English
Related papers

Related papers: Atlas-based Manifold Representations for Interpret…

200 papers

The importance of explainability in machine learning continues to grow, as both neural-network architectures and the data they model become increasingly complex. Unique challenges arise when a model's input features become high dimensional:…

Machine Learning · Computer Science 2021-12-21 Damien de Mijolla , Christopher Frye , Markus Kunesch , John Mansir , Ilya Feige

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these…

Computer Vision and Pattern Recognition · Computer Science 2019-02-20 Ankita Shukla , Shagun Uppal , Sarthak Bhagat , Saket Anand , Pavan Turaga

Disentanglement is a useful property in representation learning which increases the interpretability of generative models such as Variational autoencoders (VAE), Generative Adversarial Models, and their many variants. Typically in such…

Machine Learning · Computer Science 2022-05-31 Arun Pandey , Michael Fanuel , Joachim Schreurs , Johan A. K. Suykens

Existing symmetry discovery methods predominantly focus on global transformations across the entire system or space, but they fail to consider the symmetries in local neighborhoods. This may result in the reported symmetry group being a…

Machine Learning · Computer Science 2025-06-16 Manu Bhat , Jonghyun Park , Jianke Yang , Nima Dehmamy , Robin Walters , Rose Yu

Diffeomorphic registration frameworks such as Large Deformation Diffeomorphic Metric Mapping (LDDMM) are used in computer graphics and the medical domain for atlas building, statistical latent modeling, and pairwise and groupwise…

Image and Video Processing · Electrical Eng. & Systems 2024-07-31 Sven Dummer , Nicola Strisciuglio , Christoph Brune

Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose…

Machine Learning · Computer Science 2019-10-22 Alexander Genkin , Anirvan M. Sengupta , Dmitri Chklovskii

Graph Neural Networks usually rely on the assumption that the graph topology is available to the network as well as optimal for the downstream task. Latent graph inference allows models to dynamically learn the intrinsic graph structure of…

Machine Learning · Computer Science 2023-06-28 Haitz Sáez de Ocáriz Borde , Anees Kazi , Federico Barbero , Pietro Liò

The generalized partially linear models on Riemannian manifolds are introduced. These models, like ordinary generalized linear models, are a generalization of partially linear models on Riemannian manifolds that allow for response variables…

Methodology · Statistics 2018-03-09 Amelia Simó , M. Victoria Ibáñez , Irene Epifanio , Vicent Gimeno

Interpretability is crucial for building safe, reliable, and controllable language models, yet existing interpretability pipelines remain costly and difficult to scale. Interpreting a new model typically requires training model-specific…

Machine Learning · Computer Science 2026-04-27 Bruno Puri , Jim Berend , Sebastian Lapuschkin , Wojciech Samek

This paper advocates a novel framework for segmenting a dataset in a Riemannian manifold $M$ into clusters lying around low-dimensional submanifolds of $M$. Important examples of $M$, for which the proposed clustering algorithm is…

Machine Learning · Statistics 2014-10-02 Xu Wang , Konstantinos Slavakis , Gilad Lerman

We discover that deep ReLU neural network classifiers can see a low-dimensional Riemannian manifold structure on data. Such structure comes via the local data matrix, a variation of the Fisher information matrix, where the role of the model…

Machine Learning · Computer Science 2021-04-28 Luca Grementieri , Rita Fioresi

The analysis of data sets arising from multiple sensors has drawn significant research attention over the years. Traditional methods, including kernel-based methods, are typically incapable of capturing nonlinear geometric structures. We…

Data Analysis, Statistics and Probability · Physics 2017-08-04 Ronen Talmon , Hau-tieng Wu

Manifold learning methods play a prominent role in nonlinear dimensionality reduction and other tasks involving high-dimensional data sets with low intrinsic dimensionality. Many of these methods are graph-based: they associate a vertex…

Machine Learning · Computer Science 2021-11-16 Joe Kileel , Amit Moscovich , Nathan Zelesko , Amit Singer

Manifold learning is used for dimensionality reduction, with the goal of finding a projection subspace to increase and decrease the inter- and intraclass variances, respectively. However, a bottleneck for subspace learning methods often…

Machine Learning · Computer Science 2021-05-26 Parisa Abdolrahim Poorheravi , Vincent Gaudet

The indicator matrix plays an important role in machine learning, but optimizing it is an NP-hard problem. We propose a new relaxation of the indicator matrix and prove that this relaxation forms a manifold, which we call the Relaxed…

Machine Learning · Computer Science 2025-04-14 Jinghui Yuan , Fangyuan Xie , Feiping Nie , Xuelong Li

Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables and these models use a nonlinear function (generator) to map latent samples into the data space.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Pourya Shamsolmoali , Masoumeh Zareapoor , Huiyu Zhou , Dacheng Tao , Xuelong Li

Intelligent perception and interaction with the world hinges on internal representations that capture its underlying structure (''disentangled'' or ''abstract'' representations). Disentangled representations serve as world models, isolating…

Machine Learning · Computer Science 2025-03-04 Pantelis Vafidis , Aman Bhargava , Antonio Rangel

Symmetric positive definite (SPD) matrices (e.g., covariances, graph Laplacians, etc.) are widely used to model the relationship of spatial or temporal domain. Nevertheless, SPD matrices are theoretically embedded on Riemannian manifolds.…

Computer Vision and Pattern Recognition · Computer Science 2017-10-03 Tong Zhang , Wenming Zheng , Zhen Cui , Chaolong Li

In this paper, we propose RiemannianFlow, a deep generative model that allows robots to learn complex and stable skills evolving on Riemannian manifolds. Examples of Riemannian data in robotics include stiffness (symmetric and positive…

Robotics · Computer Science 2023-09-27 Weitao Wang , Matteo Saveriano , Fares J. Abu-Dakka

Learning-based 3D reconstruction methods have shown impressive results. However, most methods require 3D supervision which is often hard to obtain for real-world datasets. Recently, several works have proposed differentiable rendering…

Computer Vision and Pattern Recognition · Computer Science 2020-03-24 Michael Niemeyer , Lars Mescheder , Michael Oechsle , Andreas Geiger