Challenges and Future Directions for Accountable Machine Learning

Agne Zainyte, Wei Pang

Research output: Contribution to journalConference articlepeer-review

5 Downloads (Pure)

Abstract

In recent years, machine learning (ML) algorithms have been applied in many areas such as healthcare, finance and autonomous vehicles. At the same time, there is an increasing need for making ML systems accountable, which would help deal with situations when these systems made wrong decisions or predictions. Currently there exist three major frameworks for Accountable ML: Model Card Toolkit, Datasheets, and FactSheets. However, the greatest limitation of these frameworks is that they are mostly focusing on qualitative information about the machine learning models. In this research, we discuss in detail these three frameworks and future development directions of Accountable ML frameworks; we recommend the implementation of causality, decision provenance, and computational tests for achieving better ML accountability.
Original languageEnglish
Pages (from-to)40-47
Number of pages8
JournalCEUR Workshop Proceedings
Volume2894
Publication statusPublished - 2 Jul 2021
EventSICSA Workshop on eXplainable Artificial Intelligence 2021 - Aberdeen, United Kingdom
Duration: 1 Jun 20211 Jun 2021

Keywords

  • Accountable
  • Artificial
  • Frameworks
  • Intelligence
  • Learning
  • Machine
  • Transparent

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Challenges and Future Directions for Accountable Machine Learning'. Together they form a unique fingerprint.

Cite this