2024/02/19 by Paul Krzakala, Krzakala, Paul, Junjie Yang +9 · 1 voice · 1 citation
Computer Science · Neuroscience · #Advanced Graph Neural Networks #Graph Theory and Algorithms #Brain Tumor Detection and Classification
paper · pdf · doi:10.48550/arxiv.2402.12269
We propose Any2graph, a generic framework for end-to-end Supervised Graph Prediction (SGP) i.e. a deep learning model that predicts an entire graph for any kind of input. The framework is built on a novel Optimal Transport loss, the Partially-Masked Fused Gromov-Wasserstein, that exhibits all necessary properties (permutation invariance, differentiability and scalability) and is designed to handle any-sized graphs. Numerical experiments showcase the versatility of the approach that outperform existing competitors on a novel challenging synthetic dataset and a variety of real-world tasks such as map construction from satellite image (Sat2Graph) or molecule prediction from fingerprint (Fingerprint2Graph).