Search Results for author: Nicolò Navarin

Found 13 papers, 6 papers with code

Simple Graph Convolutional Networks

1 code implementation10 Jun 2021 Luca Pasa, Nicolò Navarin, Wolfgang Erb, Alessandro Sperduti

Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago.

Polynomial Graph Convolutional Networks

no code implementations1 Jan 2021 Luca Pasa, Nicolò Navarin, Alessandro Sperduti

In this paper, we propose a different strategy, considering a single graph convolution layer that independently exploits neighbouring nodes at different topological distances, generating decoupled representations for each of them.

Graph Classification

Conditional Constrained Graph Variational Autoencoders for Molecule Design

2 code implementations1 Sep 2020 Davide Rigoni, Nicolò Navarin, Alessandro Sperduti

In recent years, deep generative models for graphs have been used to generate new molecules.

A Systematic Assessment of Deep Learning Models for Molecule Generation

1 code implementation20 Aug 2020 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. drugs).

Drug Discovery

Explainable Predictive Process Monitoring

1 code implementation4 Aug 2020 Riccardo Galanti, Bernat Coma-Puig, Massimiliano de Leoni, Josep Carmona, Nicolò Navarin

Predictive Business Process Monitoring is becoming an essential aid for organizations, providing online operational support of their processes.

Predictive Process Monitoring

On Filter Size in Graph Convolutional Networks

1 code implementation23 Nov 2018 Dinh Van Tran, Nicolò Navarin, Alessandro Sperduti

Recently, many researchers have been focusing on the definition of neural networks for graphs.

Pre-training Graph Neural Networks with Kernels

no code implementations16 Nov 2018 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.

LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instances

1 code implementation10 Nov 2017 Nicolò Navarin, Beatrice Vincenzi, Mirko Polato, Alessandro Sperduti

Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints.

Graph Kernels exploiting Weisfeiler-Lehman Graph Isomorphism Test Extensions

no code implementations22 Sep 2015 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.

A tree-based kernel for graphs with continuous attributes

no code implementations3 Sep 2015 Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti

While existing kernel methods are effective techniques for dealing with graphs having discrete node labels, their adaptation to non-discrete or continuous node attributes has been limited, mainly for computational issues.

Ordered Decompositional DAG Kernels Enhancements

no code implementations13 Jul 2015 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 new state-of-the-art graph kernels.

General Classification

An Empirical Study on Budget-Aware Online Kernel Algorithms for Streams of Graphs

no code implementations8 Jul 2015 Giovanni Da San Martino, Nicolò Navarin, Alessandro Sperduti

It turns out that, when strict memory budget constraints have to be enforced, working in feature space, given the current state of the art on graph kernels, is more than a viable alternative to dual approaches, both in terms of speed and classification performance.

Cannot find the paper you are looking for? You can Submit a new open access paper.