MS-IMAP - A Multi-Scale Graph Embedding Approach for Interpretable Manifold Learning

TMLR Paper5424 Authors

Abstract: Deriving meaningful representations from complex, high-dimensional data in unsupervised settings is crucial across diverse machine learning applications. This paper introduces a framework for multi-scale graph network embedding based on spectral graph wavelets that employs a contrastive learning approach. We theoretically show that in Paley-Wiener spaces on combinatorial graphs, the spectral graph wavelets operator provides greater flexibility and control over smoothness compared to the Laplacian operator, motivating our approach. A key advantage of the proposed embedding is its ability to establish a correspondence between the embedding and input feature spaces, enabling the derivation of feature importance. We validate the effectiveness of our graph embedding framework on multiple public datasets across various downstream tasks, including clustering and unsupervised feature importance.

Submission Length: Regular submission (no more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=JMvmG6Vsun

Changes Since Last Submission: We corrected the formatting issues (e.g., font) as instructed and have resubmitted the paper, which was previously desk-rejected due to incorrect formatting.

Assigned Action Editor: ~Yuan_Cao1

Submission Number: 5424