MS-IMAP -- A Multi-Scale Graph Embedding Approach for Interpretable Manifold Learning
This work addresses the need for interpretable manifold learning in machine learning applications, offering a method for feature importance derivation, but it appears incremental as it builds on existing graph embedding techniques.
The paper tackles the problem of deriving meaningful representations from complex, high-dimensional data in unsupervised settings by introducing a multi-scale graph embedding framework based on spectral graph wavelets and contrastive learning, achieving validation on multiple public datasets for tasks like clustering and feature importance.
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.