Research Papers

Interpretable classifiers for tabular data via discretization and feature selection

Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto +2

We introduce a method for computing immediately human interpretable yet accurate classifiers from tabular data. The classifiers obtained are short Boolean formulas, computed via first discretizing the original data and then using feature selection coupled with a very fast algorithm for producing the best possible Boolean classifier for the setting. We demonstrate the approach via 12 experiments, obtaining results with accuracies comparable to ones obtained via random forests, XGBoost, and existing results for the same datasets in the literature. In most cases, the accuracy of our method is in fact similar to that of the reference methods, even though the main objective of our study is the immediate interpretability of our classifiers. We also prove a new result on the probability that the classifier we obtain from real-life data corresponds to the ideally best classifier with respect to the background distribution the data comes from.

In the European context, both the EU AI Act proposal and the draft Standardisation Request on safe and trustworthy AI link standardisation to fundamental rights. However, these texts do not provide any guidelines that specify and detail the relationship between AI standards and fundamental rights, its meaning or implication. This chapter aims to clarify this critical regulatory blind spot. The main issue tackled is whether the adoption of AI harmonised standards, based on the future AI Act, should take into account fundamental rights. In our view, the response is yes. The high risks posed by certain AI systems relate in particular to infringements of fundamental rights. Therefore, mitigating such risks involves fundamental rights considerations and this is what future harmonised standards should reflect. At the same time, valid criticisms of the European standardisation process have to be addressed. Finally, the practical incorporation of fundamental rights considerations in the ongoing European standardisation of AI systems is discussed.

While the operationalisation of high-level AI ethics principles into practical AI/ML systems has made progress, there is still a theory-practice gap in managing tensions between the underlying AI ethics aspects. We cover five approaches for addressing the tensions via trade-offs, ranging from rudimentary to complex. The approaches differ in the types of considered context, scope, methods for measuring contexts, and degree of justification. None of the approaches is likely to be appropriate for all organisations, systems, or applications. To address this, we propose a framework which consists of: (i) proactive identification of tensions, (ii) prioritisation and weighting of ethics aspects, (iii) justification and documentation of trade-off decisions. The proposed framework aims to facilitate the implementation of well-rounded AI/ML systems that are appropriate for potential regulatory requirements.

Predicting in-hospital mortality for intensive care unit (ICU) patients is key to final clinical outcomes. AI has shown advantaged accuracy but suffers from the lack of explainability. To address this issue, this paper proposes an eXplainable Multimodal Mortality Predictor (X-MMP) approaching an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data. We employ multimodal learning in our framework, which can receive heterogeneous inputs from clinical data and make decisions. Furthermore, we introduce an explainable method, namely Layer-Wise Propagation to Transformer, as a proper extension of the LRP method to Transformers, producing explanations over multimodal inputs and revealing the salient features attributed to prediction. Moreover, the contribution of each modality to clinical outcomes can be visualized, assisting clinicians in understanding the reasoning behind decision-making. We construct a multimodal dataset based on MIMIC-III and MIMIC-III Waveform Database Matched Subset. Comprehensive experiments on benchmark datasets demonstrate that our proposed framework can achieve reasonable interpretation with competitive prediction accuracy. In particular, our framework can be easily transferred to other clinical tasks, which facilitates the discovery of crucial factors in healthcare research.

Recent developments in AI have brought broader attention to tensions between two overlapping communities, "AI Ethics" and "AI Safety." In this article we (i) characterize this false binary, (ii) argue that a simple binary is not an accurate model of AI discourse, and (iii) provide concrete suggestions for how individuals can help avoid the emergence of us-vs-them conflict in the broad community of people working on AI development and governance. While we focus on "AI Ethics" an "AI Safety," the general lessons apply to related tensions, including those between accelerationist ("e/acc") and cautious stances on AI development.

We develop a model of social media in which users produce different types of content and choose whom to follow. Even when abstracting from algorithmic bias, linking costs shape networks and polarization. In the welfare-maximizing equilibrium, lower linking costs can raise welfare but also increase exposure to extreme content, while very low costs reduce welfare and heighten polarization by discouraging moderate contributors. Policies that incentivize content provision can generate large welfare gains by changing who produces information, whereas link subsidies or attention reallocation mainly affect exposure and have limited welfare impact. These insights help explain why exposure-based interventions on social media platforms often yield ambiguous effects on polarization.

Deontological ethics, specifically understood through Immanuel Kant, provides a moral framework that emphasizes the importance of duties and principles, rather than the consequences of action. Understanding that despite the prominence of deontology, it is currently an overlooked approach in fairness metrics, this paper explores the compatibility of a Kantian deontological framework in fairness metrics, part of the AI alignment field. We revisit Kant's critique of utilitarianism, which is the primary approach in AI fairness metrics and argue that fairness principles should align with the Kantian deontological framework. By integrating Kantian ethics into AI alignment, we not only bring in a widely-accepted prominent moral theory but also strive for a more morally grounded AI landscape that better balances outcomes and procedures in pursuit of fairness and justice.

Artificially intelligent chatbot, such as ChatGPT, represents a recent and powerful advancement in the AI domain. Users prefer them for obtaining quick and precise answers, avoiding the usual hassle of clicking through multiple links in traditional searches. ChatGPT's conversational approach makes it comfortable and accessible for finding answers quickly and in an organized manner. However, it is important to note that these chatbots have limitations, especially in terms of providing accurate answers as well as ethical concerns. In this study, we explore various scenarios involving ChatGPT's ethical implications within academic contexts, its limitations, and the potential misuse by specific user groups. To address these challenges, we propose architectural solutions aimed at preventing inappropriate use and promoting responsible AI interactions.

Data analysis that uses the output of topological data analysis as input for machine learning algorithms has been the subject of extensive research. This approach offers a means of capturing the global structure of data. Persistent homology (PH), a common methodology within the field of TDA, has found wide-ranging applications in machine learning. One of the key reasons for the success of the PH-ML pipeline lies in the deterministic nature of feature extraction conducted through PH. The ability to achieve satisfactory levels of accuracy with relatively simple downstream machine learning models, when processing these extracted features, underlines the pipeline's superior interpretability. However, it must be noted that this interpretation has encountered issues. Specifically, it fails to accurately reflect the feasible parameter region in the data generation process, and the physical or chemical constraints that restrict this process. Against this backdrop, we explore the potential application of explainable AI methodologies to this PH-ML pipeline. We apply this approach to the specific problem of predicting gas adsorption in metal-organic frameworks and demonstrate that it can yield suggestive results. The codes to reproduce our results are available at https://github.com/naofumihama/xai_ph_ml

In this work, we instantiate a novel perturbation-based multi-class explanation framework, LIPEx (Locally Interpretable Probabilistic Explanation). We demonstrate that LIPEx not only locally replicates the probability distributions output by the widely used complex classification models but also provides insight into how every feature deemed to be important affects the prediction probability for each of the possible classes. We achieve this by defining the explanation as a matrix obtained via regression with respect to the Hellinger distance in the space of probability distributions. Ablation tests on text and image data, show that LIPEx-guided removal of important features from the data causes more change in predictions for the underlying model than similar tests based on other saliency-based or feature importance-based Explainable AI (XAI) methods. It is also shown that compared to LIME, LIPEx is more data efficient in terms of using a lesser number of perturbations of the data to obtain a reliable explanation. This data-efficiency is seen to manifest as LIPEx being able to compute its explanation matrix around 53% faster than all-class LIME, for classification experiments with text data.

Recent advances in game informatics have enabled us to find strong strategies across a diverse range of games. However, these strategies are usually difficult for humans to interpret. On the other hand, research in Explainable Artificial Intelligence (XAI) has seen a notable surge in scholarly activity. Interpreting strong or near-optimal strategies or the game itself can provide valuable insights. In this paper, we propose two methods to quantify the feature importance using Shapley values: one for the game itself and another for individual AIs. We empirically show that our proposed methods yield intuitive explanations that resonate with and augment human understanding.

Interpretability and explainability of neural networks is continuously increasing in importance, especially within safety-critical domains and to provide the social right to explanation. Concept based explanations align well with how humans reason, proving to be a good way to explain models. Concept Embedding Models (CEMs) are one such concept based explanation architectures. These have shown to overcome the trade-off between explainability and performance. However, they have a key limitation -- they require concept annotations for all their training data. For large datasets, this can be expensive and infeasible. Motivated by this, we propose Automatic Concept Embedding Models (ACEMs), which learn the concept annotations automatically.