☆ 4.7 Article

TKAGFL: A Federated Communication Framework Under Data Heterogeneity

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING (2023)

Related references

Note: Only part of the references are listed.

Article Geography

A privacy-preserving framework for location recommendation using decentralized collaborative machine learning

Jinmeng Rao et al.

Summary: The study introduces a privacy-preserving location recommendation framework based on federated learning, which keeps user data private by storing it on their devices and aggregates local model parameters securely through multiple-party computation. The framework also integrates transportation infrastructure, place safety, and flow-based spatial interaction information to improve recommendation accuracy.

TRANSACTIONS IN GIS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A distributed density estimation algorithm and its application to naive Bayes classification

Ahmad Khajenezhad et al.

Summary: The proposed nested Log-Poly model provides an accurate density estimation in a distributed setting by transferring small-sized statistics from client nodes to a central node for estimation. It is particularly suitable for one-dimensional density estimations and is a good choice for naive Bayes classifier.

APPLIED SOFT COMPUTING (2021)

Add to Collection

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)

Add to Collection

Article Computer Science, Artificial Intelligence

SecureBoost: A Lossless Federated Learning Framework

Kewei Cheng et al.

Summary: This article introduces a privacy-preserving tree-boosting system called SecureBoost based on federated learning, which allows joint learning processes without violating user privacy. SecureBoost provides the same level of accuracy as non-privacy-preserving methods while keeping private data providers' information confidential.

IEEE INTELLIGENT SYSTEMS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Intelligent deep learning based bidirectional long short term memory model for automated reply of e-mail client prototype

P. Rajaraman et al.

Summary: E-mail is a widely used and efficient method of communication, with researchers developing intelligent systems to automate responses, such as the OBiLSTM-AER model which uses deep learning techniques for automated email replies. The model utilizes Glove, Bi-LSTM, and softmax classifier for feature extraction and label allocation, with hyperparameter tuning using OGSO algorithm for improved performance. Extensive simulations were conducted to demonstrate the effectiveness of the proposed method.

PATTERN RECOGNITION LETTERS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

MicroNet: Improving Image Recognition with Extremely Low FLOPs

Yunsheng Li et al.

Summary: This paper introduces the MicroNet family of networks, which achieves significant performance gains in the low FLOP regime by integrating sparse connectivity and dynamic activation functions. The proposed MicroNet outperforms MobileNetV3 by 9.6% in ImageNet classification under the constraint of 12M FLOPs, showcasing its efficiency and effectiveness in improving accuracy.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Hybrid Quantum Network for classification of finance and MNIST data

Gerhard Hellstem

Summary: The study found that a hybrid quantum-classical network has an advantage in classifying finance and MNIST datasets compared to a pure classical network. However, issues of overfitting the dataset still arise, indicating a need for future research in the field of (hybrid) quantum networks.

2021 IEEE 18TH INTERNATIONAL CONFERENCE ON SOFTWARE ARCHITECTURE COMPANION (ICSA-C) (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep Private-Feature Extraction

Seyed Ali Osia et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2020)

Add to Collection

Article Computer Science, Hardware & Architecture

Emerging Technologies for 5G-IoV Networks: Applications, Trends and Opportunities

Wei Duan et al.

IEEE NETWORK (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data

Felix Sattler et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

Add to Collection

Article Substance Abuse

Defining the esports bettor: evidence from an online panel survey of emerging adults

Heather Wardle et al.

INTERNATIONAL GAMBLING STUDIES (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Federated Machine Learning: Concept and Applications

Qiang Yang et al.

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY (2019)

Add to Collection

Article Engineering, Multidisciplinary

Contract Mechanism and Performance Analysis for Data Transaction in Mobile Social Networks

Jun Du et al.

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING (2019)

Add to Collection

Article Computer Science, Cybernetics

Decentralized On-Demand Energy Supply for Blockchain in Internet of Things: A Microgrids Approach

Jianan Li et al.

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Generative Adversarial Networks An overview

Antonia Creswell et al.

IEEE SIGNAL PROCESSING MAGAZINE (2018)

Add to Collection

Article Engineering, Electrical & Electronic

A survey on wireless mesh networks

IF Akyildiz et al.

IEEE COMMUNICATIONS MAGAZINE (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.