Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloNetpro2vec: a Graph Embedding Framework for Biomedical Applications
Anno di pubblicazione2021
FormatoElettronico
Autore/iI. Manipur, M. Manzo, I. Granata, M. Giordano, L. Maddalena, and M.R. Guarracino
Affiliazioni autoriICAR-CNR, University of Naples "L'Orientale",ICAR-CNR,ICAR-CNR,ICAR-CNR,ICAR-CNR and University of Cassino and Southern Lazio
Autori CNR e affiliazioni
  • ICHCHA MANIPUR
  • LUCIA MADDALENA
  • MAURIZIO GIORDANO
  • MARIO ROSARIO GUARRACINO
  • ILARIA GRANATA
Lingua/e
  • inglese
AbstractThe ever-increasing importance of structured data in different applications, especially in the biomedical field, has driven the need for reducing its complexity through projections into a more manageable space. The latest methods for learning features on graphs focus mainly on the neighborhood of nodes and edges. Methods capable of providing a representation that looks beyond the single node neighborhood are kernel graphs. However, they produce handcrafted features unaccustomed with a generalized model. To reduce this gap, in this work we propose a neural embedding framework, based on probability distribution representations of graphs, named Netpro2vec. The goal is to look at basic node descriptions other than the degree, such as those induced by the Transition Matrix and Node Distance Distribution. Netpro2vec provides embeddings completely independent from the task and nature of the data. The framework is evaluated on synthetic and various real biomedical network datasets through a comprehensive experimental classification phase and is compared to well-known competitors.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali-
RivistaIEEE/ACM transactions on computational biology and bioinformatics (Print)
Attiva dal 2004
Editore: IEEE Computer Society, - New York, NY
Paese di pubblicazione: Stati Uniti d'America
Lingua: inglese
ISSN: 1545-5963
Titolo chiave: IEEE/ACM transactions on computational biology and bioinformatics (Print)
Titolo proprio: IEEE/ACM transactions on computational biology and bioinformatics (Print)
Titolo abbreviato: IEEE/ACM trans. comput. biol. bioinform. (Print)
Titoli alternativi:
  • Computational biology and bioinformatics (Print)
  • Transactions on computational biology and bioinformatics (Print)
  • IEEE/ACM TCBB (Print)
  • IEEE transactions on computational biology and bioinformatics (Print)
Numero volume della rivista-
Fascicolo della rivista-
DOI10.1109/TCBB.2021.3078089
Verificato da refereeSì: Internazionale
Stato della pubblicazionePreprint
Indicizzazione (in banche dati controllate)-
Parole chiaveGraphs and networks, Classification, Graph embedding, Neural Networks
Link (URL, URI)https://ieeexplore.ieee.org/document/9425591
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione07/05/2021
Note/Altre informazioni-
Strutture CNR
  • ICAR — Istituto di calcolo e reti ad alte prestazioni
Moduli/Attività/Sottoprogetti CNR
  • DIT.AD022.059.001 : LAB-CDS
Progetti Europei-
Allegati
Netpro2vec: a Graph Embedding Framework for Biomedical Applications (documento privato )
Descrizione: CameraReady
Tipo documento: application/pdf