Results 71 to 80 of about 1,673 (179)

Investigating Hypernode Classification of Complex Systems Based on High-order Graph Neural Networks

Guidance, Navigation and Control
Investigating latent interactions beyond direct connections is essential for analyzing complex networks. However, traditional graph structures often fail to capture complex relationships, especially in the high-order interactions among multiple ...
Jiawen Chen, Yanyan He, Duxin Chen, Wenwu Yu   +3 more
doaj   +1 more source

Hypergraph Motif Representation Learning

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1
Hypergraphs have emerged as a powerful tool for representing high-order connections in real-world complex systems. Similar to graphs, local structural patterns in hypergraphs, known as high-order motifs (h-motifs), play a crucial role in network dynamics and serve as fundamental building blocks across various domains.
Alessia Antelmi, Gennaro Cordasco, Daniele De Vinco, Valerio Di Pasquale, Mirko Polato, Carmine Spagnuolo   +5 more
openaire   +1 more source

Cost-Sensitive Hypergraph Learning With Structure Quality Preservation for IoT Software Defect Prediction

IEEE Open Journal of the Communications Society
Generative AI is revolutionizing Software Engineering (SE), as both engineers and academics embrace this technology in their work. To better leverage this technology for software generation, it is essential to propose effective IoT software defect ...
Nan Wang, Jiqiang Liu, Bing Du, Qinxin Zhao, Yuanlin Sun, Tao Zhang, Dunqiu Fan, Wenjin Li, Binyong Li   +8 more
doaj   +1 more source

Adaptive Expansion for Hypergraph Learning

CoRR
Hypergraph, with its powerful ability to capture higher-order relationships, has gained significant attention recently. Consequently, many hypergraph representation learning methods have emerged to model the complex relationships among hypergraphs. In general, these methods leverage classic expansion methods to convert hypergraphs into weighted or ...
Tianyi Ma, Yiyue Qian, Shinan Zhang, Chuxu Zhang, Yanfang Ye 0001   +4 more
openaire   +2 more sources

AHD-SLE: Anomalous Hyperedge Detection on Hypergraph Symmetric Line Expansion

Axioms
Graph anomaly detection aims to identify unusual patterns or structures in graph-structured data. Most existing research focuses on anomalous nodes in ordinary graphs with pairwise relationships.
Yingle Li, Hongtao Yu, Haitao Li, Fei Pan, Shuxin Liu   +4 more
doaj   +1 more source

Geometric Hypergraph Learning for Visual Tracking

IEEE Transactions on Cybernetics, 2017
Graph based representation is widely used in visual tracking field by finding correct correspondences between target parts in consecutive frames. However, most graph based trackers consider pairwise geometric relations between local parts. They do not make full use of the target's intrinsic structure, thereby making the representation easily disturbed ...
Dawei Du, Honggang Qi, Longyin Wen, Qi Tian 0001, Qingming Huang, Siwei Lyu   +5 more
openaire   +3 more sources

A lightweight single-view contrastive learning hypergraph neural network for food–microbe–disease association prediction

BMC Bioinformatics
Background Identifying potential associations among food, gut microbiota and disease is fundamental for elucidating interaction mechanisms and advancing personalized healthy dietary strategies. While computational methods have been extensively applied to
Jianqiang Hu, Mingyi Hu, Yangxiang Wu, Songyao Mu, Dahao Huang, Baolong Wang, Yuchen Gao, Shixin Gu, Jinlin Zhu   +8 more
doaj   +1 more source

Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction

Applied Sciences
With the widespread adoption of mobile devices and the increasing availability of user trajectory data, accurately predicting the next location a user will visit has become a pivotal task in location-based services.
Fengyu Liu, Kexin Zhang, Chao Lian, Yunong Tian   +3 more
doaj   +1 more source

Higher-Order Regularization Learning on Hypergraphs

CoRR
Higher-Order Hypergraph Learning (HOHL) was recently introduced as a principled alternative to classical hypergraph regularization, enforcing higher-order smoothness via powers of multiscale Laplacians induced by the hypergraph structure. Prior work established the well- and ill-posedness of HOHL through an asymptotic consistency analysis in geometric ...
Adrien Weihs, Andrea L. Bertozzi, Matthew Thorpe   +2 more
openaire   +2 more sources

Robust Financial Fraud Detection via Causal Intervention and Multi-View Contrastive Learning on Dynamic Hypergraphs

Mathematics
Financial fraud detection is critical to modern economic security, yet remains challenging due to collusive group behavior, temporal drift, and severe class imbalance.
Xiong Luo
doaj   +1 more source