Research Papers

Photovoltaic (PV) energy grows rapidly and is crucial for the decarbonization of electric systems. However, centralized registries recording the technical characteristifs of rooftop PV systems are often missing, making it difficult to accurately monitor this growth. The lack of monitoring could threaten the integration of PV energy into the grid. To avoid this situation, the remote sensing of rooftop PV systems using deep learning emerged as a promising solution. However, existing techniques are not reliable enough to be used by public authorities or transmission system operators (TSOs) to construct up-to-date statistics on the rooftop PV fleet. The lack of reliability comes from the fact that deep learning models are sensitive to distribution shifts. This work proposes a comprehensive evaluation of the effects of distribution shifts on the classification accuracy of deep learning models trained to detect rooftop PV panels on overhead imagery. We construct a benchmark to isolate the sources of distribution shift and introduce a novel methodology that leverages explainable artificial intelligence (XAI) and decomposition of the input image and model's decision in terms of scales to understand how distribution shifts affect deep learning models. Finally, based on our analysis, we introduce a data augmentation technique meant to improve the robustness of deep learning classifiers to varying acquisition conditions. We show that our proposed approach outperforms competing methods. We discuss some practical recommendations for mapping PV systems using overhead imagery and deep learning models.

Explaining Decisions of Agents in Mixed-Motive Games

Maayan Orner, Oleg Maksimov, Akiva Kleinerman +2

In recent years, agents have become capable of communicating seamlessly via natural language and navigating in environments that involve cooperation and competition, a fact that can introduce social dilemmas. Due to the interleaving of cooperation and competition, understanding agents' decision-making in such environments is challenging, and humans can benefit from obtaining explanations. However, such environments and scenarios have rarely been explored in the context of explainable AI. While some explanation methods for cooperative environments can be applied in mixed-motive setups, they do not address inter-agent competition, cheap-talk, or implicit communication by actions. In this work, we design explanation methods to address these issues. Then, we proceed to establish generality and demonstrate the applicability of the methods to three games with vastly different properties. Lastly, we demonstrate the effectiveness and usefulness of the methods for humans in two mixed-motive games. The first is a challenging 7-player game called no-press Diplomacy. The second is a 3-player game inspired by the prisoner's dilemma, featuring communication in natural language.

Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers

Alex Oesterling, Usha Bhalla, Suresh Venkatasubramanian +1

As Artificial Intelligence (AI) tools are increasingly employed in diverse real-world applications, there has been significant interest in regulating these tools. To this end, several regulatory frameworks have been introduced by different countries worldwide. For example, the European Union recently passed the AI Act, the White House issued an Executive Order on safe, secure, and trustworthy AI, and the White House Office of Science and Technology Policy issued the Blueprint for an AI Bill of Rights (AI BoR). Many of these frameworks emphasize the need for auditing and improving the trustworthiness of AI tools, underscoring the importance of safety, privacy, explainability, fairness, and human fallback options. Although these regulatory frameworks highlight the necessity of enforcement, practitioners often lack detailed guidance on implementing them. Furthermore, the extensive research on operationalizing each of these aspects is frequently buried in technical papers that are difficult for practitioners to parse. In this write-up, we address this shortcoming by providing an accessible overview of existing literature related to operationalizing regulatory principles. We provide easy-to-understand summaries of state-of-the-art literature and highlight various gaps that exist between regulatory guidelines and existing AI research, including the trade-offs that emerge during operationalization. We hope that this work not only serves as a starting point for practitioners interested in learning more about operationalizing the regulatory guidelines outlined in the Blueprint for an AI BoR but also provides researchers with a list of critical open problems and gaps between regulations and state-of-the-art AI research. Finally, we note that this is a working paper and we invite feedback in line with the purpose of this document as described in the introduction.

This paper presents dilated Residual Network (ResNet) models for disease classification from retinal fundus images. Dilated convolution filters are used to replace normal convolution filters in the higher layers of the ResNet model (dilated ResNet) in order to improve the receptive field compared to the normal ResNet model for disease classification. This study introduces computer-assisted diagnostic tools that employ deep learning, enhanced with explainable AI techniques. These techniques aim to make the tool's decision-making process transparent, thereby enabling medical professionals to understand and trust the AI's diagnostic decision. They are particularly relevant in today's healthcare landscape, where there is a growing demand for transparency in AI applications to ensure their reliability and ethical use. The dilated ResNet is used as a replacement for the normal ResNet to enhance the classification accuracy of retinal eye diseases and reduce the required computing time. The dataset used in this work is the Ocular Disease Intelligent Recognition (ODIR) dataset which is a structured ophthalmic database with eight classes covering most of the common retinal eye diseases. The evaluation metrics used in this work include precision, recall, accuracy, and F1 score. In this work, a comparative study has been made between normal ResNet models and dilated ResNet models on five variants namely ResNet-18, ResNet-34, ResNet-50, ResNet-101, and ResNet-152. The dilated ResNet model shows promising results as compared to normal ResNet with an average F1 score of 0.71, 0.70, 0.69, 0.67, and 0.70 respectively for the above respective variants in ODIR multiclass disease classification.

Commonsense reasoning is a difficult task for a computer, but a critical skill for an artificial intelligence (AI). It can enhance the explainability of AI models by enabling them to provide intuitive and human-like explanations for their decisions. This is necessary in many areas especially in question answering (QA), which is one of the most important tasks of natural language processing (NLP). Over time, a multitude of methods have emerged for solving commonsense reasoning problems such as knowledge-based approaches using formal logic or linguistic analysis. In this paper, we investigate the effectiveness of large language models (LLMs) on different QA tasks with a focus on their abilities in reasoning and explainability. We study three LLMs: GPT-3.5, Gemma and Llama 3. We further evaluate the LLM results by means of a questionnaire. We demonstrate the ability of LLMs to reason with commonsense as the models outperform humans on different datasets. While GPT-3.5's accuracy ranges from 56% to 93% on various QA benchmarks, Llama 3 achieved a mean accuracy of 90% on all eleven datasets. Thereby Llama 3 is outperforming humans on all datasets with an average 21% higher accuracy over ten datasets. Furthermore, we can appraise that, in the sense of explainable artificial intelligence (XAI), GPT-3.5 provides good explanations for its decisions. Our questionnaire revealed that 66% of participants rated GPT-3.5's explanations as either "good" or "excellent". Taken together, these findings enrich our understanding of current LLMs and pave the way for future investigations of reasoning and explainability.

Black box models are increasingly being used in the daily lives of human beings living in society. Along with this increase, there has been the emergence of Explainable Artificial Intelligence (XAI) methods aimed at generating additional explanations regarding how the model makes certain predictions. In this sense, methods such as Dalex, Eli5, eXirt, Lofo and Shap emerged as different proposals and methodologies for generating explanations of black box models in an agnostic way. Along with the emergence of these methods, questions arise such as "How Reliable and Stable are XAI Methods?". With the aim of shedding light on this main question, this research creates a pipeline that performs experiments using the diabetes dataset and four different machine learning models (LGBM, MLP, DT and KNN), creating different levels of perturbations of the test data and finally generates explanations from the eXirt method regarding the confidence of the models and also feature relevances ranks from all XAI methods mentioned, in order to measure their stability in the face of perturbations. As a result, it was found that eXirt was able to identify the most reliable models among all those used. It was also found that current XAI methods are sensitive to perturbations, with the exception of one specific method.

The increasing integration of Artificial Intelligence (AI) into everyday life makes it essential to explain AI-based decision-making in a way that is understandable to all users, including those with disabilities. Accessible explanations are crucial as accessibility in technology promotes digital inclusion and allows everyone, regardless of their physical, sensory, or cognitive abilities, to use these technologies effectively. This paper presents a systematic literature review of the research on the accessibility of Explainable Artificial Intelligence (XAI), specifically considering persons with sight loss. Our methodology includes searching several academic databases with search terms to capture intersections between XAI and accessibility. The results of this survey highlight the lack of research on Accessible XAI (AXAI) and stress the importance of including the disability community in XAI development to promote digital inclusion and accessibility and remove barriers. Most XAI techniques rely on visual explanations, such as heatmaps or graphs, which are not accessible to persons who are blind or have low vision. Therefore, it is necessary to develop explanation methods through non-visual modalities, such as auditory and tactile feedback, visual modalities accessible to persons with low vision, and personalized solutions that meet the needs of individuals, including those with multiple disabilities. We further emphasize the importance of integrating universal design principles into AI development practices to ensure that AI technologies are usable by everyone.

Detecting and classifying lesions in breast ultrasound images is a promising application of artificial intelligence (AI) for reducing the burden of cancer in regions with limited access to mammography. Such AI systems are more likely to be useful in a clinical setting if their predictions can be explained to a radiologist. This work proposes an explainable AI model that provides interpretable predictions using a standard lexicon from the American College of Radiology's Breast Imaging and Reporting Data System (BI-RADS). The model is a deep neural network featuring a concept bottleneck layer in which known BI-RADS features are predicted before making a final cancer classification. This enables radiologists to easily review the predictions of the AI system and potentially fix errors in real time by modifying the concept predictions. In experiments, a model is developed on 8,854 images from 994 women with expert annotations and histological cancer labels. The model outperforms state-of-the-art lesion detection frameworks with 48.9 average precision on the held-out testing set, and for cancer classification, concept intervention is shown to increase performance from 0.876 to 0.885 area under the receiver operating characteristic curve. Training and evaluation code is available at https://github.com/hawaii-ai/bus-cbm.

A reliable knowledge structure is a prerequisite for building effective adaptive learning systems and intelligent tutoring systems. Pursuing an explainable and trustworthy knowledge structure, we propose a method for constructing causal knowledge networks. This approach leverages Bayesian networks as a foundation and incorporates causal relationship analysis to derive a causal network. Additionally, we introduce a dependable knowledge-learning path recommendation technique built upon this framework, improving teaching and learning quality while maintaining transparency in the decision-making process.

FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainability

Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng +1

We present FairX, an open-source Python-based benchmarking tool designed for the comprehensive analysis of models under the umbrella of fairness, utility, and eXplainability (XAI). FairX enables users to train benchmarking bias-mitigation models and evaluate their fairness using a wide array of fairness metrics, data utility metrics, and generate explanations for model predictions, all within a unified framework. Existing benchmarking tools do not have the way to evaluate synthetic data generated from fair generative models, also they do not have the support for training fair generative models either. In FairX, we add fair generative models in the collection of our fair-model library (pre-processing, in-processing, post-processing) and evaluation metrics for evaluating the quality of synthetic fair data. This version of FairX supports both tabular and image datasets. It also allows users to provide their own custom datasets. The open-source FairX benchmarking package is publicly available at \url{https://github.com/fahim-sikder/FairX}.

In numerous high-stakes domains, training novices via conventional learning systems does not suffice. To impart tacit knowledge, experts' hands-on guidance is imperative. However, training novices by experts is costly and time-consuming, increasing the need for alternatives. Explainable artificial intelligence (XAI) has conventionally been used to make black-box artificial intelligence systems interpretable. In this work, we utilize XAI as an alternative: An (X)AI system is trained on experts' past decisions and is then employed to teach novices by providing examples coupled with explanations. In a study with 249 participants, we measure the effectiveness of such an approach for a classification task. We show that (X)AI-based learning systems are able to induce learning in novices and that their cognitive styles moderate learning. Thus, we take the first steps to reveal the impact of XAI on human learning and point AI developers to future options to tailor the design of (X)AI-based learning systems.

With the digitalization of health care systems, artificial intelligence becomes more present in medicine. Especially machine learning shows great potential for complex tasks such as time series classification, usually at the cost of transparency and comprehensibility. This leads to a lack of trust by humans and thus hinders its active usage. Explainable artificial intelligence tries to close this gap by providing insight into the decision-making process, the actual usefulness of its different methods is however unclear. This paper proposes a user study based evaluation of the explanation method Grad-CAM with application to a neural network for the classification of breaths in time series neonatal ventilation data. We present the perceived usefulness of the explainability method by different stakeholders, exposing the difficulty to achieve actual transparency and the wish for more in-depth explanations by many of the participants.