Interpreting Black-box Machine Learning Models for High Dimensional Datasets Article Swipe

MAKE IMPACT

Md. Rezaul Karim , Md Shajalal , Alex Graß , Till Döhmen , Sisay Adugna Chala , Christian Beecks , Stefan Decker · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2208.13405

Deep neural networks (DNNs) have been shown to outperform traditional machine learning algorithms in a broad variety of application domains due to their effectiveness in modeling complex problems and handling high-dimensional datasets. Many real-life datasets, however, are of increasingly high dimensionality, where a large number of features may be irrelevant for both supervised and unsupervised learning tasks. The inclusion of such features would not only introduce unwanted noise but also increase computational complexity. Furthermore, due to high non-linearity and dependency among a large number of features, DNN models tend to be unavoidably opaque and perceived as black-box methods because of their not well-understood internal functioning. Their algorithmic complexity is often simply beyond the capacities of humans to understand the interplay among myriads of hyperparameters. A well-interpretable model can identify statistically significant features and explain the way they affect the model's outcome. In this paper, we propose an efficient method to improve the interpretability of black-box models for classification tasks in the case of high-dimensional datasets. First, we train a black-box model on a high-dimensional dataset to learn the embeddings on which the classification is performed. To decompose the inner working principles of the black-box model and to identify top-k important features, we employ different probing and perturbing techniques. We then approximate the behavior of the black-box model by means of an interpretable surrogate model on the top-k feature space. Finally, we derive decision rules and local explanations from the surrogate model to explain individual decisions. Our approach outperforms state-of-the-art methods like TabNet and XGboost when tested on different datasets with varying dimensionality between 50 and 20,000 w.r.t metrics and explainability.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2208.13405

PDF

https://arxiv.org/pdf/2208.13405

OA Status

green

Cited By

2

Related Works

10

OpenAlex ID

https://openalex.org/W4293827875

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4293827875

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2208.13405

Digital Object Identifier

Title

Interpreting Black-box Machine Learning Models for High Dimensional Datasets

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-08-29

Full publication date if available

Authors

Md. Rezaul Karim, Md Shajalal, Alex Graß, Till Döhmen, Sisay Adugna Chala, Christian Beecks, Stefan Decker

List of authors in order

Landing page

https://arxiv.org/abs/2208.13405

Publisher landing page

PDF URL

https://arxiv.org/pdf/2208.13405

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2208.13405

Direct OA link when available

Concepts

Interpretability, Machine learning, Black box, Computer science, Artificial intelligence, Curse of dimensionality, Feature (linguistics), Hyperparameter, Deep learning, Linguistics, Philosophy

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2025: 1, 2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload