Augmenting Transfer Learning with Semantic Reasoning

TL;DR

This paper introduces a framework that enhances transfer learning in the semantic Web by using semantic measurements and embeddings, improving performance in real-world forecasting tasks.

Contribution

It presents a novel framework that integrates semantic reasoning with transfer learning, addressing when and what to transfer for better accuracy.

Findings

Robust performance in bus delay forecasting

Effective in air quality forecasting

Improves transfer learning with semantic information

Abstract

Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings. We further present a general framework that integrates the above measurements and embeddings with existing transfer learning algorithms for higher performance. It has demonstrated to be robust in two real-world applications: bus delay forecasting and air quality forecasting.