b'Davide Bacciu'

research

∙ 09/15/2023

Constraint-Free Structure Learning with Smooth Acyclic Orientations

The structure learning problem consists of fitting data generated by a D...

0 Riccardo Massidda, et al. ∙

research

∙ 08/17/2023

Modeling Edge Features with Deep Bayesian Graph Networks

We propose an extension of the Contextual Graph Markov Model, a deep and...

0 Daniele Atzeni, et al. ∙

research

∙ 07/27/2023

Graph-based Polyphonic Multitrack Music Generation

Graphs can be leveraged to model polyphonic multitrack symbolic music, w...

0 Emanuele Cosenza, et al. ∙

research

∙ 07/12/2023

Deep learning for dynamic graphs: models and benchmarks

Recent progress in research on Deep Graph Networks (DGNs) has led to a m...

0 Alessio Gravina, et al. ∙

research

∙ 06/19/2023

Partial Hypernetworks for Continual Learning

Hypernetworks mitigate forgetting in continual learning (CL) by generati...

0 Hamed Hemati, et al. ∙

research

∙ 05/18/2023

Neural Algorithmic Reasoning for Combinatorial Optimisation

Solving NP-hard/complete combinatorial problems with neural networks is ...

0 Dobrik Georgiev, et al. ∙

research

∙ 03/28/2023

Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning

Distributed learning on the edge often comprises self-centered devices (...

0 Antonio Carta, et al. ∙

research

∙ 02/09/2023

Dual Algorithmic Reasoning

Neural Algorithmic Reasoning is an emerging area of machine learning whi...

0 Danilo Numeroso, et al. ∙

research

∙ 01/26/2023

Class-Incremental Learning with Repetition

Real-world data streams naturally include the repetition of previous con...

13 Hamed Hemati, et al. ∙

research

∙ 01/23/2023

ECGAN: Self-supervised generative adversarial network for electrocardiography

High-quality synthetic data can support the development of effective pre...

0 Lorenzo Simone, et al. ∙

research

∙ 11/22/2022

Causal Abstraction with Soft Interventions

Causal abstraction provides a theory describing how several causal model...

0 Riccardo Massidda, et al. ∙

research

∙ 10/18/2022

Anti-Symmetric DGN: a stable architecture for Deep Graph Networks

Deep Graph Networks (DGNs) currently dominate the research landscape of ...

3 Alessio Gravina, et al. ∙

research

∙ 10/05/2022

ChemAlgebra: Algebraic Reasoning on Chemical Reactions

While showing impressive performance on various kinds of learning tasks,...

0 Andrea Valenti, et al. ∙

research

∙ 09/12/2022

Modular Representations for Weak Disentanglement

The recently introduced weakly disentangled representations proposed to ...

0 Andrea Valenti, et al. ∙

research

∙ 08/06/2022

Graph Pooling with Maximum-Weight k-Independent Sets

Graph reductions are fundamental when dealing with large scale networks ...

0 Davide Bacciu, et al. ∙

research

∙ 07/04/2022

It's all About Consistency: A Study on Memory Composition for Replay-Based Methods in Continual Learning

Continual Learning methods strive to mitigate Catastrophic Forgetting (C...

2 Julio Hurtado, et al. ∙

research

∙ 07/01/2022

Studying the impact of magnitude pruning on contrastive learning methods

We study the impact of different pruning techniques on the representatio...

12 Francesco Corti, et al. ∙

research

∙ 06/29/2022

Continual Learning for Human State Monitoring

Continual Learning (CL) on time series data represents a promising but u...

0 Federico Matteoni, et al. ∙

research

∙ 06/23/2022

Sample Condensation in Online Continual Learning

Online Continual learning is a challenging learning scenario where the m...

10 Mattia Sangermano, et al. ∙

research

∙ 06/14/2022

Continual-Learning-as-a-Service (CLaaS): On-Demand Efficient Adaptation of Predictive Models

Predictive machine learning models nowadays are often updated in a state...

0 Rudy Semola, et al. ∙

research

∙ 05/25/2022

Federated Adaptation of Reservoirs via Intrinsic Plasticity

We propose a novel algorithm for performing federated learning with Echo...

0 Valerio De Caro, et al. ∙

research

∙ 05/20/2022

Leveraging Relational Information for Learning Weakly Disentangled Representations

Disentanglement is a difficult property to enforce in neural representat...

0 Andrea Valenti, et al. ∙

research

∙ 05/19/2022

Continual Pre-Training Mitigates Forgetting in Language and Vision

Pre-trained models are nowadays a fundamental component of machine learn...

18 Andrea Cossu, et al. ∙

research

∙ 05/18/2022

Deep Features for CBIR with Scarce Data using Hebbian Learning

Features extracted from Deep Neural Networks (DNNs) have proven to be ve...

27 Gabriele Lagani, et al. ∙

research

∙ 04/11/2022

Learning heuristics for A*

Path finding in graphs is one of the most studied classes of problems in...

0 Danilo Numeroso, et al. ∙

research

∙ 03/19/2022

Practical Recommendations for Replay-based Continual Learning Methods

Continual Learning requires the model to learn from a stream of dynamic,...

4 Gabriele Merlin, et al. ∙

research

∙ 02/03/2022

AI-as-a-Service Toolkit for Human-Centered Intelligence in Autonomous Driving

This paper presents a proof-of-concept implementation of the AI-as-a-Ser...

11 Valerio De Caro, et al. ∙

research

∙ 12/13/2021

Ex-Model: Continual Learning from a Stream of Trained Models

Learning continually from non-stationary data streams is a challenging r...

10 Antonio Carta, et al. ∙

research

∙ 12/06/2021

Is Class-Incremental Enough for Continual Learning?

The ability of a model to learn continually can be empirically assessed ...

2 Andrea Cossu, et al. ∙

research

∙ 11/03/2021

Predictive Auto-scaling with OpenStack Monasca

Cloud auto-scaling mechanisms are typically based on reactive automation...

0 Giacomo Lanciano, et al. ∙

research

∙ 10/04/2021

Inductive learning for product assortment graph completion

Global retailers have assortments that contain hundreds of thousands of ...

0 Haris Dukic, et al. ∙

research

∙ 07/18/2021

GraphGen-Redux: a Fast and Lightweight Recurrent Model for labeled Graph Generation

The problem of labeled graph generation is gaining attention in the Deep...

16 Marco Podda, et al. ∙

research

∙ 07/14/2021

TEACHING – Trustworthy autonomous cyber-physical applications through human-centred intelligence

This paper discusses the perspective of the H2020 TEACHING project on th...

14 Davide Bacciu, et al. ∙

research

∙ 07/08/2021

Calliope – A Polyphonic Music Transformer

The polyphonic nature of music makes the application of deep learning to...

0 Andrea Valenti, et al. ∙

research

∙ 05/17/2021

Continual Learning with Echo State Networks

Continual Learning (CL) refers to a learning setup where data is non sta...

39 Andrea Cossu, et al. ∙

research

∙ 05/14/2021

A causal learning framework for the analysis and interpretation of COVID-19 clinical data

We present a workflow for clinical data analysis that relies on Bayesian...

0 Elisa Ferrari, et al. ∙

research

∙ 05/13/2021

Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss

Resilience to class imbalance and confounding biases, together with the ...

0 Elisa Ferrari, et al. ∙

research

∙ 04/16/2021

MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks

Explainable AI (XAI) is a research area whose objective is to increase t...

0 Danilo Numeroso, et al. ∙

research

∙ 03/29/2021

Distilled Replay: Overcoming Forgetting through Synthetic Samples

Replay strategies are Continual Learning techniques which mitigate catas...

7 Andrea Rosasco, et al. ∙

research

∙ 03/22/2021

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

In this work, we study the phenomenon of catastrophic forgetting in the ...

8 Antonio Carta, et al. ∙

research

∙ 03/12/2021

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

Learning continuously during all model lifetime is fundamental to deploy...

16 Andrea Cossu, et al. ∙

research

∙ 12/05/2020

Graph Mixture Density Networks

We introduce the Graph Mixture Density Network, a new family of machine ...

0 Federico Errica, et al. ∙

research

∙ 11/09/2020

Explaining Deep Graph Networks with Molecular Counterfactuals

We present a novel approach to tackle explainability of deep graph netwo...

0 Danilo Numeroso, et al. ∙

research

∙ 11/05/2020

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

Training RNNs to learn long-term dependencies is difficult due to vanish...

0 Antonio Carta, et al. ∙

research

∙ 11/02/2020

Learning from Non-Binary Constituency Trees via Tensor Decomposition

Processing sentence constituency trees in binarised form is a common and...

0 Daniele Castellana, et al. ∙

research

∙ 10/26/2020

Generative Tomography Reconstruction

We propose an end-to-end differentiable architecture for tomography reco...

0 Matteo Ronchetti, et al. ∙

research

∙ 10/18/2020

FADER: Fast Adversarial Example Rejection

Deep neural networks are vulnerable to adversarial examples, i.e., caref...

1 Francesco Crecchi, et al. ∙

research

∙ 10/03/2020

Perplexity-free Parametric t-SNE

The t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm is a u...

0 Francesco Crecchi, et al. ∙

research

∙ 08/31/2020

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...

0 Andrea Valenti, et al. ∙

research

∙ 07/14/2020

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

The limits of molecular dynamics (MD) simulations of macromolecules are ...

0 Federico Errica, et al. ∙

Davide Bacciu

Featured Co-authors