Metric Learning On Manifolds

Abstract

Recent literature has shown that symbolic data, such as text and graphs, is often better represented by points on a curved manifold, rather than in Euclidean space. However, geometrical operations on manifolds are generally more complicated than in Euclidean space, and thus many techniques for processing and analysis taken for granted in Euclidean space are difficult on manifolds. A priori, it is not obvious how we may generalize such methods to manifolds. We consider specifically the problem of distance metric learning, and present a framework that solves it on a large class of manifolds, such that similar data are located in closer proximity with respect to the manifold distance function. In particular, we extend the existing metric learning algorithms, and derive the corresponding sample complexity rates for the case of manifolds. Additionally, we demonstrate an improvement of performance in \(k\)-means clustering and \(k\)-nearest neighbor classification on real-world complex netwo

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyaalto2019metric

Related papers

• Piecewise-linear Manifolds For Deep Metric Learning (2024)0.00
• Quadric Hypersurface Intersection For Manifold Learning In Feature Space (2021)0.00
• Mining On Manifolds: Metric Learning Without Labels (2018)14.31
• Computationally Efficient Learning Of Statistical Manifolds (2021)0.00
• Cross-modal Manifold Learning For Cross-modal Retrieval (2016)0.00
• A Graph-based Approach To Derive The Geodesic Distance On Statistical Manifolds: Application To Multimedia Information Retrieval (2021)2.26
• Neural Bregman Divergences For Distance Learning (2022)0.00
• An Application Of Manifold Learning In Global Shape Descriptors (2019)5.84