Generative Counterfactual Introspection for Explainable Deep Learning

Liu, Shusen; Kailkhura, Bhavya; Loveland, Donald W.; Han, Yong

doi:10.1109/globalsip45357.2019.8969491

Cited by 63 publications

(40 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This generative framework has been adopted by several recent studies [366,367] mainly as an attribution method to relate a particular output of a Deep Learning model to their input variables. Another interesting research direction is the use of generative models for the creation of counterfactuals, i.e., modifications to the input data that could eventually alter the original prediction of the model [368]. Counterfactual prototypes help the user understand the performance boundaries of the model under consideration for his/her improved trust and informed criticism.…”

Section: Explanations For Ai Security: Xai and Adversarial Machine Lementioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

show abstract

Section: Explanations For Ai Security: Xai and Adversarial Machine Lementioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Indeed, contfactuals are particularly suitable for informing the end-user why a given data example is assigned a particular class label. Thus, the outlined classification-oriented frameworks are evaluated on classifiers based on logistic regression [55], [136], [153], [158], decision trees [46], [80], [122], [140], [150], [155], [159], gradient boosted decision trees [147], support vector machines [131], [138], [146], random forests [81], [86], [142]- [144], neural networks [6], [48], [49], [91], [129], [130], [133], [135], [139], [141], [145], [148], [151], or combinations of these [100], [105], [134], [152], [154], [160]. In three studies [67], [128], [137], the classifiers used in the experiments are not specified.…”

Section: ) Ai Problemmentioning

confidence: 99%

“…For instance, Gomez et al visualize the generated explanations in the form of bar plots combining them with explicitly stated numerical values [138]. Alternatively, Liu et al combine feature importance bar plots with visual input and output [145]. While a textual explanation summarizes the degree of importance of the selected features, a visual explanation may present contextual in-method metrics that justify the classifier's reasoning [129].…”

Section: ) Output Representationmentioning

confidence: 99%

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

et al. 2021

View full text Add to dashboard Cite

A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanations justify why the output of the algorithms is not any different and how it could be changed, respectively. It is of crucial importance to bridge the gap between theoretical approaches to contrastive and counterfactual explanation and the corresponding computational frameworks. In this work we conduct a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study. We first examine theoretical foundations of contrastive and counterfactual accounts of explanation. Then, we report the state-of-the-art computational frameworks for contrastive and counterfactual explanation generation. In addition, we analyze how grounded such frameworks are on the insights from the inspected theoretical approaches. As a result, we highlight a variety of properties of the approaches under study and reveal a number of shortcomings thereof. Moreover, we define a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.

show abstract

“…Therefore, we propose to predict and ground attributes for both clean and perturbed images to provide visual as well as attribute-based interpretations. Counterfactual explanations Explanations which consider counterdecisions or counteroutcomes are known as counterfactual explanations [25]. An interesting approach in a recent paper [13] proposes to generate counterfactual expla-Fig.…”

Section: Explainabilitymentioning

confidence: 99%

Counterfactual attribute-based visual explanations for classification

Gulshad

Smeulders

2021

Int J Multimed Info Retr

View full text Add to dashboard Cite

In this paper, our aim is to provide human understandable intuitive factual and counterfactual explanations for the decisions of neural networks. Humans tend to reinforce their decisions by providing attributes and counterattributes. Hence, in this work, we utilize attributes as well as examples to provide explanations. In order to provide counterexplanations we make use of directed perturbations to arrive at the counterclass attribute values in doing so, we explain what is present and what is absent in the original image. We evaluate our method when images are misclassified into closer counterclasses as well as when misclassified into completely different counterclasses. We conducted experiments on both finegrained as well as coarsegrained datasets. We verified our attribute-based explanations method both quantitatively and qualitatively and showed that attributes provide discriminating and human understandable explanations for both standard as well as robust networks.

show abstract

Generative Counterfactual Introspection for Explainable Deep Learning

Cited by 63 publications

References 23 publications

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

Counterfactual attribute-based visual explanations for classification

Contact Info

Product

Resources

About