Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations

by   Matthew Watson, et al.

Deep Learning of neural networks has progressively become more prominent in healthcare with models reaching, or even surpassing, expert accuracy levels. However, these success stories are tainted by concerning reports on the lack of model transparency and bias against some medical conditions or patients' sub-groups. Explainable methods are considered the gateway to alleviate many of these concerns. In this study we demonstrate that the generated explanations are volatile to changes in model training that are perpendicular to the classification task and model structure. This raises further questions about trust in deep learning models for healthcare. Mainly, whether the models capture underlying causal links in the data or just rely on spurious correlations that are made visible via explanation methods. We demonstrate that the output of explainability methods on deep neural networks can vary significantly by changes of hyper-parameters, such as the random seed or how the training set is shuffled. We introduce a measure of explanation consistency which we use to highlight the identified problems on the MIMIC-CXR dataset. We find explanations of identical models but with different training setups have a low consistency: ≈ 33 robust against any orthogonal changes, with explanation consistency at 94 conclude that current trends in model explanation are not sufficient to mitigate the risks of deploying models in real life healthcare applications.



There are no comments yet.


page 4


The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations

Machine learning models in safety-critical settings like healthcare are ...

Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges

Issues regarding explainable AI involve four components: users, laws & r...

Interpretations are useful: penalizing explanations to align neural networks with prior knowledge

For an explanation of a deep learning model to be effective, it must pro...

Explainable Deep Learning for Video Recognition Tasks: A Framework Recommendations

The popularity of Deep Learning for real-world applications is ever-grow...

Exploiting Explanations for Model Inversion Attacks

The successful deployment of artificial intelligence (AI) in many domain...

NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations

Deep neural networks have achieved state-of-the-art performance on vario...

Is Deep Learning an RG Flow?

Although there has been a rapid development of practical applications, t...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.