Research Papers

The transformative potential of AI presents remarkable opportunities, but also significant risks, underscoring the importance of responsible AI development and deployment. Despite a growing emphasis on this area, there is limited understanding of industry's engagement in responsible AI research, i.e., the systematic examination of AI's ethical, social, and legal dimensions. To address this gap, we analyzed over 6 million peer-reviewed articles and 32 million patent citations using multiple methods across five distinct datasets to quantify industry's engagement. Our analysis reveals notable heterogeneity between industry's substantial presence in conventional AI research and its comparatively modest engagement in responsible AI. Leading AI firms exhibit significantly lower output in responsible AI research compared to their conventional AI research and the contributions of leading academic institutions. Our linguistic analysis reveals a more concentrated scope of responsible AI research within industry, with fewer distinct key topics addressed. Our large-scale patent citation analysis uncovers limited linkage between responsible AI research and the commercialization of AI technologies, suggesting that industry patents infrequently draw upon insights from the responsible AI literature. These patterns raise important questions about the integration of responsible AI considerations into commercialization practices, with potential implications for the alignment of AI development with broader societal objectives. Our results highlight the need for industry to publicly engage in responsible AI research to absorb academic knowledge, cultivate public trust, and proactively address the societal dimensions of AI development.

Understanding how high-level concepts are represented within artificial neural networks is a fundamental challenge in the field of artificial intelligence. While existing literature in explainable AI emphasizes the importance of labeling neurons with concepts to understand their functioning, they mostly focus on identifying what stimulus activates a neuron in most cases, this corresponds to the notion of recall in information retrieval. We argue that this is only the first-part of a two-part job, it is imperative to also investigate neuron responses to other stimuli, i.e., their precision. We call this the neuron labels error margin.

Brain-computer interface (BCI) systems facilitate unique communication between humans and computers, benefiting severely disabled individuals. Despite decades of research, BCIs are not fully integrated into clinical and commercial settings. It's crucial to assess and explain BCI performance, offering clear explanations for potential users to avoid frustration when it doesn't work as expected. This work investigates the efficacy of different deep learning and Riemannian geometry-based classification models in the context of motor imagery (MI) based BCI using electroencephalography (EEG). We then propose an optimal transport theory-based approach using earth mover's distance (EMD) to quantify the comparison of the feature relevance map with the domain knowledge of neuroscience. For this, we utilized explainable AI (XAI) techniques for generating feature relevance in the spatial domain to identify important channels for model outcomes. Three state-of-the-art models are implemented - 1) Riemannian geometry-based classifier, 2) EEGNet, and 3) EEG Conformer, and the observed trend in the model's accuracy across different architectures on the dataset correlates with the proposed feature relevance metrics. The models with diverse architectures perform significantly better when trained on channels relevant to motor imagery than data-driven channel selection. This work focuses attention on the necessity for interpretability and incorporating metrics beyond accuracy, underscores the value of combining domain knowledge and quantifying model interpretations with data-driven approaches in creating reliable and robust Brain-Computer Interfaces (BCIs).

This paper proposes a new gradient-based XAI method called Guided AbsoluteGrad for saliency map explanations. We utilize both positive and negative gradient magnitudes and employ gradient variance to distinguish the important areas for noise deduction. We also introduce a novel evaluation metric named ReCover And Predict (RCAP), which considers the Localization and Visual Noise Level objectives of the explanations. We propose two propositions for these two objectives and prove the necessity of evaluating them. We evaluate Guided AbsoluteGrad with seven gradient-based XAI methods using the RCAP metric and other SOTA metrics in three case studies: (1) ImageNet dataset with ResNet50 model; (2) International Skin Imaging Collaboration (ISIC) dataset with EfficientNet model; (3) the Places365 dataset with DenseNet161 model. Our method surpasses other gradient-based approaches, showcasing the quality of enhanced saliency map explanations through gradient magnitude.

Inclusive Design of AI's Explanations: Just for Those Previously Left Out, or for Everyone?

Md Montaser Hamid, Fatima Moussaoui, Jimena Noa Guevara +4

Motivations: Explainable Artificial Intelligence (XAI) systems aim to improve users' understanding of AI, but XAI research shows many cases of different explanations serving some users well and being unhelpful to others. In non-AI systems, some software practitioners have used inclusive design approaches and sometimes their improvements turned out to be "curb-cut" improvements -- not only addressing the needs of underserved users, but also making the products better for everyone. So, if AI practitioners used inclusive design approaches, they too might create curb-cut improvements, i.e., better explanations for everyone. Objectives: To find out, we investigated the curb-cut effects of inclusivity-driven fixes on users' mental models of AI when using an XAI prototype. The prototype and fixes came from an AI team who had adopted an inclusive design approach (GenderMag) to improve their XAI prototype. Methods: We ran a between-subject study with 69 participants with no AI background. 34 participants used the original version of the XAI prototype and 35 used the version with the inclusivity fixes. We compared the two groups' mental model concepts scores, prediction accuracy, and inclusivity. Results: We found four main results. First, it revealed several curb-cut effects of the inclusivity fixes: overall increased engagement with explanations and better mental model concepts scores, which revealed fixes with curb-cut properties. However (second), the inclusivity fixes did not improve participants' prediction accuracy scores -- instead, it appears to have harmed them. This "curb-fence" effect (opposite of the curb-cut effect) revealed the AI explanations' double-edged impact. Third, the AI team's inclusivity fixes brought significant improvements for users whose problem-solving styles had previously been underserved. Further (fourth), the AI team's fixes reduced the gender gap by 45%.

Online exams have become popular in recent years due to their accessibility. However, some concerns have been raised about the security of the online exams, particularly in the context of professional cheating services aiding malicious test takers in passing exams, forming so-called "cheating rings". In this paper, we introduce a human-in-the-loop AI cheating ring detection system designed to detect and deter these cheating rings. We outline the underlying logic of this human-in-the-loop AI system, exploring its design principles tailored to achieve its objectives of detecting cheaters. Moreover, we illustrate the methodologies used to evaluate its performance and fairness, aiming to mitigate the unintended risks associated with the AI system. The design and development of the system adhere to Responsible AI (RAI) standards, ensuring that ethical considerations are integrated throughout the entire development process.

This paper presents a novel application of explainable AI (XAI) for root-causing performance degradation in machine learning models that learn continuously from user engagement data. In such systems a single feature corruption can cause cascading feature, label and concept drifts. We have successfully applied this technique to improve the reliability of models used in personalized advertising. Performance degradation in such systems manifest as prediction anomalies in the models. These models are typically trained continuously using features that are produced by hundreds of real time data processing pipelines or derived from other upstream models. A failure in any of these pipelines or an instability in any of the upstream models can cause feature corruption, causing the model's predicted output to deviate from the actual output and the training data to become corrupted. The causal relationship between the features and the predicted output is complex, and root-causing is challenging due to the scale and dynamism of the system. We demonstrate how temporal shifts in the global feature importance distribution can effectively isolate the cause of a prediction anomaly, with better recall than model-to-feature correlation methods. The technique appears to be effective even when approximating the local feature importance using a simple perturbation-based method, and aggregating over a few thousand examples. We have found this technique to be a model-agnostic, cheap and effective way to monitor complex data pipelines in production and have deployed a system for continuously analyzing the global feature importance distribution of continuously trained models.

Debiasing Machine Learning Models by Using Weakly Supervised Learning

Renan D. B. Brotto, Jean-Michel Loubes, Laurent Risser +3

We tackle the problem of bias mitigation of algorithmic decisions in a setting where both the output of the algorithm and the sensitive variable are continuous. Most of prior work deals with discrete sensitive variables, meaning that the biases are measured for subgroups of persons defined by a label, leaving out important algorithmic bias cases, where the sensitive variable is continuous. Typical examples are unfair decisions made with respect to the age or the financial status. In our work, we then propose a bias mitigation strategy for continuous sensitive variables, based on the notion of endogeneity which comes from the field of econometrics. In addition to solve this new problem, our bias mitigation strategy is a weakly supervised learning method which requires that a small portion of the data can be measured in a fair manner. It is model agnostic, in the sense that it does not make any hypothesis on the prediction model. It also makes use of a reasonably large amount of input observations and their corresponding predictions. Only a small fraction of the true output predictions should be known. This therefore limits the need for expert interventions. Results obtained on synthetic data show the effectiveness of our approach for examples as close as possible to real-life applications in econometrics.

Artificial Intelligence (AI) Ethics is a nascent yet critical research field. Recent developments in generative AI and foundational models necessitate a renewed look at the problem of AI Ethics. In this study, we perform a bibliometric analysis of AI Ethics literature for the last 20 years based on keyword search. Our study reveals a three-phase development in AI Ethics, namely an incubation phase, making AI human-like machines phase, and making AI human-centric machines phase. We conjecture that the next phase of AI ethics is likely to focus on making AI more machine-like as AI matches or surpasses humans intellectually, a term we coin as "machine-like human".

Skin cancer detection through dermoscopy image analysis is a critical task. However, existing models used for this purpose often lack interpretability and reliability, raising the concern of physicians due to their black-box nature. In this paper, we propose a novel approach for the diagnosis of melanoma using an interpretable prototypical-part model. We introduce a guided supervision based on non-expert feedback through the incorporation of: 1) binary masks, obtained automatically using a segmentation network; and 2) user-refined prototypes. These two distinct information pathways aim to ensure that the learned prototypes correspond to relevant areas within the skin lesion, excluding confounding factors beyond its boundaries. Experimental results demonstrate that, even without expert supervision, our approach achieves superior performance and generalization compared to non-interpretable models.

Sub-population shift is a specific type of domain shift that highlights changes in data distribution within specific sub-groups or populations between training and testing. Sub-population shift accounts for a significant source of algorithmic bias and calls for distributional robustness. Recent studies found inherent distributional robustness in multi-modality foundation models, such as the vision-language model CLIP, yet this robustness is vulnerable through parameter fine-tuning. In this paper, we propose leveraging the connection of robustness among different modalities and reshaping the distributional robustness of one modality with another. Specifically, in the context of the distributional robustness of CLIP, we propose to leverage natural language inputs to debias the image feature representations, to improve worst-case performance on sub-populations. Our extensive empirical studies show that image representations debiased by natural language can achieve significant performance improvement and reduction of performance instability under sub-population shifts.

Despite neural networks (NN) have been widely applied in various fields and generally outperforms humans, they still lack interpretability to a certain extent, and humans are unable to intuitively understand the decision logic of NN. This also hinders the knowledge interaction between humans and NN, preventing humans from getting involved to give direct guidance when NN's decisions go wrong. While recent research in explainable AI has achieved interpretability of NN from various perspectives, it has not yet provided effective methods for knowledge exchange between humans and NN. To address this problem, we constructed a two-way interaction interface that uses structured representations of visual concepts and their relationships as the "language" for knowledge exchange between humans and NN. Specifically, NN provide intuitive reasoning explanations to humans based on the class-specific structural concepts graph (C-SCG). On the other hand, humans can modify the biases present in the C-SCG through their prior knowledge and reasoning ability, and thus provide direct knowledge guidance to NN through this interface. Through experimental validation, based on this interaction interface, NN can provide humans with easily understandable explanations of the reasoning process. Furthermore, human involvement and prior knowledge can directly and effectively contribute to enhancing the performance of NN.