Zobrazeno 1 - 10
of 64
pro vyhledávání: '"Sun, Yiheng"'
Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain diverse and intricate noise. Noise can significantly degrade the qual
Externí odkaz:
http://arxiv.org/abs/2309.02025
Continuous-time dynamic graph modeling is a crucial task for many real-world applications, such as financial risk management and fraud detection. Though existing dynamic graph modeling methods have achieved satisfactory results, they still suffer fro
Externí odkaz:
http://arxiv.org/abs/2309.02012
Temporal Interaction Graphs (TIGs) are widely employed to model intricate real-world systems such as financial systems and social networks. To capture the dynamism and interdependencies of nodes, existing TIG embedding models need to process edges se
Externí odkaz:
http://arxiv.org/abs/2308.14129
The emergence of vertical federated learning (VFL) has stimulated concerns about the imperfection in privacy protection, as shared feature embeddings may reveal sensitive information under privacy attacks. This paper studies the delicate equilibrium
Externí odkaz:
http://arxiv.org/abs/2308.02362
Autor:
Zhang, Yao, Xiong, Yun, Liao, Yongxiang, Sun, Yiheng, Jin, Yucheng, Zheng, Xuehao, Zhu, Yangyong
Temporal interaction graphs (TIGs), consisting of sequences of timestamped interaction events, are prevalent in fields like e-commerce and social networks. To better learn dynamic node embeddings that vary over time, researchers have proposed a serie
Externí odkaz:
http://arxiv.org/abs/2302.06057
Autor:
Wu, Xixi, Xiong, Yun, Zhang, Yao, Jiao, Yizhu, Shan, Caihua, Sun, Yiheng, Zhu, Yangyong, Yu, Philip S.
Community detection refers to the task of discovering closely related subgraphs to understand the networks. However, traditional community detection algorithms fail to pinpoint a particular kind of community. This limits its applicability in real-wor
Externí odkaz:
http://arxiv.org/abs/2210.08274
Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with sophisticated designs have achieved promising results, the black-box
Externí odkaz:
http://arxiv.org/abs/2208.07211
Federated learning has seen increased adoption in recent years in response to the growing regulatory demand for data privacy. However, the opaque local training process of federated learning also sparks rising concerns about model faithfulness. For i
Externí odkaz:
http://arxiv.org/abs/2202.04311
The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to advocating financial inclusion. It has non-trivial social benefits of diminishing financi
Externí odkaz:
http://arxiv.org/abs/2112.02365
Publikováno v:
In Biomedical Signal Processing and Control November 2024 97