A Survey of Methods for Explaining Black Box Models
Riccardo Guidotti,Anna Monreale,Salvatore Ruggieri,Franco Turini,Fosca Giannotti,Dino Pedreschi +5 more
TL;DR: In this paper, the authors provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box decision support systems, given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work.
read more
Abstract: In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Table 3. Summary of methods for opening and explaining black boxes with respect to the problem faced. 
Fig. 6. Black Box Inspection Problem. 
Table 2. Legend of Table 1. In the following are described the features reported and the abbreviations adopted. ![Fig. 11. Saliency Masks for explanation of deep neural network. (Left) From [108] the elements of the image highlighted. (Right) From [25] the mask and the level of accuracy on the image considering and not considering the learned mask.](/figures/figure11-1-5ao3relmau4d.png)
Fig. 11. Saliency Masks for explanation of deep neural network. (Left) From [108] the elements of the image highlighted. (Right) From [25] the mask and the level of accuracy on the image considering and not considering the learned mask. 
Table 4. Summary of methods for opening and explaining black boxes with respect to the explanator adopted. 
Fig. 9. (Left) Generalizable reverse engineering approach: internal peculiarities of the black box are not exploited to build the comprehensible predictor. (Right) Not Generalizable reverse engineering approach: the comprehensible predictor is the result of a procedure involving internal characteristics of the black box.
![Fig. 11. Saliency Masks for explanation of deep neural network. (Left) From [108] the elements of the image highlighted. (Right) From [25] the mask and the level of accuracy on the image considering and not considering the learned mask.](/figures/figure11-1-5ao3relmau4d.webp)
Citations
Decision Theory Meets Explainable AI
Kary Främling,Kary Främling +1 more
- 09 May 2020
TL;DR: CIU provides a universal and model-agnostic foundation for XAI and extends the notions of importance and utility for the non-linear models of AI systems and notably those produced by Machine Learning methods.
Explainable Deep Neural Network for Design of Electric Motors
TL;DR: This study presents a novel two-step optimization method that incorporates explainable neural networks into topology optimization and is shown to increase the average torque of an interior permanent magnet (IPM) motor and reduce the torque ripple by 79% compared with the original model.
37
Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists
Charles Retzlaff,Alessa Angerschmid,Anna Puspa Amarta Saranti,David Schneeberger,Richard Roettger,Heimo Mueller,Andreas Holzinger +6 more
TL;DR: This study presents a decision support framework for data scientists to choose suitable xAI approaches, comparing six ante-hoc and post-hoc methods through expert interviews, to aid in selecting xAI tools that demystify decision-making and enrich user understanding.
37
Adversarial attacks and defenses in explainable artificial intelligence: A survey
Hubert Baniecki,Przemysław Biecek +1 more
TL;DR: Adversarial attacks on explanations of machine learning models raise concerns about the trustworthiness and security of XAI methods. Recent advances in adversarial machine learning highlight the vulnerabilities of explanation methods and their susceptibility to manipulation and fooling.
37
Requirements Engineering for Artificial Intelligence Systems: A Systematic Mapping Study
TL;DR: In this paper , the authors performed a systematic mapping study to find papers on current RE4AI approaches and identified 43 primary studies and analyzed the existing methodologies, models, tools, and techniques used to specify and model requirements in real-world scenarios.
36
References
I and i
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
38.1K
•Book
C4.5: Programs for Machine Learning
J. Ross Quinlan
- 15 Oct 1992
TL;DR: A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
27.2K
Classification and regression trees
TL;DR: This article gives an introduction to the subject of classification and regression trees by reviewing some widely available algorithms and comparing their capabilities, strengths, and weakness in two examples.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro,Sameer Singh,Carlos Guestrin +2 more
- 13 Aug 2016
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.