This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy, which arises due to the existence of multiple (nearly) equally well-performing models for a given dataset and task. Despite their similar performance, such models often exhibit inconsistent or even contradictory explanations for their predictions, posing challenges to end users who rely on these models to make critical decisions. Recognizing this issue, we introduce ensemble methods as an approach to enhance the consistency of the explanations provided in these scenarios. Leveraging insights from recent work on neural network loss landscapes and mode connectivity, we devise ensemble strategies to efficiently explore the underspecification set -- the set of models with performance variations resulting solely from changes in the random seed during training. Experiments on five benchmark financial datasets reveal that ensembling can yield significant improvements when it comes to explanation similarity, and demonstrate the potential of existing ensemble methods to explore the underspecification set efficiently. Our findings highlight the importance of considering model indeterminacy when interpreting explanations and showcase the effectiveness of ensembles in enhancing the reliability of explanations in machine learning.

Recent advances in synthetic data generation (SDG) have been hailed as a solution to the difficult problem of sharing sensitive data while protecting privacy. SDG aims to learn statistical properties of real data in order to generate "artificial" data that are structurally and statistically similar to sensitive data. However, prior research suggests that inference attacks on synthetic data can undermine privacy, but only for specific outlier records. In this work, we introduce a new attribute inference attack against synthetic data. The attack is based on linear reconstruction methods for aggregate statistics, which target all records in the dataset, not only outliers. We evaluate our attack on state-of-the-art SDG algorithms, including Probabilistic Graphical Models, Generative Adversarial Networks, and recent differentially private SDG mechanisms. By defining a formal privacy game, we show that our attack can be highly accurate even on arbitrary records, and that this is the result of individual information leakage (as opposed to population-level inference). We then systematically evaluate the tradeoff between protecting privacy and preserving statistical utility. Our findings suggest that current SDG methods cannot consistently provide sufficient privacy protection against inference attacks while retaining reasonable utility. The best method evaluated, a differentially private SDG mechanism, can provide both protection against inference attacks and reasonable utility, but only in very specific settings. Lastly, we show that releasing a larger number of synthetic records can improve utility but at the cost of making attacks far more effective.

In this research, we present an end-to-end data-driven pipeline for determining the long-term stability status of objects within a given environment, specifically distinguishing between static and dynamic objects. Understanding object stability is key for mobile robots since long-term stable objects can be exploited as landmarks for long-term localisation. Our pipeline includes a labelling method that utilizes historical data from the environment to generate training data for a neural network. Rather than utilizing discrete labels, we propose the use of point-wise continuous label values, indicating the spatio-temporal stability of individual points, to train a point cloud regression network named LTS-NET. Our approach is evaluated on point cloud data from two parking lots in the NCLT dataset, and the results show that our proposed solution, outperforms direct training of a classification model for static vs dynamic object classification.

The growing utilization of machine learning (ML) in decision-making processes raises questions about its benefits to society. In this study, we identify and analyze three axes of heterogeneity that significantly influence the trajectory of ML products. These axes are i) values, culture and regulations, ii) data composition, and iii) resource and infrastructure capacity. We demonstrate how these axes are interdependent and mutually influence one another, emphasizing the need to consider and address them jointly. Unfortunately, the current research landscape falls short in this regard, often failing to adopt a holistic approach. We examine the prevalent practices and methodologies that skew these axes in favor of a selected few, resulting in power concentration, homogenized control, and increased dependency. We discuss how this fragmented study of the three axes poses a significant challenge, leading to an impractical solution space that lacks reflection of real-world scenarios. Addressing these issues is crucial to ensure a more comprehensive understanding of the interconnected nature of society and to foster the democratic and inclusive development of ML systems that are more aligned with real-world complexities and its diverse requirements.

Air pollution is the origination of particulate matter, chemicals, or biological substances that brings pain to either humans or other living creatures or instigates discomfort to the natural habitat and the airspace. Hence, air pollution remains one of the paramount environmental issues as far as metropolitan cities are concerned. Several air pollution benchmarks are even said to have a negative influence on human health. Also, improper detection of air pollution benchmarks results in severe complications for humans and living creatures. To address this aspect, a novel technique called, Discretized Regression and Least Square Support Vector (DR-LSSV) based air pollution forecasting is proposed. The results indicate that the proposed DR-LSSV Technique can efficiently enhance air pollution forecasting performance and outperforms the conventional machine learning methods in terms of air pollution forecasting accuracy, air pollution forecasting time, and false positive rate.

Skin cancer holds the highest incidence rate among all cancers globally. The importance of early detection cannot be overstated, as late-stage cases can be lethal. Classifying skin lesions, however, presents several challenges due to the many variations they can exhibit, such as differences in colour, shape, and size, significant variation within the same class, and notable similarities between different classes. This paper introduces a novel class-wise attention technique that equally regards each class while unearthing more specific details about skin lesions. This attention mechanism is progressively used to amalgamate discriminative feature details from multiple scales. The introduced technique demonstrated impressive performance, surpassing more than 15 cutting-edge methods including the winners of HAM1000 and ISIC 2019 leaderboards. It achieved an impressive accuracy rate of 97.40% on the HAM10000 dataset and 94.9% on the ISIC 2019 dataset.

Early identification of high risk heart failure (HF) patients is key to timely allocation of life-saving therapies. Hemodynamic assessments can facilitate risk stratification and enhance understanding of HF trajectories. However, risk assessment for HF is a complex, multi-faceted decision-making process that can be challenging. Previous risk models for HF do not integrate invasive hemodynamics or support missing data, and use statistical methods prone to bias or machine learning methods that are not interpretable. To address these limitations, this paper presents CARNA, a hemodynamic risk stratification and phenotyping framework for advanced HF that takes advantage of the explainability and expressivity of machine learned Multi-Valued Decision Diagrams (MVDDs). This interpretable framework learns risk scores that predict the probability of patient outcomes, and outputs descriptive patient phenotypes (sets of features and thresholds) that characterize each predicted risk score. CARNA incorporates invasive hemodynamics and can make predictions on missing data. The CARNA models were trained and validated using a total of five advanced HF patient cohorts collected from previous trials, and compared with six established HF risk scores and three traditional ML risk models. CARNA provides robust risk stratification, outperforming all previous benchmarks. Although focused on advanced HF, the CARNA framework is general purpose and can be used to learn risk stratifications for other diseases and medical applications.

This paper introduces novel supervised learning techniques for real-time selection (triggering) of hadronically decaying tau leptons in proton-proton colliders. By implementing classic machine learning decision trees and advanced deep learning models, such as Multi-Layer Perceptron or residual NN, visible improvements in performance compared to standard tau triggers are observed. We show how such an implementation may lower the current energy thresholds, thus contributing to increasing the sensitivity of searches for new phenomena in proton-proton collisions classified by low-energy tau leptons.

Learning and remembering to use APIs are difficult. Several techniques have been proposed to assist developers in using APIs. Most existing techniques focus on recommending the right API methods to call, but very few techniques focus on recommending API arguments. In this paper, we propose ARIST, a novel automated argument recommendation approach which suggests arguments by predicting developers' expectations when they define and use API methods. To implement this idea in the recommendation process, ARIST combines program analysis (PA), language models (LMs), and several features specialized for the recommendation task which consider the functionality of formal parameters and the positional information of code elements (e.g., variables or method calls) in the given context. In ARIST, the LMs and the recommending features are used to suggest the promising candidates identified by PA. Meanwhile, PA navigates the LMs and the features working on the set of the valid candidates which satisfy syntax, accessibility, and type-compatibility constraints defined by the programming language in use. Our evaluation on a large dataset of real-world projects shows that ARIST improves the state-of-the-art approach by 19% and 18% in top-1 precision and recall for recommending arguments of frequently-used libraries. For general argument recommendation task, i.e., recommending arguments for every method call, ARIST outperforms the baseline approaches by up to 125% top-1 accuracy. Moreover, for newly-encountered projects, ARIST achieves more than 60% top-3 accuracy when evaluating on a larger dataset. For working/maintaining projects, with a personalized LM to capture developers' coding practice, ARIST can productively rank the expected arguments at the top-1 position in 7/10 requests.

To assess the accuracy of parameter estimates or predictions without specific distributional knowledge of the data, the idea of re-sampling or sub-sampling on the available data has been long-established to construct prediction intervals, and there is a rich history in the statistics literature on the jackknife and bootstrap methods, see Stine (1985), Efron (1979), Quenouille (1949), Efron and Gong (1983). Among these re-sampling methods, leave-one-out methods (generally referred to as "cross-validation" or "jackknife") are widely used to assess or calibrate predictive accuracy, and can be found in a large line of literature (Stone, 1974, Geisser, 1975). While it has been demonstrated in a large body of past work with extensive evidence that jackknifetype methods have reliable empirical performance, the theoretical properties of these types of methods are studied relatively little until recently, see Steinberger and Leeb (2018), Bousquet and Elisseeff (2002). One of the most important results among these theoretically guaranteed works is Foygel Barber et al. (2019), which introduces a crucial modification compared to the traditional jackknife method that permits rigorous coverage guarantees of at least 1 2α regardless of the distribution of the data points, for any algorithm that treats the training points symmetrically. We will revisit this work and give more relative details in Section 2.1. Although theoretically jackknife+ has been proven to have coverage guarantees without distributional assumptions, in practice, this method is computationally costly, since we need to train n (which is the training sample size) leave-one-out models from scratch to find the predictive interval. Especially for large and complicated models like neural networks, this computational cost is prohibitive. The goal of this paper is to provide a fast algorithm that provides similar theoretical coverage guarantees to those in jackknife+. To achieve this goal, we develop a new procedure, called Differentially Private Lazy Predictive Inference (DP-Lazy PI), which combines two ideas: lazy training of neural networks and differentially private stochcastic gradient descent (DP-SGD).