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

arXiv: https://arxiv.org/abs/2104.04718 · HTML: https://mlsanity.com/paper/2104.04718/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 29 references that are in the map.
- First posted on arXiv 10 Apr 2021.

## Builds on (most cited first, 4 of 4)

- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models](https://mlsanity.com/paper/2002.02175/) (2020)
- [METTLE: a METamorphic testing approach to assessing and validating unsupervised machine LEarning systems](https://mlsanity.com/paper/1807.10453/) (2018)
- [Metamorphic Security Testing for Web Systems](https://mlsanity.com/paper/1912.05278/) (2019)

## Built on by (most cited first, 1 of 1)

- [Enhancing Deep Learning Model Robustness through Metamorphic Re-Training](https://mlsanity.com/paper/2412.01958/) (2024)

## Abstract (arXiv)

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.