Zobrazeno 1 - 10
of 877
pro vyhledávání: '"ZHU Yulin"'
Publikováno v:
Zhongguo linchuang yanjiu, Vol 37, Iss 3, Pp 397-400 (2024)
Objective To investigate the the clinical application of triglyceride-glucose (TyG) index and its correlation with atherosclerosis in patients with type 2 diabetes mellitus (T2DM). Methods From January 2020 to December 2022,499 patients with T2DM w
Externí odkaz:
https://doaj.org/article/7f22ba0765524e609300166e0e842d7a
Publikováno v:
High Temperature Materials and Processes, Vol 41, Iss 1, Pp 111-122 (2022)
The thermodynamic precipitation behavior of the second-phase particles in Nb-containing high titanium microalloyed steel has been studied by calculation in this article. It is revealed that FCC_A1#2 is isomorphic with FCC_A1#3 and the contents of Ti
Externí odkaz:
https://doaj.org/article/a70d83f97b884929ad7bc25c1664a0fa
Graph Neural Networks (GNNs) have demonstrated commendable performance for graph-structured data. Yet, GNNs are often vulnerable to adversarial structural attacks as embedding generation relies on graph topology. Existing efforts are dedicated to pur
Externí odkaz:
http://arxiv.org/abs/2408.16537
Publikováno v:
Saudi Pharmaceutical Journal, Vol 28, Iss 11, Pp 1408-1410 (2020)
Drug-drug interactions lead to altered clinical effects, including adverse reactions. Therapeutic drug monitoring of digoxin is necessary due to its narrow therapeutic range. Linezolid can cause variable exposures in patients hospitalized in the inte
Externí odkaz:
https://doaj.org/article/48ee2a0ee08f481ebd09bf659af84fce
Graph Neural Networks (GNNs) have become widely used in the field of graph mining. However, these networks are vulnerable to structural perturbations. While many research efforts have focused on analyzing vulnerability through poisoning attacks, we h
Externí odkaz:
http://arxiv.org/abs/2312.07158
Deep Graph Learning (DGL) has emerged as a crucial technique across various domains. However, recent studies have exposed vulnerabilities in DGL models, such as susceptibility to evasion and poisoning attacks. While empirical and provable robustness
Externí odkaz:
http://arxiv.org/abs/2312.03979
Graph anomaly detection (GAD) has achieved success and has been widely applied in various domains, such as fraud detection, cybersecurity, finance security, and biochemistry. However, existing graph anomaly detection algorithms focus on distinguishin
Externí odkaz:
http://arxiv.org/abs/2308.01063
Publikováno v:
SHS Web of Conferences, Vol 123, p 01019 (2021)
This paper selects data related to each representative industry in the Central Yunnan Urban Agglomeration from 2010-2019 as the research sample, and analyzes the functional structure of the Central Yunnan Urban Agglomeration through spatial Gini coef
Externí odkaz:
https://doaj.org/article/0357bc035def4e6288e3325831f2c51b
Autor:
Lai, Yuni, Waniek, Marcin, Li, Liying, Wu, Jingwen, Zhu, Yulin, Michalak, Tomasz P., Rahwan, Talal, Zhou, Kai
Random Walks-based Anomaly Detection (RWAD) is commonly used to identify anomalous patterns in various applications. An intriguing characteristic of RWAD is that the input graph can either be pre-existing or constructed from raw features. Consequentl
Externí odkaz:
http://arxiv.org/abs/2307.14387
We investigate adversarial robustness of unsupervised Graph Contrastive Learning (GCL) against structural attacks. First, we provide a comprehensive empirical and theoretical analysis of existing attacks, revealing how and why they downgrade the perf
Externí odkaz:
http://arxiv.org/abs/2307.12555