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
Interpreting Deep Learning-Based Networking Systems
Zili Meng,Minhu Wang,Jiasong Bai,Mingwei Xu,Hongzi Mao,Hongxin Hu +5 more
- 30 Jul 2020
TL;DR: The proposed Metis framework provides interpretability for two general categories of networking problems spanning local and global control, where it converts DNN policies to interpretable rule-based controllers and highlight critical components based on analysis over hypergraph.
79
Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations.
Yao Rong,Tobias Leemann,Thai-trang Nguyen,Lisa Fiedler,Peizhu Qian,Vaibhav V. Unhelkar,Tina Seidel,Gjergji Kasneci,Enkelejda Kasneci +8 more
TL;DR: This research shows that XAI is spreading more rapidly in certain application domains, such as recommender systems than in others, but that user evaluations are still rather sparse and incorporate hardly any insights from cognitive or social sciences.
Human-XAI Interaction: A Review and Design Principles for Explanation User Interfaces.
Michael Chromik,Andreas Butz +1 more
- 30 Aug 2021
TL;DR: In this paper, the authors present design principles for interactive explanation user interfaces for ML-based intelligent systems and inform designers of XAI systems about human-centric ways to tailor their explanation user interface to different target audiences and use cases.
78
Trust in 5G and Beyond Networks
TL;DR: A blockchain-based data integrity framework to foster trust in data used by a machine learning pipeline is proposed and pointed out potential emerging trust enablers and research directions.
Explainable Deep Reinforcement Learning: State of the Art and Challenges
TL;DR: A comprehensive review of state of the art methods for explainable deep reinforcement learning methods, categorizing them in classes according to the paradigm they follow, the interpretable models they use, and the surface representation of explanations provided.
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.