Use of Metamorphic Relations as Knowledge Carriers to Train Deep Neural Networks

TL;DR

This paper proposes a novel method of using metamorphic relations as knowledge carriers to systematically train deep neural networks, resulting in improved performance over traditional training methods.

Contribution

It introduces the innovative concept of employing metamorphic relations as a systematic training mechanism for DNNs, which is a new approach in the field.

Findings

DNN trained with MRs outperforms without MRs in preliminary tests.

Using MRs as knowledge carriers enhances training effectiveness.

Preliminary results confirm the promise of the proposed approach.

Abstract

Training multiple-layered deep neural networks (DNNs) is difficult. The standard practice of using a large number of samples for training often does not improve the performance of a DNN to a satisfactory level. Thus, a systematic training approach is needed. To address this need, we introduce an innovative approach of using metamorphic relations (MRs) as "knowledge carriers" to train DNNs. Based on the concept of metamorphic testing and MRs (which play the role of a test oracle in software testing), we make use of the notion of metamorphic group of inputs as concrete instances of MRs (which are abstractions of knowledge) to train a DNN in a systematic and effective manner. To verify the viability of our training approach, we have conducted a preliminary experiment to compare the performance of two DNNs: one trained with MRs and the other trained without MRs. We found that the DNN trained with MRs has delivered a better performance, thereby confirming that our approach of using MRs as knowledge carriers to train DNNs is promising. More work and studies, however, are needed to solidify and leverage this approach to generate widespread impact on effective DNN training.