Results 1 to 10 of about 56,309 (276)
Node Classification Method Based on Hierarchical Hypergraph Neural Network [PDF]
SensorsHypergraph neural networks have gained widespread attention due to their effectiveness in handling graph-structured data with complex relationships and multi-dimensional interactions.
Feng Xu +3 more
doaj +2 more sources
DGHSA: derivative graph-based hypergraph structure attack [PDF]
Scientific ReportsHypergraph Neural Networks (HGNNs) have been significantly successful in higher-order tasks. However, recent study have shown that they are also vulnerable to adversarial attacks like Graph Neural Networks. Attackers fool HGNNs by modifying node links in
Yang Chen +4 more
doaj +2 more sources
Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation [PDF]
The Web Conference, 2021 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.
Junliang Yu +5 more
semanticscholar +1 more source
Hypergraph Contrastive Collaborative Filtering [PDF]
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2022 Collaborative Filtering (CF) has emerged as fundamental paradigms for parameterizing users and items into latent representation space, with their correlative patterns from interaction data.
Lianghao Xia +5 more
semanticscholar +1 more source
GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning [PDF]
Computer Vision and Pattern Recognition, 2022 Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction. However, previous works only consider pair-wise interactions with limited relational reasoning. To promote
Chenxin Xu +4 more
semanticscholar +1 more source
Computing degree based topological indices of algebraic hypergraphs [PDF]
HeliyonTopological indices are numerical parameters that indicate the topology of graphs or hypergraphs. A hypergraph H=(V(H),E(H)) consists of a vertex set V(H) and an edge set E(H), where each edge e∈E(H) is a subset of V(H) with at least two elements.
Amal S. Alali +4 more
doaj +2 more sources
Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation [PDF]
Knowledge Discovery and Data Mining, 2022 Learning dynamic user preference has become an increasingly important component for many online platforms (e.g., video-sharing sites, e-commerce systems) to make sequential recommendations.
Yuhao Yang +5 more
semanticscholar +1 more source
Sheaf Hypergraph Networks [PDF]
Neural Information Processing Systems, 2023 Higher-order relations are widespread in nature, with numerous phenomena involving complex interactions that extend beyond simple pairwise connections.
Iulia Duta +3 more
semanticscholar +1 more source
Self-Supervised Hypergraph Transformer for Recommender Systems [PDF]
Knowledge Discovery and Data Mining, 2022 Graph Neural Networks (GNNs) have been shown as promising solutions for collaborative filtering (CF) with the modeling of user-item interaction graphs. The key idea of existing GNN-based recommender systems is to recursively perform the message passing ...
Lianghao Xia, Chao Huang, Chuxu Zhang
semanticscholar +1 more source
UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks [PDF]
International Joint Conference on Artificial Intelligence, 2021 Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains.
Jing Huang, Jie Yang
semanticscholar +1 more source