transfer Learning: Algorithms and …, 2022 - Springer
Federated learning aims at building machine learning models without compromising data
privacy from the clients. Since different clients naturally have different data distributions (ie …
privacy from the clients. Since different clients naturally have different data distributions (ie …
Federated Lottery: Private and Communication-Efficient Learning of Personalized Networks
E Lin - 2022 - dash.harvard.edu
A promising approach to address privacy concerns, Federated learning (FL) enables
distributed training of machine learning (ML) models where user data remains on edge …
distributed training of machine learning (ML) models where user data remains on edge …