Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View

By Octavio Loyola-González. 2019

464 citations recorded by the source corpus.

Nowadays, in the international scientific community of machine learning, there exists an enormous discussion about the use of black-box models or explainable models; especially in practical problems. On the one hand, a part of the community defends that black-box models are more accurate than explainable models in some contexts, like image preprocessing. On the other hand, there exist another part of the community alleging that explainable models are better than black-box models because they can obtain comparable results and also they can explain these results in a language close to a human expert by using patterns. In this paper, advantages and weaknesses for each approach are shown; taking into account a state-of-the-art review for both approaches, their practical applications, trends, and future challenges. This paper shows that both approaches are suitable for solving practical problems, but experts in machine learning need to understand the input data, the problem to solve, and the best way for showing the output data before applying a machine learning model. Also, we propose some ideas for fusing both, explainable and black-box, approaches to provide better solutions to experts in real-world domains. Additionally, we show one way to measure the effectiveness of the applied machine learning model by using expert opinions jointly with statistical methods. Throughout this paper, we show the impact of using explainable and black-box models on the security and medical applications.

Subfields: Artificial Intelligence, Management Science and Operations Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Safety, Robustness & Interpretability

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “In particular, this can be done by constraining the neural network thanks to a semantic KB and bias-prone concepts [169] , or by stacking ensembles jointly encompassing white-and black-box models [307] .”
Do Not Trust Additive Explanations (2019, background): “This causes an increasing number of voices to avoid using explanations in high-stakes decisions (Rudin, 2019; Lakkaraju and Bastani, 2020; Loyola-González, 2019).”
Artificial Intelligence and Business Value: a Literature Review (2021, background): “In addition, this move has sparked a general need to provide more transparency of the entire process from data collection to outcome generation (Loyola-Gonzalez, 2019).”
A Deep Blockchain Framework-Enabled Collaborative Intrusion Detection for Protecting IoT and Cloud Networks (2021, background): “Other drawbacks include difﬁculties with the use of pretrained models on data sets that are limited to automatically optimize hyperparameters of models [41].”
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, methodology): “Ensemble learning methods, particularly tree-based methods such as Random Forests and XGBoost are considered white-box models [328] since one can get information about how they made decisions in the form of if-then rules.”