Zobrazeno 71 - 80
of 366
pro vyhledávání: '"Li, Jundong"'
Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing unsupervised fe
Externí odkaz:
http://arxiv.org/abs/2106.02216
To mitigate the spread of COVID-19 pandemic, decision-makers and public authorities have announced various non-pharmaceutical policies. Analyzing the causal impact of these policies in reducing the spread of COVID-19 is important for future policy-ma
Externí odkaz:
http://arxiv.org/abs/2106.01315
Graph Neural Networks have recently become a prevailing paradigm for various high-impact graph analytical problems. Existing efforts can be mainly categorized as spectral-based and spatial-based methods. The major challenge for the former is to find
Externí odkaz:
http://arxiv.org/abs/2104.12840
When a disaster occurs, maintaining and restoring community lifelines subsequently require collective efforts from various stakeholders. Aiming at reducing the efforts associated with generating Stakeholder Collaboration Networks (SCNs), this paper p
Externí odkaz:
http://arxiv.org/abs/2103.00287
Autor:
Yu, Junliang, Yin, Hongzhi, Li, Jundong, Wang, Qinyong, Hung, Nguyen Quoc Viet, Zhang, Xiangliang
Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, rea
Externí odkaz:
http://arxiv.org/abs/2101.06448
Text classification is a critical research topic with broad applications in natural language processing. Recently, graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on t
Externí odkaz:
http://arxiv.org/abs/2011.00387
We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. With the advances of deep learning, current link prediction methods commonly compute features from subgraphs centered at two ne
Externí odkaz:
http://arxiv.org/abs/2010.10046
Attributed networks nowadays are ubiquitous in a myriad of high-impact applications, such as social network analysis, financial fraud detection, and drug discovery. As a central analytical task on attributed networks, node classification has received
Externí odkaz:
http://arxiv.org/abs/2006.12739
Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations. However, a vast majority of existing
Externí odkaz:
http://arxiv.org/abs/2004.13825
Social recommender systems are expected to improve recommendation quality by incorporating social information when there is little user-item interaction data. However, recent reports from industry show that social recommender systems consistently fai
Externí odkaz:
http://arxiv.org/abs/2004.02340