180 citations · 368 across the 30 of their papers we have counts for
20 papers · 1 filter
A Spectral Interpretation of Redundancy in a Graph Reservoir
Anna Bison, Alessandro Sperduti
Reservoir computing has been successfully applied to graphs as a preprocessing method to improve the training efficiency of Graph Neural Networks (GNNs). However, a common issue th…
Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks
Maximilian Muschalik, Fabian Fumagalli, Paolo Frazzetto +5
Albeit the ubiquitous use of Graph Neural Networks (GNNs) in machine learning (ML) prediction tasks involving graph-structured data, their interpretability remains challenging. In…
IFH: a Diffusion Framework for Flexible Design of Graph Generative Models
Samuel Cognolato, Alessandro Sperduti, Luciano Serafini
Graph generative models can be classified into two prominent families: one-shot models, which generate a graph in one go, and sequential models, which generate a graph by successiv…
RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design
Davide Rigoni, Nicolò Navarin, Alessandro Sperduti
Identifying molecules that exhibit some pre-specified properties is a difficult problem to solve. In the last few years, deep generative models have been used for molecule generati…
Simple Graph Convolutional Networks
Luca Pasa, Nicolò Navarin, Wolfgang Erb +1
Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago. Since then, many alternative definitions have been proposed, that tend…
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…
Conditional Constrained Graph Variational Autoencoders for Molecule Design
Davide Rigoni, Nicolò Navarin, Alessandro Sperduti
In recent years, deep generative models for graphs have been used to generate new molecules. These models have produced good results, leading to several proposals in the literature…
A Systematic Assessment of Deep Learning Models for Molecule Generation
Davide Rigoni, Nicolò Navarin, Alessandro Sperduti
In recent years the scientific community has devoted much effort in the development of deep learning models for the generation of new molecules with desirable properties (i.e. drug…
Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory
Antonio Carta, Alessandro Sperduti, Davide Bacciu
The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at differe…
Encoding-based Memory Modules for Recurrent Neural Networks
Antonio Carta, Alessandro Sperduti, Davide Bacciu
Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study th…
Embeddings and Representation Learning for Structured Data
Benjamin Paaßen, Claudio Gallicchio, Alessio Micheli +1
Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vect…
On Filter Size in Graph Convolutional Networks
Dinh Van Tran, Nicolò Navarin, Alessandro Sperduti
Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea p…
Pre-training Graph Neural Networks with Kernels
Nicolò Navarin, Dinh V. Tran, Alessandro Sperduti
Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from…
Linear Memory Networks
Davide Bacciu, Antonio Carta, Alessandro Sperduti
Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memo…
LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instances
Nicolò Navarin, Beatrice Vincenzi, Mirko Polato +1
Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in a…
Graph Kernels exploiting Weisfeiler-Lehman Graph Isomorphism Test Extensions
Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti
In this paper we present a novel graph kernel framework inspired the by the Weisfeiler-Lehman (WL) isomorphism tests. Any WL test comprises a relabelling phase of the nodes based o…
A tree-based kernel for graphs with continuous attributes
Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti
The availability of graph data with node attributes that can be either discrete or real-valued is constantly increasing. While existing kernel methods are effective techniques for…
Ordered Decompositional DAG Kernels Enhancements
Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti
In this paper, we show how the Ordered Decomposition DAGs (ODD) kernel framework, a framework that allows the definition of graph kernels from tree kernels, allows to easily define…
Extending local features with contextual information in graph kernels
Nicolò Navarin, Alessandro Sperduti, Riccardo Tesselli
Graph kernels are usually defined in terms of simpler kernels over local substructures of the original graphs. Different kernels consider different types of substructures. However,…
An Empirical Study on Budget-Aware Online Kernel Algorithms for Streams of Graphs
Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti
Kernel methods are considered an effective technique for on-line learning. Many approaches have been developed for compactly representing the dual solution of a kernel method when…