
Distilled Replay: Overcoming Forgetting through Synthetic Samples
Replay strategies are Continual Learning techniques which mitigate catas...
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 ...
read it

Continual Learning for Recurrent Neural Networks: a Review and Empirical Evaluation
Learning continuously during all model lifetime is fundamental to deploy...
read it

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

Explaining Deep Graph Networks with Molecular Counterfactuals
We present a novel approach to tackle explainability of deep graph netwo...
read it

ShortTerm Memory Optimization in Recurrent Neural Networks by Autoencoderbased Initialization
Training RNNs to learn longterm dependencies is difficult due to vanish...
read it

Learning from NonBinary Constituency Trees via Tensor Decomposition
Processing sentence constituency trees in binarised form is a common and...
read it

Generative Tomography Reconstruction
We propose an endtoend differentiable architecture for tomography reco...
read it

FADER: Fast Adversarial Example Rejection
Deep neural networks are vulnerable to adversarial examples, i.e., caref...
read it

Perplexityfree Parametric tSNE
The tdistributed Stochastic Neighbor Embedding (tSNE) algorithm is a u...
read it

ROSNeuro Integration of Deep Convolutional Autoencoders for EEG Signal Compression in Realtime BCIs
Typical EEGbased BCI applications require the computation of complex fu...
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 ...
read it

Incremental Training of a Recurrent Neural Network Exploiting a MultiScale Dynamic Memory
The effectiveness of recurrent neural networks can be largely influenced...
read it

Tensor Decompositions in Recursive NeuralNetworks for TreeStructured Data
The paper introduces two new aggregation functions to encode structural ...
read it

Generalising Recursive Neural Models by Tensor Decomposition
Most machine learning models for structured data encode the structural k...
read it

Continual Learning with Gated Incremental Memories for sequential data processing
The ability to learn in dynamic, nonstationary environments without forg...
read it

A Deep Generative Model for FragmentBased Molecule Generation
Molecule generation is a challenging open problem in cheminformatics. Cu...
read it

Tensor Decompositions in Deep Learning
The paper surveys the topic of tensor decompositions in modern machine l...
read it

Edgebased sequential graph generation with recurrent neural networks
Graph generation with Machine Learning is an open problem with applicati...
read it

Encodingbased Memory Modules for Recurrent Neural Networks
Learning to solve sequential tasks with recurrent models requires the ab...
read it

Theoretically Expressive and Edgeaware Graph Learning
We propose a new Graph Neural Network that combines recent advancements ...
read it

Learning StyleAware Symbolic Music Representations by Adversarial Autoencoders
We address the challenging open problem of learning an effective latent ...
read it

Learning a Latent Space of StyleAware Symbolic Music Representations by Adversarial Autoencoders
We address the challenging open problem of learning an effective latent ...
read it

A Gentle Introduction to Deep Learning for Graphs
The adaptive processing of graph data is a longstanding research topic ...
read it

A Fair Comparison of Graph Neural Networks for Graph Classification
Experimental reproducibility and replicability is a critical topic in ma...
read it

A NonNegative Factorization approach to node pooling in Graph Convolutional Neural Networks
The paper discusses a pooling mechanism to induce subsampling in graph s...
read it

Bayesian Tensor Factorisation for Bottomup Hidden Tree Markov Models
BottomUp Hidden Tree Markov Model is a highly expressive model for tree...
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...
read it

Detecting Adversarial Examples through Nonlinear Dimensionality Reduction
Deep neural networks are vulnerable to adversarial examples, i.e., caref...
read it

Deep Tree Transductions  A Short Survey
The paper surveys recent extensions of the LongShort Term Memory networ...
read it

Linear Memory Networks
Recurrent neural networks can learn complex transduction problems that r...
read it

Text Summarization as Tree Transduction by TopDown TreeLSTM
Extractive compression is a challenging natural language processing prob...
read it

Learning Tree Distributions by Hidden Markov Models
Hidden tree Markov models allow learning distributions for tree structur...
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...
read it

Concentric ESN: Assessing the Effect of Modularity in Cycle Reservoirs
The paper introduces concentric Echo State Network, an approach to desig...
read it

Bioinformatics and Medicine in the Era of Deep Learning
Many of the current scientific advances in the life sciences have their ...
read it

Hidden Tree Markov Networks: Deep and Wide Learning for Structured Data
The paper introduces the Hidden Tree Markov Network (HTN), a neuroproba...
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...
read it
Davide Bacciu
is this you? claim profile