Results 11 to 20 of about 7,673 (25)

Game of Gradients: Mitigating Irrelevant Clients in Federated Learning [PDF]

arXiv, 2021
The paradigm of Federated learning (FL) deals with multiple clients participating in collaborative training of a machine learning model under the orchestration of a central server. In this setup, each client's data is private to itself and is not transferable to other clients or the server.
arxiv  

On-Demand Unlabeled Personalized Federated Learning [PDF]

arXiv, 2021
In Federated Learning (FL), multiple clients collaborate to learn a shared model through a central server while keeping data decentralized. Personalized Federated Learning (PFL) further extends FL by learning a personalized model per client. In both FL and PFL, all clients participate in the training process and their labeled data are used for training.
arxiv  

Utilizing Free Clients in Federated Learning for Focused Model Enhancement [PDF]

arXiv, 2023
Federated Learning (FL) is a distributed machine learning approach to learn models on decentralized heterogeneous data, without the need for clients to share their data. Many existing FL approaches assume that all clients have equal importance and construct a global objective based on all clients.
arxiv  

Server-side verification of client behavior in cryptographic protocols [PDF]

arXiv, 2016
Numerous exploits of client-server protocols and applications involve modifying clients to behave in ways that untampered clients would not, such as crafting malicious packets. In this paper, we demonstrate practical verification of a cryptographic protocol client's messaging behavior as being consistent with the client program it is believed to be ...
arxiv  

PerFED-GAN: Personalized Federated Learning via Generative Adversarial Networks [PDF]

arXiv, 2022
Federated learning is gaining popularity as a distributed machine learning method that can be used to deploy AI-dependent IoT applications while protecting client data privacy and security. Due to the differences of clients, a single global model may not perform well on all clients, so the personalized federated learning method, which trains a ...
arxiv  

RSCFed: Random Sampling Consensus Federated Semi-supervised Learning [PDF]

arXiv, 2022
Federated semi-supervised learning (FSSL) aims to derive a global model by training fully-labeled and fully-unlabeled clients or training partially labeled clients. The existing approaches work well when local clients have independent and identically distributed (IID) data but fail to generalize to a more practical FSSL setting, i.e., Non-IID setting ...
arxiv  

Fairness-Aware Client Selection for Federated Learning [PDF]

arXiv, 2023
Federated learning (FL) has enabled multiple data owners (a.k.a. FL clients) to train machine learning models collaboratively without revealing private data. Since the FL server can only engage a limited number of clients in each training round, FL client selection has become an important research problem.
arxiv  

Trustware: A Device-based Protocol for Verifying Client Legitimacy [PDF]

arXiv, 2017
Online services commonly attempt to verify the legitimacy of users with CAPTCHAs. However, CAPTCHAs are annoying for users, often difficult for users to solve, and can be defeated using cheap labor or, increasingly, with improved algorithms. We propose a new protocol for clients to prove their legitimacy, allowing the client's devices to vouch for the ...
arxiv  

Waiter-Client and Client-Waiter colourability games on a $k$-uniform hypergraph and the $k$-SAT game [PDF]

arXiv, 2016
Waiter-Client and Client-Waiter games are two-player, perfect information games, with no chance moves, played on a finite set (board) with special subsets known as the winning sets. Each round of the biased $(1:q)$ game begins with Waiter offering $q+1$ previously unclaimed elements of the board to Client, who claims one. The $q$ elements remaining are
arxiv  

Anomalous Client Detection in Federated Learning [PDF]

arXiv
Federated learning (FL), with the growing IoT and edge computing, is seen as a promising solution for applications that are latency- and privacy-aware. However, due to the widespread dispersion of data across many clients, it is challenging to monitor client anomalies caused by malfunctioning devices or unexpected events.
arxiv