A survey on hypergraph representation learning
Hypergraphs have attracted increasing attention in recent years thanks to their flexibility in
naturally modeling a broad range of systems where high-order relationships exist among …
naturally modeling a broad range of systems where high-order relationships exist among …
FedGL: Federated graph learning framework with global self-supervision
Graph data are ubiquitous in the real world. Graph learning (GL) attempts to mine and
analyze graph data so that valuable information can be discovered. Existing GL methods are …
analyze graph data so that valuable information can be discovered. Existing GL methods are …
CAT-walk: Inductive hypergraph learning via set walks
Temporal hypergraphs provide a powerful paradigm for modeling time-dependent, higher-
order interactions in complex systems. Representation learning for hypergraphs is essential …
order interactions in complex systems. Representation learning for hypergraphs is essential …
SHNE: Semantics and homophily preserving network embedding
Z Zhang, C Chen, Y Chang, W Hu… - … on Neural Networks …, 2021 - ieeexplore.ieee.org
Graph convolutional networks (GCNs) have achieved great success in many applications
and have caught significant attention in both academic and industrial domains. However …
and have caught significant attention in both academic and industrial domains. However …
[HTML][HTML] Hypergraph Computation
Practical real-world scenarios such as the Internet, social networks, and biological networks
present the challenges of data scarcity and complex correlations, which limit the applications …
present the challenges of data scarcity and complex correlations, which limit the applications …
A hypergraph model of product function recombination based on online reviews
W Lin, Y Wang, R Xiao - Journal of Engineering Design, 2023 - Taylor & Francis
Functional module recombination is a common means for manufacturers to upgrade and
launch new product quickly. However, this method may bring with significant risks and it …
launch new product quickly. However, this method may bring with significant risks and it …
Hypernetwork dismantling via deep reinforcement learning
Network dismantling aims to degrade the connectivity of a network by removing an optimal
set of nodes. It has been widely adopted in many real-world applications such as epidemic …
set of nodes. It has been widely adopted in many real-world applications such as epidemic …
Influence Maximization in Hypergraphs based on Evolutionary Deep Reinforcement Learning
Influence Maximization (IM) in graphs tries to identify a subset of influential nodes that
maximize the influence spread under a propagation model. Existing works on IM mainly …
maximize the influence spread under a propagation model. Existing works on IM mainly …
HIN2Grid: A disentangled CNN-based framework for heterogeneous network learning
Recently, graph convolutional networks (GCNs) have been applied to heterogeneous
information network (HIN) learning and have shown promising performance. However, the …
information network (HIN) learning and have shown promising performance. However, the …
Ambiguities in neural-network-based hyperedge prediction
A hypergraph is a generalization of a graph that depicts higher-order relations. Predicting
higher-order relations, ie hyperedges, is a fundamental problem in hypergraph studies, and …
higher-order relations, ie hyperedges, is a fundamental problem in hypergraph studies, and …