CVFeb 21, 2018

Angle constrained path to cluster multiple manifolds

arXiv:1802.07416v11 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of manifold clustering in machine learning, particularly for datasets with intersections, but it is incremental as it builds on prior work like Isomap.

The paper tackles the problem of clustering data points from multiple intersecting manifolds by introducing an angle-constrained path algorithm that prevents connections between different manifolds, and it performs comparably to existing methods on simulated and real datasets.

In this paper, we propose a method to cluster multiple intersected manifolds. The algorithm chooses several landmark nodes randomly and then checks whether there is an angle constrained path between each landmark node and every other node in the neighborhood graph. When the points lie on different manifolds with intersection they should not be connected using a smooth path, thus the angle constraint is used to prevent connecting points from one cluster to another one. The resulting algorithm is implemented as a simple variation of Dijkstras algorithm used in Isomap. However, Isomap was specifically designed for dimensionality reduction in the single-manifold setting, and in particular, can-not handle intersections. Our method is simpler than the previous proposals in the literature and performs comparably to the best methods, both on simulated and some real datasets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes