Francesco Della Santa, Antonio Mastropietro, Sandra Pieraccini, Francesco Vaccarino
{"title":"Edge-Wise Graph-Instructed Neural Networks","authors":"Francesco Della Santa, Antonio Mastropietro, Sandra Pieraccini, Francesco Vaccarino","doi":"arxiv-2409.08023","DOIUrl":null,"url":null,"abstract":"The problem of multi-task regression over graph nodes has been recently\napproached through Graph-Instructed Neural Network (GINN), which is a promising\narchitecture belonging to the subset of message-passing graph neural networks.\nIn this work, we discuss the limitations of the Graph-Instructed (GI) layer,\nand we formalize a novel edge-wise GI (EWGI) layer. We discuss the advantages\nof the EWGI layer and we provide numerical evidence that EWGINNs perform better\nthan GINNs over graph-structured input data with chaotic connectivity, like the\nones inferred from the Erdos-R\\'enyi graph.","PeriodicalId":501162,"journal":{"name":"arXiv - MATH - Numerical Analysis","volume":"10 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - MATH - Numerical Analysis","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08023","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The problem of multi-task regression over graph nodes has been recently
approached through Graph-Instructed Neural Network (GINN), which is a promising
architecture belonging to the subset of message-passing graph neural networks.
In this work, we discuss the limitations of the Graph-Instructed (GI) layer,
and we formalize a novel edge-wise GI (EWGI) layer. We discuss the advantages
of the EWGI layer and we provide numerical evidence that EWGINNs perform better
than GINNs over graph-structured input data with chaotic connectivity, like the
ones inferred from the Erdos-R\'enyi graph.