Hyperbolic Deep Neural Networks: A Survey
It addresses the need for efficient and interpretable representation learning in hierarchical data domains, but is incremental as it synthesizes existing literature.
This survey reviews hyperbolic deep neural networks, which model hierarchical data like knowledge graphs to achieve compact models with improved interpretability compared to Euclidean methods, covering neural components, generalizations, applications, and future directions.
Recently, there has been a rising surge of momentum for deep representation learning in hyperbolic spaces due to theirhigh capacity of modeling data like knowledge graphs or synonym hierarchies, possessing hierarchical structure. We refer to the model as hyperbolic deep neural network in this paper. Such a hyperbolic neural architecture potentially leads to drastically compact model withmuch more physical interpretability than its counterpart in Euclidean space. To stimulate future research, this paper presents acoherent and comprehensive review of the literature around the neural components in the construction of hyperbolic deep neuralnetworks, as well as the generalization of the leading deep approaches to the Hyperbolic space. It also presents current applicationsaround various machine learning tasks on several publicly available datasets, together with insightful observations and identifying openquestions and promising future directions.