Sparse random networks for communication-efficient federated learning
B Isik, F Pase, D Gunduz, T Weissman… - ar** Study
Federated learning has emerged as a promising approach for collaborative model training
across distributed devices. Federated learning faces challenges such as Non-Independent …
across distributed devices. Federated learning faces challenges such as Non-Independent …
Like attracts like: Personalized federated learning in decentralized edge computing
The emerging Personalized Federated Learning (PFL) methods aim to produce
personalized models for different users, so as to keep track of their individualized …
personalized models for different users, so as to keep track of their individualized …
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
In federated learning (FL), accommodating clients' varied computational capacities poses a
challenge, often limiting the participation of those with constrained resources in global …
challenge, often limiting the participation of those with constrained resources in global …
Synergizing Foundation Models and Federated Learning: A Survey
The recent development of Foundation Models (FMs), represented by large language
models, vision transformers, and multimodal models, has been making a significant impact …
models, vision transformers, and multimodal models, has been making a significant impact …
Efficient federated learning with enhanced privacy via lottery ticket pruning in edge computing
Federated learning (FL) can train collaboratively with several mobile terminals (MTs), which
faces critical challenges in communication, resource, and privacy. Existing privacy …
faces critical challenges in communication, resource, and privacy. Existing privacy …
Efficient Federated Learning With Channel Status Awareness and Devices' Personal Touch
Federated learning (FL) is a widely used distributed learning framework. However,
constrained wireless environment and intrinsically heterogeneous data across devices can …
constrained wireless environment and intrinsically heterogeneous data across devices can …
Communication and energy efficient slimmable federated learning via superposition coding and successive decoding
Mobile devices are indispensable sources of big data. Federated learning (FL) has a great
potential in exploiting these private data by exchanging locally trained models instead of …
potential in exploiting these private data by exchanging locally trained models instead of …
Statistical Methods for Efficient and Trustworthy Machine Learning
B Isik - 2024 - search.proquest.com
STATISTICAL METHODS FOR EFFICIENT AND TRUSTWORTHY MACHINE LEARNING A
DISSERTATION SUBMITTED TO THE DEPARTMENT OF ELECTRICAL ENGI Page 1 …
DISSERTATION SUBMITTED TO THE DEPARTMENT OF ELECTRICAL ENGI Page 1 …