Research Papers

Recently, there has been a surge of explainable AI (XAI) methods driven by the need for understanding machine learning model behaviors in high-stakes scenarios. However, properly evaluating the effectiveness of the XAI methods inevitably requires the involvement of human subjects, and conducting human-centered benchmarks is challenging in a number of ways: designing and implementing user studies is complex; numerous design choices in the design space of user study lead to problems of reproducibility; and running user studies can be challenging and even daunting for machine learning researchers. To address these challenges, this paper presents OpenHEXAI, an open-source framework for human-centered evaluation of XAI methods. OpenHEXAI features (1) a collection of diverse benchmark datasets, pre-trained models, and post hoc explanation methods; (2) an easy-to-use web application for user study; (3) comprehensive evaluation metrics for the effectiveness of post hoc explanation methods in the context of human-AI decision making tasks; (4) best practice recommendations of experiment documentation; and (5) convenient tools for power analysis and cost estimation. OpenHEAXI is the first large-scale infrastructural effort to facilitate human-centered benchmarks of XAI methods. It simplifies the design and implementation of user studies for XAI methods, thus allowing researchers and practitioners to focus on the scientific questions. Additionally, it enhances reproducibility through standardized designs. Based on OpenHEXAI, we further conduct a systematic benchmark of four state-of-the-art post hoc explanation methods and compare their impacts on human-AI decision making tasks in terms of accuracy, fairness, as well as users' trust and understanding of the machine learning model.

Sparse, Efficient and Explainable Data Attribution with DualXDA

Galip Ümit Yolcu, Moritz Weckbecker, Thomas Wiegand +2

Data Attribution (DA) is an emerging approach in the field of eXplainable Artificial Intelligence (XAI), aiming to identify influential training datapoints which determine model outputs. It seeks to provide transparency about the model and individual predictions, e.g. for model debugging, identifying data-related causes of suboptimal performance. However, existing DA approaches suffer from prohibitively high computational costs and memory demands when applied to even medium-scale datasets and models, forcing practitioners to resort to approximations that may fail to capture the true inference process of the underlying model. Additionally, current attribution methods exhibit low sparsity, resulting in non-negligible attribution scores across a high number of training examples, hindering the discovery of decisive patterns in the data. In this work, we introduce DualXDA, a framework for sparse, efficient and explainable DA, comprised of two interlinked approaches, Dual Data Attribution (DualDA) and eXplainable Data Attribution (XDA): With DualDA, we propose a novel approach for efficient and effective DA, leveraging Support Vector Machine theory to provide fast and naturally sparse data attributions for AI predictions. In extensive quantitative analyses, we demonstrate that DualDA achieves high attribution quality, excels at solving a series of evaluated downstream tasks, while at the same time improving explanation time by a factor of up to 4,100,000x compared to the original Influence Functions method, and up to 11,000x compared to the method's most efficient approximation from literature to date. We further introduce XDA, a method for enhancing Data Attribution with capabilities from feature attribution methods to explain why training samples are relevant for the prediction of a test sample in terms of impactful features, which we showcase and verify qualitatively in detail.

XAI (eXplanable AI) techniques that have the property of explaining the reasons for their conclusions, i.e. explainability or interpretability, are attracting attention. XAI is expected to be used in the development of forensic science and the justice system. In today's forensic and criminal investigation environment, experts face many challenges due to large amounts of data, small pieces of evidence in a chaotic and complex environment, traditional laboratory structures and sometimes inadequate knowledge. All these can lead to failed investigations and miscarriages of justice. In this paper, we describe the application of one logical approach to crime scene investigation. The subject of the application is ``The Adventure of the Speckled Band'' from the Sherlock Holmes short stories. The applied data is the knowledge graph created for the Knowledge Graph Reasoning Challenge. We tried to find the murderer by inferring each person with the motive, opportunity, and method. We created an ontology of motives and methods of murder from dictionaries and dictionaries, added it to the knowledge graph of ``The Adventure of the Speckled Band'', and applied scripts to determine motives, opportunities, and methods.

This paper presents a comprehensive comparative analysis of explainable artificial intelligence (XAI) ensembling methods. Our research brings three significant contributions. Firstly, we introduce a novel ensembling method, NormEnsembleXAI, that leverages minimum, maximum, and average functions in conjunction with normalization techniques to enhance interpretability. Secondly, we offer insights into the strengths and weaknesses of XAI ensemble methods. Lastly, we provide a library, facilitating the practical implementation of XAI ensembling, thus promoting the adoption of transparent and interpretable deep learning models.

With the adoption of machine learning into routine clinical practice comes the need for Explainable AI methods tailored to medical applications. Shapley values have sparked wide interest for locally explaining models. Here, we demonstrate their interpretation strongly depends on both the summary statistic and the estimator for it, which in turn define what we identify as an 'anchor point'. We show that the convention of using a mean anchor point may generate misleading interpretations for survival analysis and introduce median-SHAP, a method for explaining black-box models predicting individual survival times.

Visual quality inspection systems, crucial in sectors like manufacturing and logistics, employ computer vision and machine learning for precise, rapid defect detection. However, their unexplained nature can hinder trust, error identification, and system improvement. This paper presents a framework to bolster visual quality inspection by using CAM-based explanations to refine semantic segmentation models. Our approach consists of 1) Model Training, 2) XAI-based Model Explanation, 3) XAI Evaluation, and 4) Annotation Augmentation for Model Enhancement, informed by explanations and expert insights. Evaluations show XAI-enhanced models surpass original DeepLabv3-ResNet101 models, especially in intricate object segmentation.

This paper addresses trust issues created from the ubiquity of black box algorithms and surrogate explainers in Explainable Intrusion Detection Systems (X-IDS). While Explainable Artificial Intelligence (XAI) aims to enhance transparency, black box surrogate explainers, such as Local Interpretable Model-Agnostic Explanation (LIME) and SHapley Additive exPlanation (SHAP), are difficult to trust. The black box nature of these surrogate explainers makes the process behind explanation generation opaque and difficult to understand. To avoid this problem, one can use transparent white box algorithms such as Rule Extraction (RE). There are three types of RE algorithms: pedagogical, decompositional, and eclectic. Pedagogical methods offer fast but untrustworthy white-box explanations, while decompositional RE provides trustworthy explanations with poor scalability. This work explores eclectic rule extraction, which strikes a balance between scalability and trustworthiness. By combining techniques from pedagogical and decompositional approaches, eclectic rule extraction leverages the advantages of both, while mitigating some of their drawbacks. The proposed Hybrid X-IDS architecture features eclectic RE as a white box surrogate explainer for black box Deep Neural Networks (DNN). The presented eclectic RE algorithm extracts human-readable rules from hidden layers, facilitating explainable and trustworthy rulesets. Evaluations on UNSW-NB15 and CIC-IDS-2017 datasets demonstrate the algorithm's ability to generate rulesets with 99.9% accuracy, mimicking DNN outputs. The contributions of this work include the hybrid X-IDS architecture, the eclectic rule extraction algorithm applicable to intrusion detection datasets, and a thorough analysis of performance and explainability, demonstrating the trade-offs involved in rule extraction speed and accuracy.

Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks

Tanmay Garg, Deepika Vemuri, Vineeth N Balasubramanian

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and makes use of adversarial training. During training, the explanation module is optimized to extract visual concepts from the classifier's latent representations, while the GAN-based module aims to discriminate images generated from concepts, from true images. This joint training scheme enables the model to implicitly align its internally learned concepts with human-interpretable visual properties. Comprehensive experiments demonstrate the robustness of our approach, while producing coherent concept activations. We analyse the learned concepts, showing their semantic concordance with object parts and visual attributes. We also study how perturbations in the adversarial training protocol impact both classification and concept acquisition. In summary, this work presents a significant step towards building inherently interpretable deep vision models with task-aligned concept representations - a key enabler for developing trustworthy AI for real-world perception tasks.

Explainable artificial intelligence (XAI) holds immense significance in enhancing the deep neural network's transparency and credibility, particularly in some risky and high-cost scenarios, like synthetic aperture radar (SAR). Shapley is a game-based explanation technique with robust mathematical foundations. However, Shapley assumes that model's features are independent, rendering Shapley explanation invalid for high dimensional models. This study introduces a manifold-based Shapley method by projecting high-dimensional features into low-dimensional manifold features and subsequently obtaining Fusion-Shap, which aims at (1) addressing the issue of erroneous explanations encountered by traditional Shap; (2) resolving the challenge of interpretability that traditional Shap faces in complex scenarios.

As the societal implications of Artificial Intelligence (AI) continue to grow, the pursuit of responsible AI necessitates public engagement in its development and governance processes. This involvement is crucial for capturing diverse perspectives and promoting equitable practices and outcomes. We applied Cultural Consensus Theory (CCT) to a nationally representative survey dataset on various aspects of AI to discern beliefs and attitudes about responsible AI in the United States. Our results offer valuable insights by identifying shared and contrasting views on responsible AI. Furthermore, these findings serve as critical reference points for developers and policymakers, enabling them to more effectively consider individual variances and group-level cultural perspectives when making significant decisions and addressing the public's concerns.

Fairness is a growing concern for high-risk decision-making using Artificial Intelligence (AI) but ensuring it through purely technical means is challenging: there is no universally accepted fairness measure, fairness is context-dependent, and there might be conflicting perspectives on what is considered fair. Thus, involving stakeholders, often without a background in AI or fairness, is a promising avenue. Research to directly involve stakeholders is in its infancy, and many questions remain on how to support stakeholders to feedback on fairness, and how this feedback can be integrated into AI models. Our work follows an approach where stakeholders can give feedback on specific decision instances and their outcomes with respect to their fairness, and then to retrain an AI model. In order to investigate this approach, we conducted two studies of a complex AI model for credit rating used in loan applications. In study 1, we collected feedback from 58 lay users on loan application decisions, and conducted offline experiments to investigate the effects on accuracy and fairness metrics. In study 2, we deepened this investigation by showing 66 participants the results of their feedback with respect to fairness, and then conducted further offline analyses. Our work contributes two datasets and associated code frameworks to bootstrap further research, highlights the opportunities and challenges of employing lay user feedback for improving AI fairness, and discusses practical implications for developing AI applications that more closely reflect stakeholder views about fairness.

We grapple with the question: How, for whom and why should explainable artificial intelligence (XAI) aim to support the user goal of agency? In particular, we analyze the relationship between agency and explanations through a user-centric lens through case studies and thought experiments. We find that explanation serves as one of several possible first steps for agency by allowing the user convert forethought to outcome in a more effective manner in future interactions. Also, we observe that XAI systems might better cater to laypersons, particularly "tinkerers", when combining explanations and user control, so they can make meaningful changes.