Zobrazeno 1 - 10
of 41 309
pro vyhledávání: '"Li-qiang An"'
Autor:
Li, Qiang, Wai, Hoi-To
This paper studies the effect of data homogeneity on multi-agent stochastic optimization. We consider the decentralized stochastic gradient (DSGD) algorithm and perform a refined convergence analysis. Our analysis is explicit on the similarity betwee
Externí odkaz:
http://arxiv.org/abs/2409.04092
Autor:
Yang, Kaixiang, Shan, Wenqi, Li, Xudong, Wang, Xuan, Yang, Xikai, Wang, Xi, Heng, Pheng-Ann, Li, Qiang, Wang, Zhiwei
Multi-modal brain tumor segmentation typically involves four magnetic resonance imaging (MRI) modalities, while incomplete modalities significantly degrade performance. Existing solutions employ explicit or implicit modality adaptation, aligning feat
Externí odkaz:
http://arxiv.org/abs/2408.08708
Traditional license plate detection and recognition models are often trained on closed datasets, limiting their ability to handle the diverse license plate formats across different regions. The emergence of large-scale pre-trained models has shown ex
Externí odkaz:
http://arxiv.org/abs/2408.05729
A muon collider represents a promising candidate for the next generation of particle physics experiments after the expected end of LHC operations in the early 2040s. Rare or hard-to-detect processes at the LHC, such as the production of multiple gaug
Externí odkaz:
http://arxiv.org/abs/2408.05429
The performance of conventional interference management strategies degrades when interference power is comparable to signal power. We consider a new perspective on interference management using semantic communication. Specifically, a multi-user seman
Externí odkaz:
http://arxiv.org/abs/2408.04283
The spin-singlet state $\eta_{_{c2}}(^1D_{_2})$ has not been discovered in experiment and it is the only missing low-excited $D$-wave charmonium, so in this paper, we like to study its properties. Using the Bethe-Salpeter equation method, we obtain i
Externí odkaz:
http://arxiv.org/abs/2408.03011
Federated learning (FL) is an emerging distributed learning paradigm without sharing participating clients' private data. However, existing works show that FL is vulnerable to both Byzantine (security) attacks and data reconstruction (privacy) attack
Externí odkaz:
http://arxiv.org/abs/2407.19703
In this study, we present an analysis of the archival X-ray data of the eclipsing supersoft X-ray binary CAL 87 observed with the {\it Chandra} Advanced CCD Imaging Spectrometer (ACIS) camera and Low Energy Transmission Grating (LETG) in 2001 August
Externí odkaz:
http://arxiv.org/abs/2407.17778
Federated Learning (FL) is a novel client-server distributed learning framework that can protect data privacy. However, recent works show that FL is vulnerable to poisoning attacks. Many defenses with robust aggregators (AGRs) are proposed to mitigat
Externí odkaz:
http://arxiv.org/abs/2407.15267
Federated graph learning (FedGL) is an emerging federated learning (FL) framework that extends FL to learn graph data from diverse sources. FL for non-graph data has shown to be vulnerable to backdoor attacks, which inject a shared backdoor trigger i
Externí odkaz:
http://arxiv.org/abs/2407.08935