4 papers · 1 filter
Graph Matching Relaxations and Amortization for Supervised Graph Prediction
Federico Méndez, Paul Krzakala, Gabriel Melo +3
End-to-end Supervised Graph Prediction (SGP) requires a permutation-invariant loss to compare predicted and target graphs with arbitrary node orderings. Such losses typically invol…
MSAlign: Aligning Molecule and Mass Spectra Representations for Metabolite Identification
Paul Krzakala, Gabriel Melo, Camille Lançon +4
Accurately identifying metabolites i.e. small molecules from mass spectrometry data remains a core challenge in metabolomics, with broad applications in drug discovery, environment…
Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation
Auguste de Lambilly, Vladimir Baturin, David Portehault +4
Generative diffusion models have emerged as powerful tools for the discovery of inorganic crystal structures, yet steering their sampling process toward user-defined physical and c…
Conformal Graph Prediction with Z-Gromov-Wasserstein Distances
Gabriel Melo, Thibaut de Saivre, Anna Calissano +1
Supervised graph prediction addresses regression problems where the outputs are structured graphs. Although several approaches exist for graph-valued prediction, principled uncerta…