The increasing use of AI methods in various applications has raised concerns about their explainability and transparency. Many solutions have been developed within the last few years to either explain the model itself or the decisions provided by the model. However, the number of contributions in the field of eXplainable AI (XAI) is increasing at such a high pace that it is almost impossible for a newcomer to identify key ideas, track the field’s evolution, or find promising new research directions. 

Typically, survey papers serve as a starting point, providing a feasible entry point into a research area. However, this is not trivial for some fields with exponential growth in the literature, such as XAI. For instance, we analyzed 23 surveys in the XAI domain published within the last three years and surprisingly found no common conceptualization among them. This makes XAI one of the most challenging research areas to enter. To address this problem, we propose a systematic approach that enables newcomers to identify the principal ideas and track their evolution. The proposed method includes automating the retrieval of relevant papers, extracting their semantic relationship, and creating a temporal graph of ideas by post-analysis of citation graphs. 

The main outcome of our method is Field’s Evolution Graph (FEG), which can be used to find the core idea of each approach in this field, see how a given concept has developed and evolved over time, observe how different notions interact with each other, and perceive how a new paradigm emerges through combining multiple ideas. As for demonstration, we show that FEG successfully identifies the field’s key articles, such as LIME or Grad-CAM, and maps out their evolution and relationships.

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG.

One of the most widely adopted approaches for eXplainable Artificial Intelligence (XAI) involves employing of Shapley values (SVs) to determine the relative importance of input features. While based on a solid mathematical foundation derived from cooperative game theory, SVs have a significant drawback: high computational cost. Calculating the exact SV is an NP-hard problem, necessitating the use of approximations, particularly when dealing with more than twenty features. On the other hand, determining SVs for all features is seldom necessary in practice; users are primarily interested in the most important ones only. This paper introduces the Economic Hierarchical Shapley values (ecoShap) method for calculating SVs for the most crucial features only, with reduced computational cost. EcoShap iteratively expands disjoint groups of features in a tree-like manner, avoiding the expensive computations for the majority of less important features. Our experimental results across eight datasets demonstrate that the proposed technique efficiently identifies top features; at a 50% reduction in computational costs, it can determine between three and seven of the most important features. © The Author(s) 2024.

In the rapidly evolving field of AI, Explainable Artificial Intelligence (XAI) has become paramount, particularly in Intelligent Environments applications. It offers clarity and understanding in complex decision-making processes, fostering trust and enabling rigorous scrutiny. The Shapley value, renowned for its accurate quantification of feature importance, has emerged as a prevalent standard in both academic research and practical application. Nevertheless, the Shapley value's reliance on the calculation of all possible coalitions poses a significant computational challenge, as it falls within the class of NP-hard problems. Consequently, approximation techniques are employed in most practical scenarios as a substitute for precise computations. The most common of those is the SHAP (SHapley Additive exPlanations) technique, which quantifies the influence exerted by a specific feature on decision outcomes of a specific Machine Learning model. However, the Shapley value's theoretical underpinnings focus on assessing and understanding feature impact on model evaluation metrics, rather than just alterations in the responses. This paper conducts a comparative analysis using controlled synthetic data with established ground truths. It juxtaposes the practical implementation of the SHAP approach with the theoretical model in two distinct scenarios: one using the F1-score and the other, the accuracy metric. These are two representative characteristic functions, capturing different aspects and whose appropriateness depends on the specific requirements and context of the task to be solved. We analyze how the three alternatives exhibit similarity and disparity in their manifestation of feature effects. We explore the parallels and differences between these approaches in reflecting feature effects. Ultimately, our research seeks to determine the conditions under which SHAP outcomes are more aligned with either the F1-score or the accuracy metric, thereby providing valuable insights for their application in various Intelligent Environment contexts. © 2024 IEEE.

Explainable Artificial Intelligence (XAI) is crucial in ensuring transparency, accountability, and trust in machine learning models, especially in applications involving high-stakes decision-making. This paper focuses on addressing the research gap in federated learning (FL), specifically emphasizing the use of inherently interpretable underlying models. While most FL frameworks rely on complex, black-box models such as Artificial Neural Networks (ANNs), we propose using Decision Tree (DT) classifiers to maintain explainability. More specifically, we introduce a novel framework for horizontal federated learning using Extremely Fast Decision Trees (EFDTs) with streaming data on the client side. Our approach involves aggregating clients' EFDTs on the server side without centralizing raw data, and the training process occurs on the clients' sides. We outline three aggregation strategies and demonstrate that our methods outperform local models and achieve performance levels close to centralized models while retaining inherent explainability. © 2024 CEUR-WS. All rights reserved.