activity
20172025
most citedExplaining Deep Graph Networks with Molecular Counterfactuals

18 citations · 82 across the 27 of their papers we have counts for

collaborators
Showing 2020Show all

19 papers · 1 filter

cs.LG2020

Graph Mixture Density Networks

Federico Errica, Davide Bacciu, Alessio Micheli

We introduce the Graph Mixture Density Networks, a new family of machine learning models that can fit multimodal output distributions conditioned on graphs of arbitrary topology. B…

eess.IV2020

Generative Tomography Reconstruction

Matteo Ronchetti, Davide Bacciu

We propose an end-to-end differentiable architecture for tomography reconstruction that directly maps a noisy sinogram into a denoised reconstruction. Compared to existing approach…

q-bio.QM202018 cited

Explaining Deep Graph Networks with Molecular Counterfactuals

Danilo Numeroso, Davide Bacciu

We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We ge…

cs.LG2020

Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization

Antonio Carta, Alessandro Sperduti, Davide Bacciu

Training RNNs to learn long-term dependencies is difficult due to vanishing gradients. We explore an alternative solution based on explicit memorization using linear autoencoders f…

cs.LG2020

Learning from Non-Binary Constituency Trees via Tensor Decomposition

Daniele Castellana, Davide Bacciu

Processing sentence constituency trees in binarised form is a common and popular approach in literature. However, constituency trees are non-binary by nature. The binarisation proc…

cs.LG2020

FADER: Fast Adversarial Example Rejection

Francesco Crecchi, Marco Melis, Angelo Sotgiu +2

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adv…