Results 11 to 20 of about 1,673 (179)
Learning on Hypergraphs with Sparsity [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020 Hypergraph is a general way of representing high-order relations on a set of objects. It is a generalization of graph, in which only pairwise relations can be represented. It finds applications in various domains where relationships of more than two objects are observed.
Nguyen, Canh Hao, Mamitsuka, Hiroshi
openaire +4 more sources
Learnable Hypergraph Laplacian for Hypergraph Learning
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022 HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data. However, most existing convolution filters are localized and determined by the pre-defined initial hypergraph topology, neglecting to explore implicit and long-ange relations in real-world data.
Jiying Zhang +4 more
openaire +3 more sources
A Survey on Hypergraph Representation Learning
ACM Computing Surveys, 2023 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 their interacting parts. This survey reviews the newly born hypergraph representation learning problem, whose goal is to learn a function to project objects—most commonly ...
Alessia Antelmi +5 more
openaire +4 more sources
On multistage learning a hidden hypergraph [PDF]
2016 IEEE International Symposium on Information Theory (ISIT), 2016 5 pages, IEEE ...
Arkadii G. D'yachkov +3 more
openaire +2 more sources
Learning Low Degree Hypergraphs
CoRR, 2022 We study the problem of learning a hypergraph via edge detecting queries. In this problem, a learner queries subsets of vertices of a hidden hypergraph and observes whether these subsets contain an edge or not. In general, learning a hypergraph with $m$ edges of maximum size $d$ requires $Ω((2m/d)^{d/2})$ queries.
Eric Balkanski +2 more
openaire +3 more sources
Unified Low-Rank Subspace Clustering with Dynamic Hypergraph for Hyperspectral Image
Remote Sensing, 2021 Low-rank representation with hypergraph regularization has achieved great success in hyperspectral imagery, which can explore global structure, and further incorporate local information.
Jinhuan Xu, Liang Xiao, Jingxiang Yang
doaj +1 more source
Deep Hypergraph Structure Learning
CoRR, 2022 Learning on high-order correlation has shown superiority in data representation learning, where hypergraph has been widely used in recent decades. The performance of hypergraph-based representation learning methods, such as hypergraph neural networks, highly depends on the quality of the hypergraph structure.
Zizhao Zhang 0003 +3 more
openaire +2 more sources
Learning a Hidden Hypergraph [PDF]
, 2005 We consider the problem of learning a hypergraph using edge-detecting queries. In this model, the learner may query whether a set of vertices induces an edge of the hidden hypergraph or not. We show that an r-uniform hypergraph with m edges and n vertices is learnable with O(2$^{\rm 4{\it r}}$m · poly(r,log n)) queries with high probability.
Dana Angluin, Jiang Chen
openaire +2 more sources
Dynamic Hypergraph Structure Learning [PDF]
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018 In recent years, hypergraph modeling has shown its superiority on correlation formulation among samples and has wide applications in classification, retrieval, and other tasks. In all these works, the performance of hypergraph learning highly depends on the generated hypergraph structure.
Zizhao Zhang 0003 +2 more
openaire +1 more source
Semi-Supervised Classification via Hypergraph Convolutional Extreme Learning Machine
Applied Sciences, 2021 Extreme Learning Machine (ELM) is characterized by simplicity, generalization ability, and computational efficiency. However, previous ELMs fail to consider the inherent high-order relationship among data points, resulting in being powerless on ...
Zhewei Liu +4 more
doaj +1 more source