b'Davide Bacciu'

Distilled Replay: Overcoming Forgetting through Synthetic Samples

Replay strategies are Continual Learning techniques which mitigate catas...
03/29/2021 ∙ by Andrea Rosasco, et al. ∙ 7 ∙ share

read it
Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification

In this work, we study the phenomenon of catastrophic forgetting in the ...
03/22/2021 ∙ by Antonio Carta, et al. ∙ 8 ∙ share

read it
Continual Learning for Recurrent Neural Networks: a Review and Empirical Evaluation

Learning continuously during all model lifetime is fundamental to deploy...
03/12/2021 ∙ by Andrea Cossu, et al. ∙ 16 ∙ share

read it
Graph Mixture Density Networks

We introduce the Graph Mixture Density Network, a new family of machine ...
12/05/2020 ∙ by Federico Errica, et al. ∙ 0 ∙ share

read it
Explaining Deep Graph Networks with Molecular Counterfactuals

We present a novel approach to tackle explainability of deep graph netwo...
11/09/2020 ∙ by Danilo Numeroso, et al. ∙ 0 ∙ share

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

Training RNNs to learn long-term dependencies is difficult due to vanish...
11/05/2020 ∙ by Antonio Carta, et al. ∙ 0 ∙ share

read it
Learning from Non-Binary Constituency Trees via Tensor Decomposition

Processing sentence constituency trees in binarised form is a common and...
11/02/2020 ∙ by Daniele Castellana, et al. ∙ 0 ∙ share

read it
Generative Tomography Reconstruction

We propose an end-to-end differentiable architecture for tomography reco...
10/26/2020 ∙ by Matteo Ronchetti, et al. ∙ 0 ∙ share

read it
FADER: Fast Adversarial Example Rejection

Deep neural networks are vulnerable to adversarial examples, i.e., caref...
10/18/2020 ∙ by Francesco Crecchi, et al. ∙ 1 ∙ share

read it
Perplexity-free Parametric t-SNE

The t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm is a u...
10/03/2020 ∙ by Francesco Crecchi, et al. ∙ 0 ∙ share

read it
ROS-Neuro Integration of Deep Convolutional Autoencoders for EEG Signal Compression in Real-time BCIs

Typical EEG-based BCI applications require the computation of complex fu...
08/31/2020 ∙ by Andrea Valenti, et al. ∙ 0 ∙ share

read it
Accelerating the identification of informative reduced representations of proteins with deep learning for graphs

The limits of molecular dynamics (MD) simulations of macromolecules are ...
07/14/2020 ∙ by Federico Errica, et al. ∙ 0 ∙ share

read it
Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory

The effectiveness of recurrent neural networks can be largely influenced...
06/29/2020 ∙ by Antonio Carta, et al. ∙ 0 ∙ share

read it
Tensor Decompositions in Recursive NeuralNetworks for Tree-Structured Data

The paper introduces two new aggregation functions to encode structural ...
06/18/2020 ∙ by Daniele Castellana, et al. ∙ 0 ∙ share

read it
Generalising Recursive Neural Models by Tensor Decomposition

Most machine learning models for structured data encode the structural k...
06/17/2020 ∙ by Daniele Castellana, et al. ∙ 0 ∙ share

read it
Continual Learning with Gated Incremental Memories for sequential data processing

The ability to learn in dynamic, nonstationary environments without forg...
04/08/2020 ∙ by Andrea Cossu, et al. ∙ 0 ∙ share

read it
A Deep Generative Model for Fragment-Based Molecule Generation

Molecule generation is a challenging open problem in cheminformatics. Cu...
02/28/2020 ∙ by Marco Podda, et al. ∙ 0 ∙ share

read it
Tensor Decompositions in Deep Learning

The paper surveys the topic of tensor decompositions in modern machine l...
02/26/2020 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Edge-based sequential graph generation with recurrent neural networks

Graph generation with Machine Learning is an open problem with applicati...
01/31/2020 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Encoding-based Memory Modules for Recurrent Neural Networks

Learning to solve sequential tasks with recurrent models requires the ab...
01/31/2020 ∙ by Antonio Carta, et al. ∙ 0 ∙ share

read it
Theoretically Expressive and Edge-aware Graph Learning

We propose a new Graph Neural Network that combines recent advancements ...
01/24/2020 ∙ by Federico Errica, et al. ∙ 0 ∙ share

read it
Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders

We address the challenging open problem of learning an effective latent ...
01/15/2020 ∙ by Andrea Valenti, et al. ∙ 0 ∙ share

read it
Learning a Latent Space of Style-Aware Symbolic Music Representations by Adversarial Autoencoders

We address the challenging open problem of learning an effective latent ...
01/15/2020 ∙ by Andrea Valenti, et al. ∙ 0 ∙ share

read it
A Gentle Introduction to Deep Learning for Graphs

The adaptive processing of graph data is a long-standing research topic ...
12/29/2019 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
A Fair Comparison of Graph Neural Networks for Graph Classification

Experimental reproducibility and replicability is a critical topic in ma...
12/20/2019 ∙ by Federico Errica, et al. ∙ 0 ∙ share

read it
A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks

The paper discusses a pooling mechanism to induce subsampling in graph s...
09/07/2019 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Bayesian Tensor Factorisation for Bottom-up Hidden Tree Markov Models

Bottom-Up Hidden Tree Markov Model is a highly expressive model for tree...
05/31/2019 ∙ by Daniele Castellana, et al. ∙ 0 ∙ share

read it
Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI)

Over the years, there has been growing interest in using Machine Learnin...
05/21/2019 ∙ by Elisa Ferrari, et al. ∙ 0 ∙ share

read it
Detecting Adversarial Examples through Nonlinear Dimensionality Reduction

Deep neural networks are vulnerable to adversarial examples, i.e., caref...
04/30/2019 ∙ by Francesco Crecchi, et al. ∙ 16 ∙ share

read it
Deep Tree Transductions - A Short Survey

The paper surveys recent extensions of the Long-Short Term Memory networ...
02/05/2019 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Linear Memory Networks

Recurrent neural networks can learn complex transduction problems that r...
11/08/2018 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Text Summarization as Tree Transduction by Top-Down TreeLSTM

Extractive compression is a challenging natural language processing prob...
09/24/2018 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Learning Tree Distributions by Hidden Markov Models

Hidden tree Markov models allow learning distributions for tree structur...
05/31/2018 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing

We introduce the Contextual Graph Markov Model, an approach combining id...
05/27/2018 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Concentric ESN: Assessing the Effect of Modularity in Cycle Reservoirs

The paper introduces concentric Echo State Network, an approach to desig...
05/23/2018 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Bioinformatics and Medicine in the Era of Deep Learning

Many of the current scientific advances in the life sciences have their ...
02/27/2018 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
Hidden Tree Markov Networks: Deep and Wide Learning for Structured Data

The paper introduces the Hidden Tree Markov Network (HTN), a neuro-proba...
11/21/2017 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it
DropIn: Making Reservoir Computing Neural Networks Robust to Missing Inputs by Dropout

The paper presents a novel, principled approach to train recurrent neura...
05/07/2017 ∙ by Davide Bacciu, et al. ∙ 0 ∙ share

read it

Davide Bacciu

Featured Co-authors