FedBnR: Mitigating federated learning Non-IID problem by breaking the skewed task and reconstructing representation

Article Computer Science, Theory & Methods

FedProc: Prototypical contrastive federated learning on non-IID data

Xutong Mu et al.

Summary: This paper proposes FedProc, a prototypical contrastive federated learning approach that uses prototypes as global knowledge to correct the drift of each client's local training. Experimental results show that FedProc can improve accuracy by 1.6% to 7.9% with an acceptable computational cost compared to state-of-the-art federated learning methods.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2023)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Services Management and Distributed Multihop Requests Routing in Mobile Edge Networks

Tuo Shi et al.

Summary: This paper presents an online problem of jointly managing mobile edge services and routing distributed multi-hop requests in an MEC network. By proposing approximation algorithms and online algorithms, this problem can be effectively addressed.

IEEE-ACM TRANSACTIONS ON NETWORKING (2023)

添加到收藏夹

Article Automation & Control Systems

Privacy Threat and Defense for Federated Learning With Non-i.i.d. Data in AIoT

Zuobin Xiong et al.

Summary: This article explores innovative approaches to privacy protection in federated learning with non-i.i.d. data. A novel algorithm, 2DP-FL, is designed to achieve differential privacy by adding noise during training local models and when distributing global model. The results of theoretical analysis and real-data experiments validate the advantages of 2DP-FL in privacy protection, learning convergence, and model accuracy.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

添加到收藏夹

Article Automation & Control Systems

From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where

Imran Ahmed et al.

Summary: This article provides a comprehensive survey of AI and XAI-based methods in the context of Industry 4.0. It discusses the technologies enabling Industry 4.0, investigates the main methods used in the literature, and addresses the future research directions and the importance of responsible and human-centric AI and XAI systems.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Federated Learning on Non-IID Data Silos: An Experimental Study

Qinbin Li et al.

Summary: Due to increasing privacy concerns and data regulations, training data has become more fragmented, forming distributed databases of multiple data silos. Federated learning (FL) has emerged as a solution to train machine learning models collaboratively without exchanging raw data. However, the heterogeneity of data distribution among parties is a common challenge in distributed databases. Previous studies lack a comprehensive understanding of the advantages and disadvantages of FL algorithms under non-IID data settings. This paper proposes comprehensive data partitioning strategies and conducts extensive experiments to evaluate state-of-the-art FL algorithms, providing insights for future studies in addressing challenges in data silos.

2022 IEEE 38TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2022) (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A survey on federated learning

Chen Zhang et al.

Summary: Federated learning is a setup where multiple clients collaborate to solve machine learning problems under the coordination of a central aggregator. It reduces systematic privacy risks and costs through local computing and model transmission. This method ensures data privacy for each device and improves learning efficiency and security.

KNOWLEDGE-BASED SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Distributed Query Processing in the Edge-Assisted IoT Data Monitoring System

Zhipeng Cai et al.

Summary: This article investigates query processing in an edge-assisted IoT data monitoring system (EDMS), proposing an approximation algorithm and evaluating its performance through extensive simulations.

IEEE INTERNET OF THINGS JOURNAL (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Towards Fair Federated Learning with Zero-Shot Data Augmentation

Weituo Hao et al.

Summary: This work presents a federated learning scheme that improves fairness by using zero-shot data augmentation to mitigate statistical heterogeneity and encourage more uniform accuracy performance across clients in federated networks.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence