Generating Natural Counterfactual Visual Explanations

Zhao, Wenqi; Oyama, Satoshi; Kurihara, Masahito

doi:10.24963/ijcai.2020/742

Cited by 11 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More commonly, humans are engaged to evaluate the effectiveness of methods in generating explanations and their usefulness in real scenarios [72][73][74][75]. Zhao et al [73] employed Generative Adversarial Networks (GANs) to generate counterfactual visual explanations. Crowd workers were recruited to evaluate their effectiveness for classification.…”

Section: Evaluation Of Explainability Methods By Means Of Human Knowl...mentioning

confidence: 99%

The Role of Human Knowledge in Explainable AI

Tocchetti

Brambilla

2022

Data

View full text Add to dashboard Cite

As the performance and complexity of machine learning models have grown significantly over the last years, there has been an increasing need to develop methodologies to describe their behaviour. Such a need has mainly arisen due to the widespread use of black-box models, i.e., high-performing models whose internal logic is challenging to describe and understand. Therefore, the machine learning and AI field is facing a new challenge: making models more explainable through appropriate techniques. The final goal of an explainability method is to faithfully describe the behaviour of a (black-box) model to users who can get a better understanding of its logic, thus increasing the trust and acceptance of the system. Unfortunately, state-of-the-art explainability approaches may not be enough to guarantee the full understandability of explanations from a human perspective. For this reason, human-in-the-loop methods have been widely employed to enhance and/or evaluate explanations of machine learning models. These approaches focus on collecting human knowledge that AI systems can then employ or involving humans to achieve their objectives (e.g., evaluating or improving the system). This article aims to present a literature overview on collecting and employing human knowledge to improve and evaluate the understandability of machine learning models through human-in-the-loop approaches. Furthermore, a discussion on the challenges, state-of-the-art, and future trends in explainability is also provided.

show abstract

Section: Evaluation Of Explainability Methods By Means Of Human Knowl...mentioning

confidence: 99%

The Role of Human Knowledge in Explainable AI

Tocchetti

Brambilla

2022

Data

View full text Add to dashboard Cite

show abstract

“…However, as suggested in [39], the processing time overhead is not significant for all counterfactual explanation applications. In fact, the rapid development of one or more counterfactual explanations is relevant for only certain applications that require an immediate response such as machine teaching, where explanation algorithms need to perform in real-time, and in low-complexity platforms like mobile devices [44].…”

Section: ) Compirsion Of Processing Timementioning

confidence: 99%

Counterfactual Explanation of AI Models Using an Adaptive Genetic Algorithm With Embedded Feature Weights

AlJalaud,

Hosny

2024

IEEE Access

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) is a cutting-edge development in the field of AI that is motivated by the need for transparency of black-box models in AI systems. This transparency enhances user trust, facilitates accountability, and enables better understanding of AI systems decisions especially in critical applications where insights into decision processes are essential. This has increased XAI research interest, aiming to provide techniques for interpreting and understanding the behavior of intelligent models. Counterfactual explanation is a popular technique for model interpretation based on updating a few features such that the outcome of an AI model is changed. By analyzing these counterfactuals, users can gain insights into the critical features or factors that influenced the AI system's decision. However, most counterfactual techniques often lack qualifications such as simplicity, robustness, and coherence. In this research, we propose a novel approach: Adaptive Feature Weight Genetic Explanation (AFWGE), for generating counterfactual explanations of AI models, where a custom genetic algorithm (GA) is employed, incorporating adaptive feature weights to enhance the algorithm's performance. Experimental results on four benchmark datasets show that AFWGE allows for the adaptation of feature weights during the evolutionary process, producing more effective counterfactual explanations with superior proximity, sparsity, plausibility, and actionability. Furthermore, it emphasizes feature weights as reliable indicators of the significance of the model's features, providing valuable insights for interpreting the model. AFWGE not only advances the field of counterfactual explanation generation but also establishes a robust framework for assessing feature importance in machine learning models.

show abstract

“…Singla & Pollack [87] sample instances that vary the prediction probability to navigate through the manifold of the counterfactuals. Zhao [89] proposes using a Star-GAN [146] to generate robust counterfactuals faster. However, it is to be noted that the generative models employed to learn the underlying distribution are, again, black boxes whose working is unknown.…”

Section: Counterfactual Explanationsmentioning

confidence: 99%

Explainable Image Classification: The Journey So Far and the Road Ahead

Kamakshi,

Krishnan

2023

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address the interpretability challenges posed by complex machine learning models. In this survey paper, we provide a comprehensive analysis of existing approaches in the field of XAI, focusing on the tradeoff between model accuracy and interpretability. Motivated by the need to address this tradeoff, we conduct an extensive review of the literature, presenting a multi-view taxonomy that offers a new perspective on XAI methodologies. We analyze various sub-categories of XAI methods, considering their strengths, weaknesses, and practical challenges. Moreover, we explore causal relationships in model explanations and discuss approaches dedicated to explaining cross-domain classifiers. The latter is particularly important in scenarios where training and test data are sampled from different distributions. Drawing insights from our analysis, we propose future research directions, including exploring explainable allied learning paradigms, developing evaluation metrics for both traditionally trained and allied learning-based classifiers, and applying neural architectural search techniques to minimize the accuracy–interpretability tradeoff. This survey paper provides a comprehensive overview of the state-of-the-art in XAI, serving as a valuable resource for researchers and practitioners interested in understanding and advancing the field.

show abstract

Generating Natural Counterfactual Visual Explanations

Cited by 11 publications

References 2 publications

The Role of Human Knowledge in Explainable AI

The Role of Human Knowledge in Explainable AI

Counterfactual Explanation of AI Models Using an Adaptive Genetic Algorithm With Embedded Feature Weights

Explainable Image Classification: The Journey So Far and the Road Ahead

Contact Info

Product

Resources

About