Algorithmic Interpretability Across Large Multidimensional Scientific Data Spaces
Keywords:
Interpretability, explainability, high-dimensional data, scientific computing, machine learning, dimensionality reduction, feature attribution, model transparencyAbstract
In contemporary scientific research, large-scale multidimensional data is being generated at unprecedented rates, posing both opportunities and challenges for knowledge discovery. As advanced machine learning and deep learning techniques become integral to analyzing such datasets, the issue of algorithmic interpretability has gained paramount importance. This paper investigates interpretability methods tailored for high-dimensional scientific datasets, analyzes key trade-offs between model performance and transparency, and proposes a conceptual framework for integrating interpretable algorithms into scientific inquiry. We explore domain-specific needs across disciplines such as genomics, astrophysics, and climate science, highlighting the necessity for tailored interpretability approaches.
References
Ribeiro MT, Singh S, Guestrin C. Why Should I Trust You? Explaining the Predictions of Any Classifier. In: Proceedings of the 22nd ACM SIGKDD. ACM. 2016.
Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems. 2017.
Lipton ZC. The mythos of model interpretability. Communications of the ACM. 2018.
Doshi-Velez F, Kim B. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608. 2017.
Montavon G, Samek W, Müller K-R. Methods for interpreting and understanding deep neural networks. Digital Signal Processing. 2018.
Samek W, Montavon G, Lapuschkin S, Anders CJ, Müller K-R. Toward interpretable machine learning: Transparent deep neural networks and beyond. arXiv:1903.10464. 2019.
van der Maaten L, Hinton G. Visualizing data using t-SNE. Journal of Machine Learning Research. 2008.
McInnes L, Healy J, Melville J. UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426. 2018.
Gilpin LH, Bau D, Yuan BZ, Bajwa A, Specter M, Kagal L. Explaining explanations: An overview of interpretability of machine learning. In: IEEE ICMLA. 2018.
Tonekaboni S, Joshi S, McCradden MD, Goldenberg A. What clinicians want: Contextualizing explainable machine learning for clinical end use. In: Machine Learning for Healthcare Conference. 2019.
Caruana R, Lou Y, Gehrke J, Koch P, Sturm M, Elhadad N. Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. In: KDD. 2015.
Biran O, Cotton C. Explanation and justification in machine learning: A survey. In: IJCAI. 2017.
Holzinger A, Biemann C, Pattichis CS, Kell DB. What do we need to build explainable AI systems for the medical domain? Reviews in the Medical Informatics. 2017.
Molnar C. Interpretable Machine Learning. A Guide for Making Black Box Models Explainable. Book. 2019.
Chen J, Song L, Wainwright MJ, Jordan MI. Learning to explain: An information-theoretic perspective on model interpretation. In: ICML. 2018.
Zhang Q, Zhu S-C. Visual interpretability for deep learning: A survey. Frontiers of Information Technology & Electronic Engineering. 2018
