Full Professor, Technion - Israel Institute of Technology
3 papers at NeurIPS 2025
We introduce an iterative framework to jointly learn hierarchical representations of both samples and features using tree-Wasserstein distance and data-driven Haar wavelet filters.
Learning shared representations almost exculsively from unpaired data.
A novel graph coarsening method that focuses on preserving the inner products between node features and demonstrates superior performance on graph coarsening benchmarks.
