Tao Xie

Linyi Li, Yuhao Zhang, Luyao Ren et al. · pku

With the widespread deployment of deep neural networks (DNNs), ensuring the reliability of DNN-based systems is of great importance. Serious reliability issues such as system failures can be caused by numerical defects, one of the most frequent defects in DNNs. To assure high reliability against numerical defects, in this paper, we propose the RANUM approach including novel techniques for three reliability assurance tasks: detection of potential numerical defects, confirmation of potential-defect feasibility, and suggestion of defect fixes. To the best of our knowledge, RANUM is the first approach that confirms potential-defect feasibility with failure-exhibiting tests and suggests fixes automatically. Extensive experiments on the benchmarks of 63 real-world DNN architectures show that RANUM outperforms state-of-the-art approaches across the three reliability assurance tasks. In addition, when the RANUM-generated fixes are compared with developers' fixes on open-source projects, in 37 out of 40 cases, RANUM-generated fixes are equivalent to or even better than human fixes.

Linyi Li, Jiawei Zhang, Tao Xie et al.

Neural networks (NNs) are known to be vulnerable against adversarial perturbations, and thus there is a line of work aiming to provide robustness certification for NNs, such as randomized smoothing, which samples smoothing noises from a certain distribution to certify the robustness for a smoothed classifier. However, as shown by previous work, the certified robust radius in randomized smoothing suffers from scaling to large datasets ("curse of dimensionality"). To overcome this hurdle, we propose a Double Sampling Randomized Smoothing (DSRS) framework, which exploits the sampled probability from an additional smoothing distribution to tighten the robustness certification of the previous smoothed classifier. Theoretically, under mild assumptions, we prove that DSRS can certify $Θ(\sqrt d)$ robust radius under $\ell_2$ norm where $d$ is the input dimension, implying that DSRS may be able to break the curse of dimensionality of randomized smoothing. We instantiate DSRS for a generalized family of Gaussian smoothing and propose an efficient and sound computing method based on customized dual optimization considering sampling error. Extensive experiments on MNIST, CIFAR-10, and ImageNet verify our theory and show that DSRS certifies larger robust radii than existing baselines consistently under different settings. Code is available at https://github.com/llylly/DSRS.

Xinzhou Jin, Jintang Li, Liang Chen et al.

Graph neural networks (GNNs) have recently emerged as an effective approach to model neighborhood signals in collaborative filtering. Towards this research line, graph contrastive learning (GCL) demonstrates robust capabilities to address the supervision label shortage issue through generating massive self-supervised signals. Despite its effectiveness, GCL for recommendation suffers seriously from two main challenges: i) GCL relies on graph augmentation to generate semantically different views for contrasting, which could potentially disrupt key information and introduce unwanted noise; ii) current works for GCL primarily focus on contrasting representations using sophisticated networks architecture (usually deep) to capture high-order interactions, which leads to increased computational complexity and suboptimal training efficiency. To this end, we propose L2CL, a principled Layer-to-Layer Contrastive Learning framework that contrasts representations from different layers. By aligning the semantic similarities between different layers, L2CL enables the learning of complex structural relationships and gets rid of the noise perturbation in stochastic data augmentation. Surprisingly, we find that L2CL, using only one-hop contrastive learning paradigm, is able to capture intrinsic semantic structures and improve the quality of node representation, leading to a simple yet effective architecture. We also provide theoretical guarantees for L2CL in minimizing task-irrelevant information. Extensive experiments on five real-world datasets demonstrate the superiority of our model over various state-of-the-art collaborative filtering methods. Our code is available at https://github.com/downeykking/L2CL.

Tao Xie, Kun Dai, Ke Wang et al.

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods. The key insight is that local feature matcher with deep layers can capture more human-intuitive and simpler-to-match features. Based on this, we propose a Slimming Transformer (SlimFormer) dedicated for DeepMatcher, which leverages vector-based attention to model relevance among all keypoints and achieves long-range context aggregation in an efficient and effective manner. A relative position encoding is applied to each SlimFormer so as to explicitly disclose relative distance information, further improving the representation of keypoints. A layer-scale strategy is also employed in each SlimFormer to enable the network to assimilate message exchange from the residual block adaptively, thus allowing it to simulate the human behaviour that humans can acquire different matching cues each time they scan an image pair. To facilitate a better adaption of the SlimFormer, we introduce a Feature Transition Module (FTM) to ensure a smooth transition in feature scopes with different receptive fields. By interleaving the self- and cross-SlimFormer multiple times, DeepMatcher can easily establish pixel-wise dense matches at coarse level. Finally, we perceive the match refinement as a combination of classification and regression problems and design Fine Matches Module to predict confidence and offset concurrently, thereby generating robust and accurate matches. Experimentally, we show that DeepMatcher significantly outperforms the state-of-the-art methods on several benchmarks, demonstrating the superior matching capability of DeepMatcher.

Qifeng Cai, Hao Liang, Chang Xu et al.

The data-centric paradigm has become pivotal in AI, especially for Text-to-SQL, where performance is limited by scarce, simplistic, and low-diversity datasets. To address this, we propose Text2SQL-Flow, a SQL-aware data augmentation framework that generates large-scale, semantically valid, and structurally diverse Text-to-SQL pairs from minimal seed data. It operates across six augmentation dimensions and integrates an end-to-end pipeline featuring SQL execution verification, natural language question generation, chain-of-thought reasoning traces, and data classification. A modular Database Manager ensures cross-database compatibility and scalability. Using this framework, we build SQLFlow, a high-quality dataset of 89,544 annotated examples. We evaluate SQLFlow in two settings: (1) For open-source LLMs, fine-tuning on SQLFlow consistently improves performance across benchmarks under the same data budget. (2) For closed-source LLMs, we introduce a masked alignment retrieval method that treats SQLFlow as both knowledge base and training data for the retriever. This enables structure-aware example matching by modeling fine-grained alignments between questions and SQL queries. Experiments show our retrieval strategy outperforms existing methods, underscoring the value of SQLFlow's high-fidelity data and our novel technique. Our work establishes a scalable, data-centric foundation for advancing Text-to-SQL systems and highlights the critical role of high-quality structured data in modern AI.

Yuanzhen Xie, Xinzhou Jin, Tao Xie et al.

In-context learning of large-language models (LLMs) has achieved remarkable success in the field of natural language processing, while extensive case studies reveal that the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL. To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition. Specifically, the information determination module for eliminating redundant information and the brand-new prompt structure based on problem classification greatly enhance the model's attention. Additionally, the inclusion of self-correction and active learning modules greatly expands the problem-solving scope of LLMs, hence improving the upper limit of LLM-based approaches. Extensive experiments conducted on three datasets demonstrate that our approach outperforms other methods by a significant margin. About 2-3 percentage point improvements compared to the existing baseline on the Spider Dev, Spider-Realistic, and Bird Dev datasets and new SOTA results on the Spider Test dataset are achieved. Our code is available on GitHub: \url{https://github.com/FlyingFeather/DEA-SQL}.

Linyi Li, Shijie Geng, Zhenwen Li et al.

Large Language Models for code (code LLMs) have witnessed tremendous progress in recent years. With the rapid development of code LLMs, many popular evaluation benchmarks, such as HumanEval, DS-1000, and MBPP, have emerged to measure the performance of code LLMs with a particular focus on code generation tasks. However, they are insufficient to cover the full range of expected capabilities of code LLMs, which span beyond code generation to answering diverse coding-related questions. To fill this gap, we propose InfiBench, the first large-scale freeform question-answering (QA) benchmark for code to our knowledge, comprising 234 carefully selected high-quality Stack Overflow questions that span across 15 programming languages. InfiBench uses four types of model-free automatic metrics to evaluate response correctness where domain experts carefully concretize the criterion for each question. We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings. Our detailed analyses showcase potential directions for further advancement of code LLMs. InfiBench is fully open source at https://infi-coder.github.io/infibench and continuously expanding to foster more scientific and systematic practices for code LLM evaluation.

Yibo He, Shuoran Zhao, Jiaming Huang et al.

SIMD (Single Instruction Multiple Data) instructions and their compiler intrinsics are widely supported by modern processors to accelerate performance-critical tasks. SIMD intrinsic programming, a trade-off between coding productivity and high performance, is widely used in the development of mainstream performance-critical libraries and daily computing tasks. Large Language Models (LLMs), which have demonstrated strong and comprehensive capabilities in code generation, show promise in assisting programmers with the challenges of SIMD intrinsic programming. However, existing code-generation benchmarks focus on only scalar code, and it is unclear how LLMs perform in generating vectorized code using SIMD intrinsics. To fill this gap, we propose SimdBench, the first code benchmark specifically designed for SIMD-intrinsic code generation, comprising 136 carefully crafted tasks and targeting five representative SIMD intrinsics: SSE (x86 Streaming SIMD Extension), AVX (x86 Advanced Vector Extension), Neon (ARM Advanced SIMD Extension), SVE (ARM Scalable Vector Extension), and RVV (RISC-V Vector Extension). We conduct a systematic evaluation (measuring both correctness and performance) of 18 representative LLMs on SimdBench, resulting in a series of novel and insightful findings. Our evaluation results demonstrate that LLMs exhibit a universal decrease in pass@k during SIMD-intrinsic code generation compared to scalar-code generation. Our in-depth analysis highlights promising directions for the further advancement of LLMs in the challenging domain of SIMD-intrinsic code generation. SimdBench is fully open source at https://anonymous.4open.science/r/SimdBench-1B3F/ to benefit the broader research community.

Yuanzhen Xie, Tao Xie, Mingxiong Lin et al.

In most current research, large language models (LLMs) are able to perform reasoning tasks by generating chains of thought through the guidance of specific prompts. However, there still exists a significant discrepancy between their capability in solving complex reasoning problems and that of humans. At present, most approaches focus on chains of thought (COT) and tool use, without considering the adoption and application of human cognitive frameworks. It is well-known that when confronting complex reasoning challenges, humans typically employ various cognitive abilities, and necessitate interaction with all aspects of tools, knowledge, and the external environment information to accomplish intricate tasks. This paper introduces a novel intelligent framework, referred to as OlaGPT. OlaGPT carefully studied a cognitive architecture framework, and propose to simulate certain aspects of human cognition. The framework involves approximating different cognitive modules, including attention, memory, reasoning, learning, and corresponding scheduling and decision-making mechanisms. Inspired by the active learning mechanism of human beings, it proposes a learning unit to record previous mistakes and expert opinions, and dynamically refer to them to strengthen their ability to solve similar problems. The paper also outlines common effective reasoning frameworks for human problem-solving and designs Chain-of-Thought (COT) templates accordingly. A comprehensive decision-making mechanism is also proposed to maximize model accuracy. The efficacy of OlaGPT has been stringently evaluated on multiple reasoning datasets, and the experimental outcomes reveal that OlaGPT surpasses state-of-the-art benchmarks, demonstrating its superior performance. Our implementation of OlaGPT is available on GitHub: \url{https://github.com/oladata-team/OlaGPT}.

Linyi Li, Tao Xie, Bo Li

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when deploying these models to safety-critical applications such as autonomous driving. Different defense approaches have been proposed against adversarial attacks, including: a) empirical defenses, which can usually be adaptively attacked again without providing robustness certification; and b) certifiably robust approaches, which consist of robustness verification providing the lower bound of robust accuracy against any attacks under certain conditions and corresponding robust training approaches. In this paper, we systematize certifiably robust approaches and related practical and theoretical implications and findings. We also provide the first comprehensive benchmark on existing robustness verification and training approaches on different datasets. In particular, we 1) provide a taxonomy for the robustness verification and training approaches, as well as summarize the methodologies for representative algorithms, 2) reveal the characteristics, strengths, limitations, and fundamental connections among these approaches, 3) discuss current research progresses, theoretical barriers, main challenges, and future directions for certifiably robust approaches for DNNs, and 4) provide an open-sourced unified platform to evaluate 20+ representative certifiably robust approaches.

Jintang Li, Tao Xie, Liang Chen et al.

Recent studies have shown that graph neural networks (GNNs) are vulnerable against perturbations due to lack of robustness and can therefore be easily fooled. Currently, most works on attacking GNNs are mainly using gradient information to guide the attack and achieve outstanding performance. However, the high complexity of time and space makes them unmanageable for large scale graphs and becomes the major bottleneck that prevents the practical usage. We argue that the main reason is that they have to use the whole graph for attacks, resulting in the increasing time and space complexity as the data scale grows. In this work, we propose an efficient Simplified Gradient-based Attack (SGA) method to bridge this gap. SGA can cause the GNNs to misclassify specific target nodes through a multi-stage attack framework, which needs only a much smaller subgraph. In addition, we present a practical metric named Degree Assortativity Change (DAC) to measure the impacts of adversarial attacks on graph data. We evaluate our attack method on four real-world graph networks by attacking several commonly used GNNs. The experimental results demonstrate that SGA can achieve significant time and memory efficiency improvements while maintaining competitive attack performance compared to state-of-art attack techniques. Codes are available via: https://github.com/EdisonLeeeee/SGAttack.

Liang Chen, Jintang Li, Jiaying Peng et al.

Deep learning models on graphs have achieved remarkable performance in various graph analysis tasks, e.g., node classification, link prediction, and graph clustering. However, they expose uncertainty and unreliability against the well-designed inputs, i.e., adversarial examples. Accordingly, a line of studies has emerged for both attack and defense addressed in different graph analysis tasks, leading to the arms race in graph adversarial learning. Despite the booming works, there still lacks a unified problem definition and a comprehensive review. To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically. Specifically, we survey and unify the existing works w.r.t. attack and defense in graph analysis tasks, and give appropriate definitions and taxonomies at the same time. Besides, we emphasize the importance of related evaluation metrics, investigate and summarize them comprehensively. Hopefully, our works can provide a comprehensive overview and offer insights for the relevant researchers. Latest advances in graph adversarial learning are summarized in our GitHub repository https://github.com/EdisonLeeeee/Graph-Adversarial-Learning.

Zhenwen Li, Tao Xie

Text-to-SQL models can generate a list of candidate SQL queries, and the best query is often in the candidate list, but not at the top of the list. An effective re-rank method can select the right SQL query from the candidate list and improve the model's performance. Previous studies on code generation automatically generate test cases and use them to re-rank candidate codes. However, automatic test case generation for text-to-SQL is an understudied field. We propose an automatic test case generation method that first generates a database and then uses LLMs to predict the ground truth, which is the expected execution results of the ground truth SQL query on this database. To reduce the difficulty for LLMs to predict, we conduct experiments to search for ways to generate easy databases for LLMs and design easy-to-understand prompts. Based on our test case generation method, we propose a re-rank method to select the right SQL query from the candidate list. Given a candidate list, our method can generate test cases and re-rank the candidate list according to their pass numbers on these test cases and their generation probabilities. The experiment results on the validation dataset of Spider show that the performance of some state-of-the-art models can get a 3.6\% improvement after applying our re-rank method.

Jie Zhu, Leye Wang, Xiao Han et al.

The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, hindering the large-scale deployment on resource-restricted devices (e.g., smartphones). To mitigate this issue, AI software compression plays a crucial role, which aims to compress model size while keeping high performance. However, the intrinsic defects in a big model may be inherited by the compressed one. Such defects may be easily leveraged by adversaries, since a compressed model is usually deployed in a large number of devices without adequate protection. In this article, we aim to address the safe model compression problem from the perspective of safety-performance co-optimization. Specifically, inspired by the test-driven development (TDD) paradigm in software engineering, we propose a test-driven sparse training framework called SafeCompress. By simulating the attack mechanism as safety testing, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm. Then, considering two kinds of representative and heterogeneous attack mechanisms, i.e., black-box membership inference attack and white-box membership inference attack, we develop two concrete instances called BMIA-SafeCompress and WMIA-SafeCompress. Further, we implement another instance called MMIA-SafeCompress by extending SafeCompress to defend against the occasion when adversaries conduct black-box and white-box membership inference attacks simultaneously. We conduct extensive experiments on five datasets for both computer vision and natural language processing tasks. The results show the effectiveness and generalizability of our framework. We also discuss how to adapt SafeCompress to other attacks besides membership inference attack, demonstrating the flexibility of SafeCompress.

Dezhi Ran, Yuan Cao, Mengzhou Wu et al.

Large language models (LLMs) have demonstrated remarkable capability in function-level code generation tasks. Unlike isolated functions, real-world applications demand reasoning over the entire software system: developers must orchestrate how different components interact, maintain consistency across states over time, and ensure the application behaves correctly within the lifecycle and framework constraints. Yet, no existing benchmark adequately evaluates whether LLMs can bridge this gap and construct entire software systems from scratch. To address this gap, we propose APPFORGE, a benchmark consisting of 101 software development problems drawn from real-world Android apps. Given a natural language specification detailing the app functionality, a language model is tasked with implementing the functionality into an Android app from scratch. Developing an Android app from scratch requires understanding and coordinating app states, lifecycle management, and asynchronous operations, calling for LLMs to generate context-aware, robust, and maintainable code. To construct APPFORGE, we design a multi-agent system to automatically summarize the main functionalities from app documents and navigate the app to synthesize test cases validating the functional correctness of app implementation. Following rigorous manual verification by Android development experts, APPFORGE incorporates the test cases within an automated evaluation framework that enables reproducible assessment without human intervention, making it easily adoptable for future research. Our evaluation on 12 flagship LLMs show that all evaluated models achieve low effectiveness, with the best-performing model (GPT-5) developing only 18.8% functionally correct applications, highlighting fundamental limitations in current models' ability to handle complex, multi-component software engineering challenges.

Dong Chen, Shaoxin Lin, Muhan Zeng et al.

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs and add new features within code Repository. On SWE-bench lite, CodeR is able to solve 28.33% of issues, when submitting only once for each issue. We examine the performance impact of each design of CodeR and offer insights to advance this research direction.

Hanzhang Wang, Zhengkai Wu, Huai Jiang et al.

For large-scale distributed systems, it's crucial to efficiently diagnose the root causes of incidents to maintain high system availability. The recent development of microservice architecture brings three major challenges (i.e., operation, system scale, and monitoring complexities) to root cause analysis (RCA) in industrial settings. To tackle these challenges, in this paper, we present Groot, an event-graph-based approach for RCA. Groot constructs a real-time causality graph based on events that summarize various types of metrics, logs, and activities in the system under analysis. Moreover, to incorporate domain knowledge from site reliability engineering (SRE) engineers, Groot can be customized with user-defined events and domain-specific rules. Currently, Groot supports RCA among 5,000 real production services and is actively used by the SRE teamin a global e-commerce system serving more than 185 million active buyers per year. Over 15 months, we collect a data setcontaining labeled root causes of 952 real production incidents for evaluation. The evaluation results show that Groot is able to achieve 95% top-3 accuracy and 78% top-1 accuracy. To share our experience in deploying and adopting RCA in industrial settings, we conduct survey to show that users of Grootfindit helpful and easy to use. We also share the lessons learnedfrom deploying and adopting Grootto solve RCA problems inproduction environments.

Qilin Xiang, Xin Peng, Chuan He et al.

Microservice architecture advocates a number of technologies and practices such as lightweight container, container orchestration, and DevOps, with the promised benefits of faster delivery, improved scalability, and greater autonomy. However, microservice systems implemented in industry vary a lot in terms of adopted practices and achieved benefits, drastically different from what is advocated in the literature. In this article, we conduct an empirical study, including an online survey with 51 responses and 14 interviews for experienced microservice experts to advance our understanding regarding to microservice practices in industry. As a part of our findings, the empirical study clearly revealed three levels of maturity of microservice systems (from basic to advanced): independent development and deployment, high scalability and availability, and service ecosystem, categorized by the fulfilled benefits of microservices. We also identify 11 practical issues that constrain the microservice capabilities of organizations. For each issue, we summarize the practices that have been explored and adopted in industry, along with the remaining challenges. Our study can help practitioners better position their microservice systems and determine what infrastructures and capabilities are worth investing. Our study can also help researchers better understand industrial microservice practices and identify useful research problems.

Zhenpeng Chen, Yanbin Cao, Yuanqiang Liu et al.

Deep learning (DL) becomes increasingly pervasive, being used in a wide range of software applications. These software applications, named as DL based software (in short as DL software), integrate DL models trained using a large data corpus with DL programs written based on DL frameworks such as TensorFlow and Keras. A DL program encodes the network structure of a desirable DL model and the process by which the model is trained using the training data. To help developers of DL software meet the new challenges posed by DL, enormous research efforts in software engineering have been devoted. Existing studies focus on the development of DL software and extensively analyze faults in DL programs. However, the deployment of DL software has not been comprehensively studied. To fill this knowledge gap, this paper presents a comprehensive study on understanding challenges in deploying DL software. We mine and analyze 3,023 relevant posts from Stack Overflow, a popular Q&A website for developers, and show the increasing popularity and high difficulty of DL software deployment among developers. We build a taxonomy of specific challenges encountered by developers in the process of DL software deployment through manual inspection of 769 sampled posts and report a series of actionable implications for researchers, developers, and DL framework vendors.

Linyi Li, Maurice Weber, Xiaojun Xu et al.

As machine learning (ML) systems become pervasive, safeguarding their security is critical. However, recently it has been demonstrated that motivated adversaries are able to mislead ML systems by perturbing test data using semantic transformations. While there exists a rich body of research providing provable robustness guarantees for ML models against $\ell_p$ norm bounded adversarial perturbations, guarantees against semantic perturbations remain largely underexplored. In this paper, we provide TSS -- a unified framework for certifying ML robustness against general adversarial semantic transformations. First, depending on the properties of each transformation, we divide common transformations into two categories, namely resolvable (e.g., Gaussian blur) and differentially resolvable (e.g., rotation) transformations. For the former, we propose transformation-specific randomized smoothing strategies and obtain strong robustness certification. The latter category covers transformations that involve interpolation errors, and we propose a novel approach based on stratified sampling to certify the robustness. Our framework TSS leverages these certification strategies and combines with consistency-enhanced training to provide rigorous certification of robustness. We conduct extensive experiments on over ten types of challenging semantic transformations and show that TSS significantly outperforms the state of the art. Moreover, to the best of our knowledge, TSS is the first approach that achieves nontrivial certified robustness on the large-scale ImageNet dataset. For instance, our framework achieves 30.4% certified robust accuracy against rotation attack (within $\pm 30^\circ$) on ImageNet. Moreover, to consider a broader range of transformations, we show TSS is also robust against adaptive attacks and unforeseen image corruptions such as CIFAR-10-C and ImageNet-C.

Siwakorn Srisakaokul, Yuhao Zhang, Zexuan Zhong et al.

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety and security critical applications. However, existing defense approaches are still vulnerable to attacks, especially in a white-box attack scenario. To address this issue, we propose a new defense approach, named MulDef, based on robustness diversity. Our approach consists of (1) a general defense framework based on multiple models and (2) a technique for generating these multiple models to achieve high defense capability. In particular, given a target model, our framework includes multiple models (constructed from the target model) to form a model family. The model family is designed to achieve robustness diversity (i.e., an adversarial example successfully attacking one model cannot succeed in attacking other models in the family). At runtime, a model is randomly selected from the family to be applied on each input example. Our general framework can inspire rich future research to construct a desirable model family achieving higher robustness diversity. Our evaluation results show that MulDef (with only up to 5 models in the family) can substantially improve the target model's accuracy on adversarial examples by 22-74% in a white-box attack scenario, while maintaining similar accuracy on legitimate examples.

Wujie Zheng, Wenyu Wang, Dian Liu et al.

Neural Machine Translation (NMT) has been widely adopted recently due to its advantages compared with the traditional Statistical Machine Translation (SMT). However, an NMT system still often produces translation failures due to the complexity of natural language and sophistication in designing neural networks. While in-house black-box system testing based on reference translations (i.e., examples of valid translations) has been a common practice for NMT quality assurance, an increasingly critical industrial practice, named in-vivo testing, exposes unseen types or instances of translation failures when real users are using a deployed industrial NMT system. To fill the gap of lacking test oracle for in-vivo testing of an NMT system, in this paper, we propose a new approach for automatically identifying translation failures, without requiring reference translations for a translation task; our approach can directly serve as a test oracle for in-vivo testing. Our approach focuses on properties of natural language translation that can be checked systematically and uses information from both the test inputs (i.e., the texts to be translated) and the test outputs (i.e., the translations under inspection) of the NMT system. Our evaluation conducted on real-world datasets shows that our approach can effectively detect targeted property violations as translation failures. Our experiences on deploying our approach in both production and development environments of WeChat (a messenger app with over one billion monthly active users) demonstrate high effectiveness of our approach along with high industry impact.

Yi Qin, Tao Xie, Chang Xu et al.

Cyber-physical software continually interacts with its physical environment for adaptation in order to deliver smart services. However, the interactions can be subject to various errors when the software's assumption on its environment no longer holds, thus leading to unexpected misbehavior or even failure. To address this problem, one promising way is to conduct runtime monitoring of invariants, so as to prevent cyber-physical software from entering such errors (a.k.a. abnormal states). To effectively detect abnormal states, we in this article present an approach, named Context-based Multi-Invariant Detection (CoMID), which consists of two techniques: context-based trace grouping and multi-invariant detection. The former infers contexts to distinguish different effective scopes for CoMID's derived invariants, and the latter conducts ensemble evaluation of multiple invariants to detect abnormal states. We experimentally evaluate CoMID on real-world cyber-physical software. The results show that CoMID achieves a 5.7-28.2% higher true-positive rate and a 6.8-37.6% lower false-positive rate in detecting abnormal states, as compared with state-of-the-art approaches (i.e., Daikon and ZoomIn). When deployed in field tests, CoMID's runtime monitoring improves the success rate of cyber-physical software in its task executions by 15.3-31.7%.

Xuanzhe Liu, Huoran Li, Xuan Lu et al.

The prevalence of smart mobile devices has promoted the popularity of mobile applications (a.k.a. apps). Supporting mobility has become a promising trend in software engineering research. This article presents an empirical study of behavioral service profiles collected from millions of users whose devices are deployed with Wandoujia, a leading Android app store service in China. The dataset of Wandoujia service profiles consists of two kinds of user behavioral data from using 0.28 million free Android apps, including (1) app management activities (i.e., downloading, updating, and uninstalling apps) from over 17 million unique users and (2) app network usage from over 6 million unique users. We explore multiple aspects of such behavioral data and present patterns of app usage. Based on the findings as well as derived knowledge, we also suggest some new open opportunities and challenges that can be explored by the research community, including app development, deployment, delivery, revenue, etc.

Yuan Yao, Hanghang Tong, Tao Xie et al.

Community Question Answering (CQA) websites have become valuable repositories which host a massive volume of human knowledge. To maximize the utility of such knowledge, it is essential to evaluate the quality of an existing question or answer, especially soon after it is posted on the CQA website. In this paper, we study the problem of inferring the quality of questions and answers through a case study of a software CQA (Stack Overflow). Our key finding is that the quality of an answer is strongly positively correlated with that of its question. Armed with this observation, we propose a family of algorithms to jointly predict the quality of questions and answers, for both quantifying numerical quality scores and differentiating the high-quality questions/answers from those of low quality. We conduct extensive experimental evaluations to demonstrate the effectiveness and efficiency of our methods.

Eric Anderson, Sihan Li, Tao Xie

TouchDevelop is a new programming environment that allows users to create applications on mobile devices. Applications created with TouchDevelop have continued to grow in popularity since TouchDevelop was first released to public in 2011. This paper presents a field study of 31,699 applications, focusing on different characteristics between 539 game scripts and all other non-game applications, as well as what make some game applications more popular than others to users. The study provides a list of findings on characteristics of game scripts and also implications for improving end-user programming of game applications.