Hypergraph and Uncertain Hypergraph Representation Learning Theory and Methods

With the advent of big data and information age, magnitude various complex networks is growing rapidly. Many real-life situations cannot be portrayed by ordinary networks, while hypergraphs have ability to describe characterize higher order relationships, which attracted extensive attention from academia industry in recent years. Firstly, this paper described development process, application areas, existing review research hypergraphs; secondly, introduced theory briefly; then, compared learning methods graphs three aspects: matrix decomposition, random walk, deep learning; next, structural optimization perspectives: dynamic hypergraphs, hyperedge weight optimization, multimodal hypergraph generation; after that, applicability uncertain models were analyzed based on uncertainty theories: probability theory, fuzzy set, rough set; finally, future directions prospected.