Results 141 to 150 of about 7,049,980 (289)
Privacy-preserving Quantification of Non-IID Degree in Federated Learning
Federated learning (FL) offers a privacy-preserving approach to machine learning for multiple collaborators without sharing raw data. However, the existence of non-independent and non-identically distributed (non-IID) datasets across different clients ...
Jin, Yaochu +3 more
core
Non-IID outlier detection with coupled outlier factors [PDF]
, 2019 University of Technology Sydney. Faculty of Engineering and Information Technology.Outliers are data objects which are rare or inconsistent compared to the majority of objects.
Pang, Guansong
core
NIPD: A Federated Learning Person Detection Benchmark Based on Real-World Non-IID Data
, 2023 Federated learning (FL), a privacy-preserving distributed machine learning, has been rapidly applied in wireless communication networks. FL enables Internet of Things (IoT) clients to obtain well-trained models while preventing privacy leakage.
Ding, Zhen +7 more
core
Inconsistency of the Capital Asset Pricing Model in a Multi‐Currency Environment
International Journal of Finance &Economics, EarlyView.ABSTRACT The capital asset pricing model (CAPM) is a widely adopted model in asset pricing theory and portfolio construction because of its intuitive nature. One of its main conclusions is that there exists a global market portfolio that each rational investor should hold in proportion to the risk‐free asset. In this paper, we demonstrate theoretically
Khalifa Al‐Thani +4 more
wiley +1 more source
SensorsFederated Learning (FL) enables collaborative model training on smart edge devices while preserving data privacy, but it suffers from decreased performance when faced with non-Independent and Identically Distributed (non-IID) data.
Kinda Mreish +4 more
doaj +1 more source
Quantum tomography for non-iid sources
Quantum state and process tomography are typically analyzed under the assumption that devices emit independent and identically distributed (i.i.d.) states or channels. In realistic experiments, however, noise, drift, feedback, or adversarial behavior violate this assumption.
openaire +2 more sources
International Journal of Finance &Economics, EarlyView.ABSTRACT This study examines risk transmission and co‐movements between financial markets (G7 countries and China) and commodity markets (gold and oil) during the COVID‐19 crisis. Daily closing prices for major equity indices (CAC40, CSI300, DAX30, FTSE100, MIB, NIKKEI, TSX and S&P500) and futures prices for gold, brent and WTI were analysed using DCC ...
V. Moutinho +3 more
wiley +1 more source
Impact of Sovereign Debt Maturity on Fiscal Sustainability
International Journal of Finance &Economics, EarlyView.ABSTRACT This study is the first to investigate the impact of the term structure of public debt on fiscal sustainability. We adopt the widely used backward‐looking measure of fiscal sustainability—fiscal responsiveness as proposed by Bohn. Using data from De Graeve and Mazzolini and focusing on a sample of 19 most developed countries, we demonstrate ...
António Afonso +3 more
wiley +1 more source
Big Data and Cognitive ComputingThe increasing deployment of Internet of Things (IoT) devices introduces significant security challenges, while privacy concerns limit centralized data aggregation for intrusion detection.
Thaer AL Ibaisi +5 more
doaj +1 more source
PFL-NON-IID Framework: Evaluating MOON Algorithm on Handling Non-IID Data Distributions
, 2023 Sheng Chen +3 more
openaire +1 more source