Conditional independence (CI) testing is frequently used in data analysis and machine learning for various scientific fields and it forms the basis of constraint-based causal discovery. Oftentimes, CI testing relies on strong, rather unrealistic assumptions. One of these assumptions is homoskedasticity, in other words, a constant conditional variance is assumed. We frame heteroskedasticity in a structural causal model framework and present an adaptation of the partial correlation CI test that works well in the presence of heteroskedastic noise, given that expert knowledge about the heteroskedastic relationships is available. Further, we provide theoretical consistency results for the proposed CI test which carry over to causal discovery under certain assumptions. Numerical causal discovery experiments demonstrate that the adapted partial correlation CI test outperforms the standard test in the presence of heteroskedasticity and is on par for the homoskedastic case. Finally, we discuss the general challenges and limits as to how expert knowledge about heteroskedasticity can be accounted for in causal discovery.

Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. However, it is clear that AI and business models based on it can only reach their full potential if AI applications are developed according to high quality standards and are effectively protected against new AI risks. For instance, AI bears the risk of unfair treatment of individuals when processing personal data e.g., to support credit lending or staff recruitment decisions. The emergence of these new risks is closely linked to the fact that the behavior of AI applications, particularly those based on Machine Learning (ML), is essentially learned from large volumes of data and is not predetermined by fixed programmed rules. Thus, the issue of the trustworthiness of AI applications is crucial and is the subject of numerous major publications by stakeholders in politics, business and society. In addition, there is mutual agreement that the requirements for trustworthy AI, which are often described in an abstract way, must now be made clear and tangible. One challenge to overcome here relates to the fact that the specific quality criteria for an AI application depend heavily on the application context and possible measures to fulfill them in turn depend heavily on the AI technology used. Lastly, practical assessment procedures are needed to evaluate whether specific AI applications have been developed according to adequate quality standards. This AI assessment catalog addresses exactly this point and is intended for two target groups: Firstly, it provides developers with a guideline for systematically making their AI applications trustworthy. Secondly, it guides assessors and auditors on how to examine AI applications for trustworthiness in a structured way.

Graph Neural Networks (GNNs) are promising surrogates for quantum mechanical calculations as they establish unprecedented low errors on collections of molecular dynamics (MD) trajectories. Thanks to their fast inference times they promise to accelerate computational chemistry applications. Unfortunately, despite low in-distribution (ID) errors, such GNNs might be horribly wrong for out-of-distribution (OOD) samples. Uncertainty estimation (UE) may aid in such situations by communicating the model's certainty about its prediction. Here, we take a closer look at the problem and identify six key desiderata for UE in molecular force fields, three 'physics-informed' and three 'application-focused' ones. To overview the field, we survey existing methods from the field of UE and analyze how they fit to the set desiderata. By our analysis, we conclude that none of the previous works satisfies all criteria. To fill this gap, we propose Localized Neural Kernel (LNK) a Gaussian Process (GP)-based extension to existing GNNs satisfying the desiderata. In our extensive experimental evaluation, we test four different UE with three different backbones and two datasets. In out-of-equilibrium detection, we find LNK yielding up to 2.5 and 2.1 times lower errors in terms of AUC-ROC score than dropout or evidential regression-based methods while maintaining high predictive performance.

Detecting duplicate patient participation in clinical trials is a major challenge because repeated patients can undermine the credibility and accuracy of the trial's findings and result in significant health and financial risks. Developing accurate automated speaker verification (ASV) models is crucial to verify the identity of enrolled individuals and remove duplicates, but the size and quality of data influence ASV performance. However, there has been limited investigation into the factors that can affect ASV capabilities in clinical environments. In this paper, we bridge the gap by conducting analysis of how participant demographic characteristics, audio quality criteria, and severity level of Alzheimer's disease (AD) impact the performance of ASV utilizing a dataset of speech recordings from 659 participants with varying levels of AD, obtained through multiple speech tasks. Our results indicate that ASV performance: 1) is slightly better on male speakers than on female speakers; 2) degrades for individuals who are above 70 years old; 3) is comparatively better for non-native English speakers than for native English speakers; 4) is negatively affected by clinician interference, noisy background, and unclear participant speech; 5) tends to decrease with an increase in the severity level of AD. Our study finds that voice biometrics raise fairness concerns as certain subgroups exhibit different ASV performances owing to their inherent voice characteristics. Moreover, the performance of ASV is influenced by the quality of speech recordings, which underscores the importance of improving the data collection settings in clinical trials.

Understanding the effect of a feature vector $x \in \mathbb{R}^d$ on the response value (label) $y \in \mathbb{R}$ is the cornerstone of many statistical learning problems. Ideally, it is desired to understand how a set of collected features combine together and influence the response value, but this problem is notoriously difficult, due to the high-dimensionality of data and limited number of labeled data points, among many others. In this work, we take a new perspective on this problem, and we study the question of assessing the difference of influence that the two given features have on the response value. We first propose a notion of closeness for the influence of features, and show that our definition recovers the familiar notion of the magnitude of coefficients in the parametric model. We then propose a novel method to test for the closeness of influence in general model-free supervised learning problems. Our proposed test can be used with finite number of samples with control on type I error rate, no matter the ground truth conditional law $\mathcal{L}(Y |X)$. We analyze the power of our test for two general learning problems i) linear regression, and ii) binary classification under mixture of Gaussian models, and show that under the proper choice of score function, an internal component of our test, with sufficient number of samples will achieve full statistical power. We evaluate our findings through extensive numerical simulations, specifically we adopt the datamodel framework (Ilyas, et al., 2022) for CIFAR-10 dataset to identify pairs of training samples with different influence on the trained model via optional black box training mechanisms.

Neural networks are promising tools for high-throughput and accurate transmission electron microscopy (TEM) analysis of nanomaterials, but are known to generalize poorly on data that is "out-of-distribution" from their training data. Given the limited set of image features typically seen in high-resolution TEM imaging, it is unclear which images are considered out-of-distribution from others. Here, we investigate how the choice of metadata features in the training dataset influences neural network performance, focusing on the example task of nanoparticle segmentation. We train and validate neural networks across curated, experimentally-collected high-resolution TEM image datasets of nanoparticles under controlled imaging and material parameters, including magnification, dosage, nanoparticle diameter, and nanoparticle material. Overall, we find that our neural networks are not robust across microscope parameters, but do generalize across certain sample parameters. Additionally, data preprocessing heavily influences the generalizability of neural networks trained on nominally similar datasets. Our results highlight the need to understand how dataset features affect deployment of data-driven algorithms.

This paper proposes a statistical framework with which artificial intelligence can improve human decision making. The performance of each human decision maker is first benchmarked against machine predictions; we then replace the decisions made by a subset of the decision makers with the recommendation from the proposed artificial intelligence algorithm. Using a large nationwide dataset of pregnancy outcomes and doctor diagnoses from prepregnancy checkups of reproductive age couples, we experimented with both a heuristic frequentist approach and a Bayesian posterior loss function approach with an application to abnormal birth detection. We find that our algorithm on a test dataset results in a higher overall true positive rate and a lower false positive rate than the diagnoses made by doctors only. We also find that the diagnoses of doctors from rural areas are more frequently replaceable, suggesting that artificial intelligence assisted decision making tends to improve precision more in less developed regions.

Automatic blood vessel segmentation from retinal images plays an important role in the diagnosis of many systemic and eye diseases, including retinopathy of prematurity. Current state-of-the-art research in blood vessel segmentation from retinal images is based on convolutional neural networks. The solutions proposed so far are trained and tested on images from a few available retinal blood vessel segmentation datasets, which might limit their performance when given an image with retinopathy of prematurity signs. In this paper, we evaluate the performance of three high-performing convolutional neural networks for retinal blood vessel segmentation in the context of blood vessel segmentation on retinopathy of prematurity retinal images. The main motive behind the study is to test if existing public datasets suffice to develop a high-performing predictor that could assist an ophthalmologist in retinopathy of prematurity diagnosis. To do so, we create a dataset consisting solely of retinopathy of prematurity images with retinal blood vessel annotations manually labeled by two observers, where one is the ophthalmologist experienced in retinopathy of prematurity treatment. Experimental results show that all three solutions have difficulties in detecting the retinal blood vessels of infants due to a lower contrast compared to images from public datasets as demonstrated by a significant drop in classification sensitivity. All three solutions segment alongside retinal also choroidal blood vessels which are not used to diagnose retinopathy of prematurity, but instead represent noise and are confused with retinal blood vessels. By visual and numerical observations, we observe that existing solutions for retinal blood vessel segmentation need improvement toward more detailed datasets or deeper models in order to assist the ophthalmologist in retinopathy of prematurity diagnosis.

In this study, we partition users by rating disposition - looking first at their percentage of negative ratings, and then at the general use of the rating scale. We hypothesize that users with different rating dispositions may use the recommender system differently and therefore the agreement with their past ratings may be less predictive of the future agreement. We use data from a large movie rating website to explore whether users should be grouped by disposition, focusing on identifying their various rating distributions that may hurt recommender effectiveness. We find that such partitioning not only improves computational efficiency but also improves top-k performance and predictive accuracy. Though such effects are largest for the user-based KNN CF, smaller for item-based KNN CF, and smallest for latent factor algorithms such as SVD.

Correlated time series analysis plays an important role in many real-world industries. Learning an efficient representation of this large-scale data for further downstream tasks is necessary but challenging. In this paper, we propose a time-step-level representation learning framework for individual instances via bootstrapped spatiotemporal representation prediction. We evaluated the effectiveness and flexibility of our representation learning framework on correlated time series forecasting and cold-start transferring the forecasting model to new instances with limited data. A linear regression model trained on top of the learned representations demonstrates our model performs best in most cases. Especially compared to representation learning models, we reduce the RMSE, MAE, and MAPE by 37%, 49%, and 48% on the PeMS-BAY dataset, respectively. Furthermore, in real-world metro passenger flow data, our framework demonstrates the ability to transfer to infer future information of new cold-start instances, with gains of 15%, 19%, and 18%. The source code will be released under the GitHub https://github.com/bonaldli/Spatiotemporal-TS-Representation-Learning