18 citations · 82 across the 27 of their papers we have counts for
19 papers · 1 filter
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…
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…
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…
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…
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…
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…