Knowledge-Based Transfer Learning Explanation

Jiaoyan Chen, Freddy Lécué, Jeff Pan, Ian Horrocks, Huajun Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Machine learning explanation can significantly boost machine learning's application in decision making, but the usability of current methods is limited in human-centric explanation, especially for transfer learning, an important machine learning branch that aims at utilizing knowledge from one learning domain (i.e., a pair of dataset and prediction task) to enhance prediction model training in another learning domain. In this paper, we propose an ontology-based approach for human-centric explanation of transfer learning. Three kinds of knowledge-based explanatory evidence, with different granularities, including general factors, particular narrators and core contexts are first proposed and then inferred with both local ontologies and external knowledge bases.The evaluation with US flight data and DBpedia has presented their confidence and availability in explaining the transferability of feature representation in flight departure delay forecasting.
Original languageEnglish
Title of host publicationPrinciples of Knowledge Representation and Reasoning
Subtitle of host publicationProceedings of the Sixteenth International Conference (KR2018)
EditorsMichael Thielscher, Francesca Toni, Frank Wolter
PublisherAAAI Press
Pages349-358
Number of pages10
ISBN (Print)978-1-57735-803-9
Publication statusPublished - 24 Sept 2018
Event16th International Conference on Principles of Knowledge Representation and Reasoning - Tempe, United States
Duration: 27 Oct 20202 Nov 2020
http://reasoning.eas.asu.edu/kr2018/

Publication series

Name
PublisherAAAI Press
ISSN (Print)2334-1025
ISSN (Electronic)2334-1033

Conference

Conference16th International Conference on Principles of Knowledge Representation and Reasoning
Abbreviated titleKR 2018
Country/TerritoryUnited States
CityTempe
Period27/10/202/11/20
Internet address

Keywords / Materials (for Non-textual outputs)

  • Ontology
  • Transfer Learning
  • Description Logic
  • Explanative AI

Fingerprint

Dive into the research topics of 'Knowledge-Based Transfer Learning Explanation'. Together they form a unique fingerprint.

Cite this