Knowledge-based Transfer Learning Explanation
This work addresses the usability gap in explaining transfer learning for decision-making applications, though it is incremental as it builds on existing explanation methods.
The paper tackles the problem of explaining transfer learning decisions by proposing an ontology-based approach that generates human-centric explanations using three types of knowledge-based evidence. The evaluation on US flight data and DBpedia demonstrates confidence and availability in explaining feature representation transferability for flight departure delay forecasting.
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.