Machine Learning (ML) achievements enabled automatic extraction of actionable information from data in a wide range of decision-making scenarios. This demands for improving both ML technical aspects (e.g., design and automation) and human-related metrics (e.g., fairness, robustness, privacy, and explainability), with performance guarantees at both levels. The aforementioned scenario posed three main challenges: (i) Learning from Complex Data (i.e., sequence, tree, and graph data), (ii) Learning Trustworthily, and (iii) Learning Automatically with Guarantees. The focus of this special session is on addressing one or more of these challenges with the final goal of Learning Trustworthily, Automatically, and with Guarantees from Complex Data.

Complex Data: Learning Trustworthily, Automatically, and with Guarantees

Biggio B.;
2021-01-01

Abstract

Machine Learning (ML) achievements enabled automatic extraction of actionable information from data in a wide range of decision-making scenarios. This demands for improving both ML technical aspects (e.g., design and automation) and human-related metrics (e.g., fairness, robustness, privacy, and explainability), with performance guarantees at both levels. The aforementioned scenario posed three main challenges: (i) Learning from Complex Data (i.e., sequence, tree, and graph data), (ii) Learning Trustworthily, and (iii) Learning Automatically with Guarantees. The focus of this special session is on addressing one or more of these challenges with the final goal of Learning Trustworthily, Automatically, and with Guarantees from Complex Data.
2021
9782875870810
Automatic extraction; Complex data; Decisions makings; Learning achievement; Machine-learning; Performance guarantees; Sequence data; Sequence trees; Technical aspects; Tree data
File in questo prodotto:
File Dimensione Formato  
ES2021-6.pdf

Solo gestori archivio

Descrizione: paper online
Tipologia: versione editoriale (VoR)
Dimensione 1.44 MB
Formato Adobe PDF
1.44 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/349283
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact