Knowledge-based Transfer Learning Explanation

TL;DR

This paper introduces an ontology-based method for human-centric explanation of transfer learning, leveraging knowledge bases to improve interpretability in domain adaptation tasks.

Contribution

It proposes a novel ontology-driven framework that infers explanatory evidence at multiple granularities for transfer learning models.

Findings

Effective explanation of transferability in flight delay prediction

Utilizes external knowledge bases for enhanced interpretability

Demonstrates confidence and availability in real-world data

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.