Manifold Learning
Overview
Manifold learning seeks compact representations of high-dimensional data by modeling it as lying near a lower-dimensional, possibly curved space, enabling visualization, denoising, scientific analysis, and learning with fewer effective degrees of freedom. Common approaches build neighborhood graphs and optimize UMAP- or t-SNE-style embeddings, recover coordinates or operators with spectral and diffusion methods, or use autoencoders with geometric constraints; Riemannian and optimal-transport methods handle structured objects such as covariance matrices and probability distributions. Work increasingly targets properties beyond nearest-neighbor preservation—including density, geodesic distances, topology, tangent spaces, symmetry, and out-of-sample mapping—in settings from images and single-cell data to networks and dynamical systems. A central challenge is balancing local fidelity against global geometry and computational scale, while noise, sparse or anisotropic sampling, and inconsistent evaluation metrics make it difficult to tell when an embedding reflects the underlying manifold.
Latest papers
124 papers10 papers in the last four weeks, down 23% on the four weeks before. 0.1% of all new papers.
Dual-Manifold Geometry Guided Representation Learning: Adaptive Coupling between Kernel and Data Spaces
CosMAP: Contrastive Manifold Approximation and Projection for Dimensionality Reduction of Omics and Genealogical Data
What Carries the Signal in Pathology Foundation-Model Atlases? A Patient-Level Controlled Benchmark in Breast Cancer
Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds
Dual-Domain Manifold Modeling for Hyperspectral Image Fusion
RODR: Riemannian Orthogonally Decoupled Regularization for Disentangled Manifold Representation
Escaping the Euclidean Void: Manifold-Informed Flow Matching for Sequential Recommendation
Data-Driven Diffusion Processes on Differential Forms via the Projected Ambient Connection Laplacian
Group Invariant Spectral Embedding
Intrinsic Green's Learning: Supervised Learning on Manifolds via Inverse PDE
EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning
Physics-Informed Neural Embeddings of PDE Solution Families
On the convergence of graph Laplacians with a symmetric divergence
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
skeleton' of the manifold. However, directly applying LCC suffers from mean regression, pulling latents toward the geometric mean and losing high-frequency details. We therefore extend it to Shell Local Coordinate Coding (Shell-LCC), which models the manifold surface' as an isotropic shell to align with the true high-density region. Experiments demonstrate that our approach improves realism, enhances high-frequency details, reduces over-smoothing artifacts, and alleviates motion blur.