Machine Learning (ML) software employs statistical algorithms to perform high-stake tasks in our daily lives, whose results are usually discriminatory due to protected features (e.g., gender), i.e., one part (called privileged, e.g., male) may be more likely to obtain beneficial decisions than the other part (called unprivileged, e.g., female). In alleviating the unfairness, developers have obtained widely held beliefs about the tradeoff between performance and fairness for ML software. Surprisingly, recent research on feature engineering suggests that enlarging the feature set is the perfect way to kill two birds with one stone, i.e., achieving both higher performance and fairness. However, the experiments used in the prior study did not remove the effect of protected features, which have been suggested to be excluded in both industrial applications and academic studies. As a result, the study did not fully explore the tradeoff between performance and fairness. In this article, we first conduct an empirical study to replicate this prior study after excluding the protected features and observe that there is still a tradeoff between performance and fairness with enlarging the features, i.e., more features are not perfect, which would lead to higher performance and lower fairness. Due to more features causing more collection and pre-processing budgets, we aim to search for an effective alternative. Inspired by the “less is more” principle, we propose a novel feature ranking method, Hybrid-importance and Early-validation based Feature Ranking (HEFR) , to find an efficient subset to replace the full feature set with comparable performance and fairness. Our method, HEFR, employs hybrid feature importances to combine performance and fairness and conducts early validation to check the effectiveness of hybrid importances. We conduct experiments on seven datasets and three classifiers to evaluate our method with five baselines. The results have shown that (a) HEFR is efficient for ML software feature engineering: applying HEFR to choose about 10% of features would construct ML software with better or comparable performance and fairness, and (b) HEFR is actionable with small dataset sizes: applying HEFR with only 10% data size would still help choose the proper feature subset.

The objective of transfer learning is to enhance estimation and inference in a target data by leveraging knowledge gained from additional sources. Recent studies have explored transfer learning for independent observations in complex, high-dimensional models assuming sparsity, yet research on time series models remains limited. Our focus is on transfer learning for sequences of observations with temporal dependencies and a more intricate model parameter structure. Specifically, we investigate the vector autoregressive model (VAR), a widely recognized model for time series data, where the transition matrix can be deconstructed into a combination of a sparse matrix and a low-rank one. We propose a new transfer learning algorithm tailored for estimating high-dimensional VAR models characterized by low-rank and sparse structures. Additionally, we present a novel approach for selecting informative observations from auxiliary datasets. Theoretical guarantees are established, encompassing model parameter consistency, informative set selection, and the asymptotic distribution of estimators under mild conditions. The latter facilitates the construction of entry-wise confidence intervals for model parameters. Finally, we demonstrate the empirical efficacy of our methodologies through both simulated and real-world datasets.

Deep learning (DL) models have proven to be highly successful and are now essential to our everyday routines. However, DL models, like traditional software, inevitably contain bugs that affect their performance in real-world scenarios. Effective software engineering techniques are necessary to ensure their dependability. In recent years, fault localization methods for DL models have gained significant attention as a valuable tool for improving the reliability of DL models. Owing to the data-driven programming paradigm, traditional fault localization techniques are challenging to apply directly to DL programs. Previous studies have shown that neuron errors within models can lead to abnormal behavior, and they fix the DL model errors from the perspective of neurons. Nonetheless, there remains a significant gap between the DL program statement and model errors. To tackle this problem, this paper proposes a novel fault localization method for DL models, named wei G hted s U sp I ciousness an D balanc E d agg R egation ( \(\mathsf{GUIDER}\) ) that revisits the idea and challenge of spectrum-based fault localization in the context of DL models. For pre-trained DL models, \(\mathsf{GUIDER}\) utilizes neuron coverage information and test case confidence to compute weighted neuron suspiciousness values and employs balanced aggregation methods to elevate these values from the neuron level to the layer level, which establishes a bridge between the DL model and the DL program, facilitating the developers’ debugging process. We evaluate \(\mathsf{GUIDER}\) using 161 real model bugs collected from StackOverflow and five state-of-the-art fault localization methods for DL models as baselines. The results indicate that (a) our method successfully localizes 67% of the model bugs by ranking the buggy layer to the first place (i.e., top- \(1\) ), significantly outperforming all five baselines, and (b) our method maintains an acceptable time overhead compared with all baseline methods.

Summary Natural language inference (NLI) is a task to infer the relationship between the premise and hypothesis sentences, whose models have essential applications in the many natural language processing (NLP) fields, for example, machine reading comprehension and recognizing textual entailment. Due to the data‐driven programming paradigm, bugs inevitably occur in NLI models during the application process, which calls for novel automatic testing techniques to deal with NLI testing challenges. The main difficulty in achieving automatic testing for NLI models is the oracle problem; that is, it may be too expensive to label NLI model inputs manually and hence be too challenging to verify the correctness of model outputs. To tackle the oracle problem, this study proposes a novel automatic testing method hybrid mutation driven testing (HMT), which extends the mutation idea applied in other NLP domains successfully. Specifically, as there are two sets of sentences, that is, premise and hypothesis, to be mutated, we propose four mutation operators to achieve the hybrid mutation strategy, which mutate the premise and the hypothesis sentences jointly or individually. We assume that the mutation would not affect the outputs; that is, if the original and mutated outputs are inconsistent, inconsistency bugs could be detected without knowing the true labels. To evaluate our method HMT, we conduct experiments on two widely used datasets with two advanced models and generate more than 520,000 mutations by applying our mutation operators. Our experimental results show that (a) our method, HMT, can effectively generate mutated testing samples, (b) our method can effectively trigger the inconsistency bugs of the NLI models, and (c) all four mutation operators can independently trigger inconsistency bugs.

The calling relationship between projects becomes complicated as the number of open-source projects increases. Different issues across projects can also be related, referred to as cross-project correlated issues (CPCIs), and bring new challenges for developers to fix these issues. When solving these CPCIs, developers have to accurately locate the source code that causes it in the current project and also needs to know the related issues in other projects. However, few studies have proposed specific methods to help developers effectively address these CPCIs, i.e., find related issues for CPCIs.

Background. Code-line-level bugginess identification (CLBI) is a vital technique that can facilitate developers to identify buggy lines without expending a large amount of human effort. Most of the existing studies tried to mine the characteristics of source codes to train supervised prediction models, which have been reported to be able to discriminate buggy code lines amongst others in a target program. Problem. However, several simple and clear code characteristics, such as complexity of code lines, have been disregarded in the current literature. Such characteristics can be acquired and applied easily in an unsupervised way to conduct more accurate CLBI, which also can decrease the application cost of existing CLBI approaches by a large margin. Objective. We aim at investigating the status quo in the field of CLBI from the perspective of (1) how far we have really come in the literature, and (2) how far we have yet to go in the industry, by analyzing the performance of state-of-the-art (SOTA) CLBI approaches and tools, respectively. Method. We propose a simple heuristic baseline solution GLANCE (aimin G at contro L - AN d C ompl E x-statements) with three implementations (i.e., GLANCE-MD, GLANCE-EA, and GLANCE-LR). GLANCE is a two-stage CLBI framework: first, use a simple model to predict the potentially defective files; second, leverage simple code characteristics to identify buggy code lines in the predicted defective files. We use GLANCE as the baseline to investigate the effectiveness of the SOTA CLBI approaches, including natural language processing (NLP) based, model interpretation techniques (MIT) based, and popular static analysis tools (SAT). Result. Based on 19 open-source projects with 142 different releases, the experimental results show that GLANCE framework has a prediction performance comparable or even superior to the existing SOTA CLBI approaches and tools in terms of 8 different performance indicators. Conclusion. The results caution us that, if the identification performance is the goal, the real progress in CLBI is not being achieved as it might have been envisaged in the literature and there is still a long way to go to really promote the effectiveness of static analysis tools in industry. In addition, we suggest using GLANCE as a baseline in future studies to demonstrate the usefulness of any newly proposed CLBI approach.

Deep neural networks are powerful tools to model observations over time with non-linear patterns. Despite the widespread useof neural networks in such settings, most theoretical developments of deep neural networks are under the assumption of independent observations, and theoretical results for temporally dependent observations are scarce. To bridge this gap, we study theoretical properties of deep neural networks on modeling non-linear time series data. Specifically, non-asymptotic bounds for prediction error of (sparse) feed-forward neural network with ReLU activation function is established under mixing-type assumptions. These assumptions are mild such that they include a wide range of time series models including auto-regressive models. Compared to independent observations, established convergence rates have additional logarithmic factors to compensate for additional complexity due to dependence among data points. The theoretical results are supported via various numerical simulation settings as well as an application to a macroeconomic data set.

Reentrancy bugs, one of the most severe vulnerabilities in smart contracts, have caused huge financial loss in recent years. Researchers have proposed many approaches to detecting them. However, empirical studies have shown that these approaches suffer from undesirable false positives and false negatives, when the code under detection involves the interaction between multiple smart contracts.