loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Author: Lars Fluri

Affiliation: Department of Computational Economics and Finance, Department of Management Accounting University of Basel, Peter Merian-Weg 6, Basel, Switzerland

Keyword(s): XAI, XML, SHAP, Shapley Value Sampling, DeepLIFT, LIME, Integrated Gradients, GradientSHAP, Deep Learning, Neural Networks, Finance.

Abstract: This paper evaluates the effectiveness of different feature importance algorithms employed on a neural network, focused on target prediction tasks with varying data complexities. The study reveals that the feature importance algorithms excel with data featuring minimal correlation between the attributes. However, their determination considerably decreases with escalating levels of correlation, while the inclusion of irrelevant features has minimal impact on determination. In terms of predictive power, DeepLIFT surpasses other methods for most data cases, but falls short in total infidelity. For more complex cases, Shapley Value Sampling outperforms DeepLIFT. In an empirical application, Integrated Gradients and DeepLIFT demonstrate lower sensitivity and lower infidelity, respectively. this paper highlights interesting dynamics between predictive power and fidelity in feature importance algorithms and offers key insights for their application in complex data scenarios.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.139.64.39

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Fluri, L. (2024). Feature Importance for Deep Neural Networks: A Comparison of Predictive Power, Infidelity and Sensitivity. In Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - EXPLAINS; ISBN 978-989-758-720-7, SciTePress, pages 15-26. DOI: 10.5220/0012903300003886

@conference{explains24,
author={Lars Fluri},
title={Feature Importance for Deep Neural Networks: A Comparison of Predictive Power, Infidelity and Sensitivity},
booktitle={Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - EXPLAINS},
year={2024},
pages={15-26},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012903300003886},
isbn={978-989-758-720-7},
}

TY - CONF

JO - Proceedings of the 1st International Conference on Explainable AI for Neural and Symbolic Methods - EXPLAINS
TI - Feature Importance for Deep Neural Networks: A Comparison of Predictive Power, Infidelity and Sensitivity
SN - 978-989-758-720-7
AU - Fluri, L.
PY - 2024
SP - 15
EP - 26
DO - 10.5220/0012903300003886
PB - SciTePress