3 papers
cs.LG2025
Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations
Lorenzo Bini, Stephane Marchand-Maillet
We present LaplaceGNN, a novel self-supervised graph learning framework that bypasses the need for negative sampling by leveraging spectral bootstrapping techniques. Our method int…
cs.LG2025
LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations
Lorenzo Bini, Stephane Marchand-Maillet
Generating high-fidelity and biologically plausible synthetic single-cell RNA sequencing (scRNA-seq) data, especially with conditional control, is challenging due to its high dimen…
cs.LG2025
Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability
Lorenzo Bini, Marco Sorbi, Stephane Marchand-Maillet
Graph Neural Networks (GNNs) have become increasingly popular for effectively modeling graph-structured data, and attention mechanisms have been pivotal in enabling these models to…