A group-theoretic framework for machine learning in hyperbolic spaces
Embedding the data in hyperbolic spaces can preserve complex relationships in very few dimensions, thus enabling compact models and improving efficiency of machine learning (ML) algorithms. The underlying idea is that hyperbolic representations can prevent the loss of important structural information for certain ubiquitous types of data. However, further advances in hyperbolic ML require more principled mathematical approaches and adequate geometric methods. The present study aims at enhancing mathematical foundations of hyperbolic ML by combining group-theoretic and conformal-geometric arguments with optimization and statistical techniques. Precisely, we introduce the notion of the mean (barycenter) and the novel family of probability distributions on hyperbolic balls. We further propose efficient optimization algorithms for computation of the barycenter and for maximum likelihood estimation. One can build upon basic concepts presented here in order to design more demanding algorithms and implement hyperbolic deep learning pipelines.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Cartan Networks: Group theoretical Hyperbolic Deep Learning
Hyperbolic deep learning leverages the metric properties of hyperbolic spaces to develop efficient and informative embeddings of hierarchical data. Here, we focus on the solvable group structure of hyperbolic spaces, whi…
Deep LearningKernel Methods in Hyperbolic Spaces
Embedding data in hyperbolic spaces has proven beneficial for many advanced machine learning applications such as image classification and word embeddings. However, working in hyperbolic spaces is not without difficu…
Few-Shot Learningimage-classificationImage ClassificationKnowledge Distillation+4Robust Large-Margin Learning in Hyperbolic Space
Recently, there has been a surge of interest in representation learning in hyperbolic spaces, driven by their ability to represent hierarchical data with significantly fewer dimensions than standard Euclidean spaces. How…
Representation LearningHyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections
It has been shown beneficial for many types of data which present an underlying hierarchical structure to be embedded in hyperbolic spaces. Consequently, many tools of machine learning were extended to such spaces, but o…
image-classificationImage ClassificationClustering in hyperbolic balls
The idea of representations of the data in negatively curved manifolds recently attracted a lot of attention and gave a rise to the new research direction named {\it hyperbolic machine learning} (ML). In order to unveil …
Clustering