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

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. An additional 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.

@article{deutsch2025_2406.02778,
  title={ MS-IMAP -- A Multi-Scale Graph Embedding Approach for Interpretable Manifold Learning },
  author={ Shay Deutsch and Lionel Yelibi and Alex Tong Lin and Arjun Ravi Kannan },
  journal={arXiv preprint arXiv:2406.02778},
  year={ 2025 }
}