Knowledge-based Transfer Learning Explanation
- Submitting institution
-
University of Aberdeen
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 161111700
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Principles of Knowledge Representation and Reasoning : Proceedings of the Sixteenth International Conference (KR2018)
- First page
- 349
- Volume
- -
- Issue
- -
- ISSN
- 2334-1025
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first work to apply ontology reasoning to improve explainability of transfer learning, published in the leading international conference in the field. Previously work on explaining machine learning assumed that target users had machine learning expertise, missing out non-experts. This work applies ontology reasoning and external knowledge graphs to identify root entailment and root entities for human-centric transfer learning explanation, providing three kinds of human-centric explanation services, including general factors, particular narrators and core contexts. The research led to an IJCAI (2019) paper on improving transfer learning, extending the explanation framework
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
