Results 111 to 120 of about 2,491 (218)

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

Hypergraph Node Representation Learning with One-Stage Message Passing

, 2023
Hypergraphs as an expressive and general structure have attracted considerable attention from various research domains. Most existing hypergraph node representation learning techniques are based on graph neural networks, and thus adopt the two-stage ...
Wang, Weiqing, Li, Yuan-Fang, Yuan, Fajie, Zhou, Xin, Qu, Shilin   +4 more
core  

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

Data mining, Hypergraph Transversals, and Machine Learning (Extended Abstract)

, 1997
Several data mining problems can be formulated as problems of finding maximally specific sentences that are interesting in a database. We first show that this problem has a close relationship with the hypergraph transversal problem.
Dimitrios Gunopulos, Roni Khardon, Hannu Toivonen, Heikki Mannila   +3 more
core   +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

Fault diagnosis of shearer cutting unit gearbox based on improved cascaded broad learning

Gong-kuang zidonghua
The vibration monitoring data of the shearer cutting unit gearbox has a complex structure and is prone to class imbalance issues, leading to frequent false positives in traditional machine learning-based fault diagnosis methods.
LI Xin, LI Shuhua, CHEN Hao, SI Lei, WEI Dong, ZOU Xiaoyu   +5 more
doaj   +1 more source

Hypergraph-based optimisations for scalable graph analytics and learning [PDF]

Graph-structured data has benefits of capturing inter-connectivity (topology) and hetero geneous knowledge (node/edge features) simultaneously. Hypergraphs may glean even more information reflecting complex non-pairwise relationships and additional ...
Haldar, Aparajita
core  

Identifying autism spectrum disorder from multi-modal data with privacy-preserving

npj Mental Health Research
The application of deep learning models to precision medical diagnosis often requires the aggregation of large amounts of medical data to effectively train high-quality models.
Haishuai Wang, Hezi Jing, Jianjun Yang, Chao Liu, Liwei Hu, Guangyu Tao, Ziping Zhao, Ning Shen   +7 more
doaj   +1 more source

Hypergraph Representation Learning with Weighted- and Clustering-Biased Random Walks

Entropy
Hypergraphs are powerful tools for modeling complex systems because they naturally encode higher-order interactions. However, most existing hypergraph representation-learning methods still struggle to capture such high-order structures, particularly in ...
Li Liang, Shi-Ming Cai, Shi-Cai Gong
doaj   +1 more source