How Should Artificial Intelligence Explain Itself? Understanding Preferences for Explanations Generated by XAI Algorithms

Ramon, Yanou; Vermeire, Tom; Martens, David; Evgeniou, Theodoros; Toubia, Olivier

doi:10.2139/ssrn.3877426

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In spite of the above, studies related to XAI have shown that user preferences on interpretability are context and requirements dependent, and that users may even prefer more complex explanations (Ramon et al, 2021;Fürnkranz et al, 2020). Other recent examples of user studies are Byrne (2019) and Dodge et al (2019), with the latter explicitly concluding that there is no one-size-fitsall approach to explaining, but that the usefulness of explanations depends on user profiles and expertise.…”

Section: User Interpretabilitymentioning

confidence: 99%

“…Versatility: NICE has the ability to optimize for multiple counterfactual properties. Research has shown that the preference for counterfactual properties is context-dependant (Ramon et al, 2021;Fürnkranz et al, 2020). An algorithm that can provide multiple counterfactual explanations with different characteristics allows for personalized explanations per user.…”

Section: Introduction 1the Need For Explainabilitymentioning

confidence: 99%

See 1 more Smart Citation

NICE: an algorithm for nearest instance counterfactual explanations

Brughmans

Leyman

Martens

2023

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

In this paper we propose a new algorithm, named NICE, to generate counterfactual explanations for tabular data that specifically takes into account algorithmic requirements that often emerge in real-life deployments: (1) the ability to provide an explanation for all predictions, (2) being able to handle any classification model (also non-differentiable ones), (3) being efficient in run time, and (4) providing multiple counterfactual explanations with different characteristics. More specifically, our approach exploits information from a nearest unlike neighbor to speed up the search process, by iteratively introducing feature values from this neighbor in the instance to be explained. We propose four versions of NICE, one without optimization and, three which optimize the explanations for one of the following properties: sparsity, proximity or plausibility. An extensive empirical comparison on 40 datasets shows that our algorithm outperforms the current state-of-the-art in terms of these criteria. Our analyses show a trade-off between on the one hand plausibility and on the other hand proximity or sparsity, with our different optimization methods offering users the choice to select the types of counterfactuals that they prefer. An open-source implementation of NICE can be found at https://github.com/ADMAntwerp/NICE.

show abstract

Section: User Interpretabilitymentioning

confidence: 99%

Section: Introduction 1the Need For Explainabilitymentioning

confidence: 99%

NICE: an algorithm for nearest instance counterfactual explanations

Brughmans

Leyman

Martens

2023

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

show abstract

“…XAI is mainly used for deep learning models, which are black-box models. XAI is used for many applications such as multimedia computing [9], computer vision [20,29], business intelligence [36] and Twitter analysis [14]. In this research work, we focus on applications based on Twitter analytics.…”

Section: Introductionmentioning

confidence: 99%

An Efficient and Accurate GPU-based Deep Learning Model for Multimedia Recommendation

Djenouri

Belhadi

Srivastava

et al. 2023

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

This paper proposes the use of deep learning in human-computer interaction and presents a new explainable hybrid framework for recommending relevant hashtags on a set of orpheline tweets orpheline tweet: It is a tweet with hashtags. The approach starts by determining the set of batches used in the convolution neural network based on frequent pattern mining solutions. The convolutional neural network is then applied to the set of batches of tweets to learn the hashtags of the tweets. An optimization strategy has been proposed to accurately perform the learning process by reducing the number of frequent patterns. Moreover, eXplainable AI (XAI) is introduced for hashtag recommendations by analyzing the user preferences and understanding the different weights of the deep learning model used in the learning process. This is performed by learning the hyper-parameters of the deep architecture using the genetic algorithm. GPU computing is also investigated to achieve high speed and enable the execution of the overall framework in real time. Extensive experimental analysis has been performed to show that our methodology is useful on different collections of tweets. The experimental results clearly show the efficiency of our proposed approach compared to baseline approaches in terms of both runtime and accuracy. Thus, the proposed solution achieves an accuracy of \(90\% \) when analyzing complex Wikipedia data while the other algorithms did not achieve \(85\% \) when processing the same amount of data.

show abstract

For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI

Kuhl,

Artelt,

Hammer

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI), highlighting changes to input data necessary for altering a model’s output. A CFE can either describe a scenario that is better than the factual state (upward CFE), or a scenario that is worse than the factual state (downward CFE). However, potential benefits and drawbacks of the directionality of CFEs for user behavior in xAI remain unclear. The current user study (N = 161) compares the impact of CFE directionality on behavior and experience of participants tasked to extract new knowledge from an automated system based on model predictions and CFEs. Results suggest that upward CFEs provide a significant performance advantage over other forms of counterfactual feedback. Moreover, the study highlights potential benefits of mixed CFEs improving user performance compared to downward CFEs or no explanations. In line with the performance results, users’ explicit knowledge of the system is statistically higher after receiving upward CFEs compared to downward comparisons. These findings imply that the alignment between explanation and task at hand, the so-called regulatory fit, may play a crucial role in determining the effectiveness of model explanations, informing future research directions in (xAI). To ensure reproducible research, the entire code, underlying models and user data of this study is openly available: https://github.com/ukuhl/DirectionalAlienZoo

show abstract

How Should Artificial Intelligence Explain Itself? Understanding Preferences for Explanations Generated by XAI Algorithms

Cited by 4 publications

References 0 publications

NICE: an algorithm for nearest instance counterfactual explanations

NICE: an algorithm for nearest instance counterfactual explanations

An Efficient and Accurate GPU-based Deep Learning Model for Multimedia Recommendation

For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI

Contact Info

Product

Resources

About