3 papers
cs.LG2024
Sparse Implementation of Versatile Graph-Informed Layers
Francesco Della Santa
Graph Neural Networks (GNNs) have emerged as effective tools for learning tasks on graph-structured data. Recently, Graph-Informed (GI) layers were introduced to address regression…
cs.LG2024
Graph-Instructed Neural Networks for Sparse Grid-Based Discontinuity Detectors
Francesco Della Santa, Sandra Pieraccini
In this paper, we present a novel approach for detecting the discontinuity interfaces of a discontinuous function. This approach leverages Graph-Instructed Neural Networks (GINNs)…
cs.LG2023
ATE-SG: Alternate Through the Epochs Stochastic Gradient for Multi-Task Neural Networks
Stefania Bellavia, Francesco Della Santa, Alessandra Papini
This paper introduces novel alternate training procedures for hard-parameter sharing Multi-Task Neural Networks (MTNNs). Traditional MTNN training faces challenges in managing conf…