Defect prediction is one of the most popular research topics due to its potential to minimize software quality assurance efforts. Existing approaches have examined defect prediction from various perspectives such as complexity and developer metrics. However, none of these consider programming style for defect prediction. This paper aims at analyzing the impact of stylistic metrics on both within-project and crossproject defect prediction. For prediction, 4 widely used machine learning algorithms namely Naive Bayes, Support Vector Machine, Decision Tree and Logistic Regression are used. The experiment is conducted on 14 releases of 5 popular, open source projects. F1, Precision and Recall are inspected to evaluate the results. Results reveal that stylistic metrics are a good predictor of defects.

Group fairness ensures that the outcome of machine learning (ML) based decision making systems are not biased towards a certain group of people defined by a sensitive attribute such as gender or ethnicity. Achieving group fairness in Federated Learning (FL) is challenging because mitigating bias inherently requires using the sensitive attribute values of all clients, while FL is aimed precisely at protecting privacy by not giving access to the clients' data. As we show in this paper, this conflict between fairness and privacy in FL can be resolved by combining FL with Secure Multiparty Computation (MPC) and Differential Privacy (DP). In doing so, we propose a method for training group-fair ML models in cross-device FL under complete and formal privacy guarantees, without requiring the clients to disclose their sensitive attribute values. Empirical evaluations on real world datasets demonstrate the effectiveness of our solution to train fair and accurate ML models in federated cross-device setups with privacy guarantees to the users.

Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This "hold-speaker(s)-out" data partitioning strategy, however, may not be ideal for data sets in which the number of speakers is very small. This study investigates ten different data split methods for five languages with minimal ASR training resources. We find that (1) model performance varies greatly depending on which speaker is selected for testing; (2) the average word error rate (WER) across all held-out speakers is comparable not only to the average WER over multiple random splits but also to any given individual random split; (3) WER is also generally comparable when the data is split heuristically or adversarially; (4) utterance duration and intensity are comparatively more predictive factors of variability regardless of the data split. These results suggest that the widely used hold-speakers-out approach to ASR data partitioning can yield results that do not reflect model performance on unseen data or speakers. Random splits can yield more reliable and generalizable estimates when facing data sparsity.

Text representations learned by machine learning models often encode undesirable demographic information of the user. Predictive models based on these representations can rely on such information, resulting in biased decisions. We present a novel debiasing technique, Fairness-aware Rate Maximization (FaRM), that removes protected information by making representations of instances belonging to the same protected attribute class uncorrelated, using the rate-distortion function. FaRM is able to debias representations with or without a target task at hand. FaRM can also be adapted to remove information about multiple protected attributes simultaneously. Empirical evaluations show that FaRM achieves state-of-the-art performance on several datasets, and learned representations leak significantly less protected attribute information against an attack by a non-linear probing network.

Currency is used almost everywhere to facilitate business. In most developing countries, especially the ones in Africa, tangible notes are predominantly used in everyday financial transactions. One of these countries, Ethiopia, is believed to have one of the world highest rates of blindness (1.6%) and low vision (3.7%). There are around 4 million visually impaired people; With 1.7 million people being in complete vision loss. Those people face a number of challenges when they are in a bus station, in shopping centers, or anywhere which requires the physical exchange of money. In this paper, we try to provide a solution to this issue using AI/ML applications. We developed an Android and IOS compatible mobile application with a model that achieved 98.9% classification accuracy on our dataset. The application has a voice integrated feature that tells the type of the scanned currency in Amharic, the working language of Ethiopia. The application is developed to be easily accessible by its users. It is build to reduce the burden of visually impaired people in Ethiopia.

Tabular data typically contains private and important information; thus, precautions must be taken before they are shared with others. Although several methods (e.g., differential privacy and k-anonymity) have been proposed to prevent information leakage, in recent years, tabular data synthesis models have become popular because they can well trade-off between data utility and privacy. However, recent research has shown that generative models for image data are susceptible to the membership inference attack, which can determine whether a given record was used to train a victim synthesis model. In this paper, we investigate the membership inference attack in the context of tabular data synthesis. We conduct experiments on 4 state-of-the-art tabular data synthesis models under two attack scenarios (i.e., one black-box and one white-box attack), and find that the membership inference attack can seriously jeopardize these models. We next conduct experiments to evaluate how well two popular differentially-private deep learning training algorithms, DP-SGD and DP-GAN, can protect the models against the attack. Our key finding is that both algorithms can largely alleviate this threat by sacrificing the generation quality.

Machine learning has opened up new tools for financial fraud detection. Using a sample of annotated transactions, a machine learning classification algorithm learns to detect frauds. With growing credit card transaction volumes and rising fraud percentages there is growing interest in finding appropriate machine learning classifiers for detection. However, fraud data sets are diverse and exhibit inconsistent characteristics. As a result, a model effective on a given data set is not guaranteed to perform on another. Further, the possibility of temporal drift in data patterns and characteristics over time is high. Additionally, fraud data has massive and varying imbalance. In this work, we evaluate sampling methods as a viable pre-processing mechanism to handle imbalance and propose a data-driven classifier selection strategy for characteristic highly imbalanced fraud detection data sets. The model derived based on our selection strategy surpasses peer models, whilst working in more realistic conditions, establishing the effectiveness of the strategy.

With growing credit card transaction volumes, the fraud percentages are also rising, including overhead costs for institutions to combat and compensate victims. The use of machine learning into the financial sector permits more effective protection against fraud and other economic crime. Suitably trained machine learning classifiers help proactive fraud detection, improving stakeholder trust and robustness against illicit transactions. However, the design of machine learning based fraud detection algorithms has been challenging and slow due the massively unbalanced nature of fraud data and the challenges of identifying the frauds accurately and completely to create a gold standard ground truth. Furthermore, there are no benchmarks or standard classifier evaluation metrics to measure and identify better performing classifiers, thus keeping researchers in the dark. In this work, we develop a theoretical foundation to model human annotation errors and extreme imbalance typical in real world fraud detection data sets. By conducting empirical experiments on a hypothetical classifier, with a synthetic data distribution approximated to a popular real world credit card fraud data set, we simulate human annotation errors and extreme imbalance to observe the behavior of popular machine learning classifier evaluation matrices. We demonstrate that a combined F1 score and g-mean, in that specific order, is the best evaluation metric for typical imbalanced fraud detection model classification.

Topology inference for network systems (NSs) plays a crucial role in many areas. This paper advocates a causality-based method based on noisy observations from a single trajectory of a NS, which is represented by the state-space model with general directed topology. Specifically, we first prove its close relationships with the ideal Granger estimator for multiple trajectories and the traditional ordinary least squares (OLS) estimator for a single trajectory. Along with this line, we analyze the non-asymptotic inference performance of the proposed method by taking the OLS estimator as a reference, covering both asymptotically and marginally stable systems. The derived convergence rates and accuracy results suggest the proposed method has better performance in addressing potentially correlated observations and achieves zero inference error asymptotically. Besides, an online/recursive version of our method is established for efficient computation or time-varying cases. Extensions on NSs with nonlinear dynamics are also discussed. Comprehensive tests corroborate the theoretical findings and comparisons with other algorithms highlight the superiority of the proposed method.

Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today. However, such efforts have coalesced around a small subset of languages, leaving behind the vast majority of mostly low-resource languages. What does it take to break the 200 language barrier while ensuring safe, high quality results, all while keeping ethical considerations in mind? In No Language Left Behind, we took on this challenge by first contextualizing the need for low-resource language translation support through exploratory interviews with native speakers. Then, we created datasets and models aimed at narrowing the performance gap between low and high-resource languages. More specifically, we developed a conditional compute model based on Sparsely Gated Mixture of Experts that is trained on data obtained with novel and effective data mining techniques tailored for low-resource languages. We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. Critically, we evaluated the performance of over 40,000 different translation directions using a human-translated benchmark, Flores-200, and combined human evaluation with a novel toxicity benchmark covering all languages in Flores-200 to assess translation safety. Our model achieves an improvement of 44% BLEU relative to the previous state-of-the-art, laying important groundwork towards realizing a universal translation system.