Luigi Di Sotto

I am a Team Lead at Accenture LLMCoE R&D Dept where I work on Generative AI, Machine Learning and Deep Learning. Previously, I worked as a Machine Learning Engineer at AI Technologies @ Gate Centre aggregator (Pisa, Italy), where I worked on Deep Learning for Natural Languange Processing.

I have an MS in Computer Science (AI focus) from University of Pisa, where I was advised by Professor Davide Bacciu and worked on Graph Representation Learning. I have a BS in Computer Science from the same University, where I worked in Professor Marco Vanneschi's lab.

Email  /  GitHub  /  LinkedIn

I'm interested in Deep Learning for Natural Language Processing, Graph Representation Learning and Computer Vision.

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

The paper discusses a pooling mechanism to induce subsampling in graph structured data and introduces it as a component of a graph convolutional neural network. The pooling mechanism builds on the Non-Negative Matrix Factorization (NMF) of a matrix representing node adjacency and node similarity as adaptively obtained through the vertices embedding learned by the model. Such mechanism is applied to obtain an incrementally coarser graph where nodes are adaptively pooled into communities based on the outcomes of the non-negative factorization. The empirical analysis on graph classification benchmarks shows how such coarsening process yields significant improvements in the predictive performance of the model with respect to its non-pooled counterpart.