Actionable Explainable AI (AxAI): A Practical Example with Aggregation Functions for Adaptive Classification and Textual Explanations for Interpretable Machine Learning

Abstract

In many domains of our daily life (e.g., agriculture, forestry, health, etc.), both laymen and experts need to classify entities into two binary classes (yes/no, good/bad, sufficient/insufficient, benign/malign, etc.). For many entities, this decision is difficult and we need another class called “maybe”, which contains a corresponding quantifiable tendency toward one of these two opposites. Human domain experts are often able to mark any entity, place it in a different class and adjust the position of the slope in the class. Moreover, they can often explain the classification space linguistically—depending on their individual domain experience and previous knowledge. We consider this human-in-the-loop extremely important and call our approach actionable explainable AI. Consequently, the parameters of the functions are adapted to these requirements and the solution is explained to the domain experts accordingly. Specifically, this paper contains three novelties going beyond the state-of-the-art: (1) A novel method for detecting the appropriate parameter range for the averaging function to treat the slope in the “maybe” class, along with a proposal for a better generalisation than the existing solution. (2) the insight that for a given problem, the family of t-norms and t-conorms covering the whole range of nilpotency is suitable because we need a clear “no” or “yes” not only for the borderline cases. Consequently, we adopted the Schweizer–Sklar family of t-norms or t-conorms in ordinal sums. (3) A new fuzzy quasi-dissimilarity function for classification into three classes: Main difference, irrelevant difference and partial difference. We conducted all of our experiments with real-world datasets.

Predicting and understanding human action decisions during skillful joint-action using supervised machine learning and explainable-AI

“…Future research should also compare the effectiveness of the SHAP technique employed here with other explainable AI tools, such as LIME 61 , Deep-Lift 62 or LRP 63 , as well as interpretable Transformer techniques 85 , 86 . Future work could also explore the possibility of using explainable-AI to understand decision making in contexts where indecision often occurs 87 , as well as whether an explainable-AI analysis of the input–output mappings that underlie miss-classification or incorrect decision predictions could be used to understand ineffective decision-making.…”

Chained Deep Learning Using Generalized Cross-Entropy for Multiple Annotators Classification

“…Furthermore, we plan to test more Explainable AI methods to provide deeper insight into our model performance [ 61 , 62 , 63 ], e.g., Layer-wise Relevance Propagation that captures both negative and positive relevance. Finally, actionable and explainable AI extensions based on our GCECDL would be an exciting research line [ 64 ].…”

Reviewing the essential roles of remote phenotyping, GWAS and explainable AI in practical marker-assisted selection for drought-tolerant winter wheat breeding

“…Each of them sheds light on a different aspect of the AI model’s computation and many times it has been shown that there is no mutual consent between them, leading to the so-called ‘disagreement’ problem ( Krishna et al., 2022 ). Currently, quality metrics for xAI methods ( Doumard et al., 2023 ; Schwalbe and Finzel, 2023 ) and benchmarks for its evaluation are being defined ( Agarwal et al., 2023 ) to motivate xAI research in directions that support trustworthy, reliable, actionable and causal explanations even if they don’t always align with human pre-conceived notions and expectations ( Holzinger et al., 2019 ; Magister et al., 2021 ; Finzel et al., 2022 ; Saranti et al., 2022 ; Cabitza et al., 2023 ; Holzinger et al., 2023c ).…”