5 papers
A Framework for Directed Hypergraph Signal Processing via tensor t-SVD
Carlos Mundo-Levano, Nicolás Bello, Daniel L. Lau +1
We introduce Directed Hypergraph Signal Processing (DHGSP), a unified framework that extends graph signal processing to accommodate both higher-order (polyadic) and asymmetric (dir…
A Framework for Directed Acyclic Hypergraph Learning
Zhiyuan Dong, Carlos Mundo-Levano, Wei Qian +2
Continuous optimization methods for learning Directed Acyclic Graphs (DAGs) operate on weighted adjacency matrices and are therefore limited to pairwise causal relationships. We pr…
Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets
Fuli Wang, Wei Qian, Daniel L. Lau +1
Convolutions have successfully transitioned from image processing to the complex realm of non-Euclidean higher-order domains, particularly in hypergraphs. Despite the success in co…
Scalable Hypergraph Structure Learning with Diverse Smoothness Priors
Benjamin T. Brown, Haoxiang Zhang, Daniel L. Lau +1
In graph signal processing, learning the weighted connections between nodes from a set of sample signals is a fundamental task when the underlying relationships are not known a pri…
Generalization Performance of Hypergraph Neural Networks
Yifan Wang, Gonzalo R. Arce, Guangmo Tong
Hypergraph neural networks have been promising tools for handling learning tasks involving higher-order data, with notable applications in web graphs, such as modeling multi-way hy…