Xiaochen Li

Xiaochen Li, Yuke Hu, Weiran Liu et al.

Vertical Federated Learning (FL) is a new paradigm that enables users with non-overlapping attributes of the same data samples to jointly train a model without directly sharing the raw data. Nevertheless, recent works show that it's still not sufficient to prevent privacy leakage from the training process or the trained model. This paper focuses on studying the privacy-preserving tree boosting algorithms under the vertical FL. The existing solutions based on cryptography involve heavy computation and communication overhead and are vulnerable to inference attacks. Although the solution based on Local Differential Privacy (LDP) addresses the above problems, it leads to the low accuracy of the trained model. This paper explores to improve the accuracy of the widely deployed tree boosting algorithms satisfying differential privacy under vertical FL. Specifically, we introduce a framework called OpBoost. Three order-preserving desensitization algorithms satisfying a variant of LDP called distance-based LDP (dLDP) are designed to desensitize the training data. In particular, we optimize the dLDP definition and study efficient sampling distributions to further improve the accuracy and efficiency of the proposed algorithms. The proposed algorithms provide a trade-off between the privacy of pairs with large distance and the utility of desensitized values. Comprehensive evaluations show that OpBoost has a better performance on prediction accuracy of trained models compared with existing LDP approaches on reasonable settings. Our code is open source.

Sicong Liu, Xiaochen Li, Zimu Zhou et al.

The ubiquity of camera-embedded devices and the advances in deep learning have stimulated various intelligent mobile video applications. These applications often demand on-device processing of video streams to deliver real-time, high-quality services for privacy and robustness concerns. However, the performance of these applications is constrained by the raw video streams, which tend to be taken with small-aperture cameras of ubiquitous mobile platforms in dim light. Despite extensive low-light video enhancement solutions, they are unfit for deployment to mobile devices due to their complex models and and ignorance of system dynamics like energy budgets. In this paper, we propose AdaEnlight, an energy-aware low-light video stream enhancement system on mobile devices. It achieves real-time video enhancement with competitive visual quality while allowing runtime behavior adaptation to the platform-imposed dynamic energy budgets. We report extensive experiments on diverse datasets, scenarios, and platforms and demonstrate the superiority of AdaEnlight compared with state-of-the-art low-light image and video enhancement solutions.

Yuke Hu, Wei Liang, Ruofan Wu et al.

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging federated KGE (FKGE) collaboratively trains from distributed KGs held among clients while avoiding exchanging clients' sensitive raw KGs, which can still suffer from privacy threats as evidenced in other federated model trainings (e.g., neural networks). However, quantifying and defending against such privacy threats remain unexplored for FKGE which possesses unique properties not shared by previously studied models. In this paper, we conduct the first holistic study of the privacy threat on FKGE from both attack and defense perspectives. For the attack, we quantify the privacy threat by proposing three new inference attacks, which reveal substantial privacy risk by successfully inferring the existence of the KG triple from victim clients. For the defense, we propose DP-Flames, a novel differentially private FKGE with private selection, which offers a better privacy-utility tradeoff by exploiting the entity-binding sparse gradient property of FKGE and comes with a tight privacy accountant by incorporating the state-of-the-art private selection technique. We further propose an adaptive privacy budget allocation policy to dynamically adjust defense magnitude across the training procedure. Comprehensive evaluations demonstrate that the proposed defense can successfully mitigate the privacy threat by effectively reducing the success rate of inference attacks from $83.1\%$ to $59.4\%$ on average with only a modest utility decrease.

Stone Tao, Xiaochen Li, Tongzhou Mu et al.

Training long-horizon robotic policies in complex physical environments is essential for many applications, such as robotic manipulation. However, learning a policy that can generalize to unseen tasks is challenging. In this work, we propose to achieve one-shot task generalization by decoupling plan generation and plan execution. Specifically, our method solves complex long-horizon tasks in three steps: build a paired abstract environment by simplifying geometry and physics, generate abstract trajectories, and solve the original task by an abstract-to-executable trajectory translator. In the abstract environment, complex dynamics such as physical manipulation are removed, making abstract trajectories easier to generate. However, this introduces a large domain gap between abstract trajectories and the actual executed trajectories as abstract trajectories lack low-level details and are not aligned frame-to-frame with the executed trajectory. In a manner reminiscent of language translation, our approach leverages a seq-to-seq model to overcome the large domain gap between the abstract and executable trajectories, enabling the low-level policy to follow the abstract trajectory. Experimental results on various unseen long-horizon tasks with different robot embodiments demonstrate the practicability of our methods to achieve one-shot task generalization.

Max Zuo, Francisco Piedrahita Velez, Xiaochen Li et al.

Recent works have explored using language models for planning problems. One approach examines translating natural language descriptions of planning tasks into structured planning languages, such as the planning domain definition language (PDDL). Existing evaluation methods struggle to ensure semantic correctness and rely on simple or unrealistic datasets. To bridge this gap, we introduce \textit{Planetarium}, a benchmark designed to evaluate language models' ability to generate PDDL code from natural language descriptions of planning tasks. \textit{Planetarium} features a novel PDDL equivalence algorithm that flexibly evaluates the correctness of generated PDDL, along with a dataset of 145,918 text-to-PDDL pairs across 73 unique state combinations with varying levels of difficulty. Finally, we evaluate several API-access and open-weight language models that reveal this task's complexity. For example, 96.1\% of the PDDL problem descriptions generated by GPT-4o are syntactically parseable, 94.4\% are solvable, but only 24.8\% are semantically correct, highlighting the need for a more rigorous benchmark for this problem.

Ang Jia, Yaxin Duan, He Jiang et al.

As emerging attacks increasingly target Industrial Control Systems (ICS), the security of Programmable Logic Controllers (PLCs) has become a critical concern. Binary Code Analysis (BCA), which enables analysts to understand compiled programs without source code, is essential for ICS security tasks such as post-attack digital forensics and incident response. However, automated BCA for PLC binaries remains challenging due to three key issues: heterogeneous binary formats across PLC platforms, entangled program semantics caused by the mixture of control logic with runtime code, and limited semantic representations for interpretable and learning-based downstream analysis. In this paper, we present PLC-BinX, a BCA workflow for cross-platform PLC binary understanding. PLC-BinX analyzes PLC binaries from four platforms: CODESYS v3, GEB, OpenPLC v2, and OpenPLC v3, and recovers function-level information through cross-platform reverse engineering, core-function extraction, and function-level semantic representation construction. Based on the recovered semantic representations, we further study two downstream tasks: toolchain prediction and functionality prediction. Under ten-fold program-level evaluation, PLC-BinX achieves 100.00% precision, recall, and F1 in toolchain prediction, and 51.43% precision, 49.38% recall, and 49.18% F1 in functionality prediction over 22 labels. The results demonstrate that PLC-BinX provides an effective and interpretable approach to cross-platform PLC binary understanding by exposing task-relevant function-level semantics from heterogeneous PLC binaries.

Xiaochen Li, Sicong Liu, Bin Guo et al.

GB-scale large apps like on-device LLMs and rich media editors are becoming the next-generation trend, but their heavy memory and I/O demands, especially during multitasking, cause devices to reclaim or kill processes, turning warm apps into cold launches. The challenge lies not in storing them, but in fast, accurate launching. For users, 1s is the usability cliff, yet our measurements show 86.6\% of GB-scale cold launches exceed it. Also, Android Vitals flags only $\geq$ 5s as slow, exposing a large satisfaction gap. Existing optimizations are designed in isolation and conflict. For example, preloading reduces I/O stalls but consumes scarce memory and is undone by reclamation, while reclamation and killing free memory but sacrifice background survivability, leading to repeated cold relaunches. Our key insight is that, although multitasking makes runtime behavior complex, each app's file access pattern remains predictable. The challenge lies in exploiting this predictability, i.e., preloading without exhausting memory, reclaiming without undoing gains, and killing selectively to preserve background survivability. We introduce AppFlow, a prediction-based system-wide scheduler that integrates a Selective File Preloader, an Adaptive Memory Reclaimer, and a Context-Aware Process Killer. Implemented across the Android framework and Linux kernel without app changes, AppFlow cuts GB-scale cold-launch latency by 66.5\% (e.g., 2s$\rightarrow$690ms) and sustains 95\% of launches within 1s over a 100-day test, significantly improving responsiveness and multitasking experience.

Fenmin Wu, Sicong Liu, Kehao Zhu et al.

The rise of mobile devices equipped with numerous sensors, such as LiDAR and cameras, has spurred the adoption of multi-modal deep intelligence for distributed sensing tasks, such as smart cabins and driving assistance. However, the arrival times of mobile sensory data vary due to modality size and network dynamics, which can lead to delays (if waiting for slower data) or accuracy decline (if inference proceeds without waiting). Moreover, the diversity and dynamic nature of mobile systems exacerbate this challenge. In response, we present a shift to \textit{opportunistic} inference for asynchronous distributed multi-modal data, enabling inference as soon as partial data arrives. While existing methods focus on optimizing modality consistency and complementarity, known as modal affinity, they lack a \textit{computational} approach to control this affinity in open-world mobile environments. AdaFlow pioneers the formulation of structured cross-modality affinity in mobile contexts using a hierarchical analysis-based normalized matrix. This approach accommodates the diversity and dynamics of modalities, generalizing across different types and numbers of inputs. Employing an affinity attention-based conditional GAN (ACGAN), AdaFlow facilitates flexible data imputation, adapting to various modalities and downstream tasks without retraining. Experiments show that AdaFlow significantly reduces inference latency by up to 79.9\% and enhances accuracy by up to 61.9\%, outperforming status quo approaches.

Kecen Li, Chen Gong, Xiaochen Li et al.

Differentially private (DP) image synthesis aims to generate synthetic images from a sensitive dataset, alleviating the privacy leakage concerns of organizations sharing and utilizing synthetic images. Although previous methods have significantly progressed, especially in training diffusion models on sensitive images with DP Stochastic Gradient Descent (DP-SGD), they still suffer from unsatisfactory performance. In this work, inspired by curriculum learning, we propose a two-stage DP image synthesis framework, where diffusion models learn to generate DP synthetic images from easy to hard. Unlike existing methods that directly use DP-SGD to train diffusion models, we propose an easy stage in the beginning, where diffusion models learn simple features of the sensitive images. To facilitate this easy stage, we propose to use `central images', simply aggregations of random samples of the sensitive dataset. Intuitively, although those central images do not show details, they demonstrate useful characteristics of all images and only incur minimal privacy costs, thus helping early-phase model training. We conduct experiments to present that on the average of four investigated image datasets, the fidelity and utility metrics of our synthetic images are 33.1% and 2.1% better than the state-of-the-art method.

Zhi Liu, Tao Yang, Jing Wang et al.

Natural medicines, particularly Traditional Chinese Medicine (TCM), are gaining global recognition for their therapeutic potential in addressing human symptoms and diseases. TCM, with its systematic theories and extensive practical experience, provides abundant resources for healthcare. However, the effective application of TCM requires precise syndrome diagnosis, determination of treatment principles, and prescription formulation, which demand decades of clinical expertise. Despite advancements in TCM-based decision systems, machine learning, and deep learning research, limitations in data and single-objective constraints hinder their practical application. In recent years, large language models (LLMs) have demonstrated potential in complex tasks, but lack specialization in TCM and face significant challenges, such as too big model scale to deploy and issues with hallucination. To address these challenges, we introduce Tianyi with 7.6-billion-parameter LLM, a model scale proper and specifically designed for TCM, pre-trained and fine-tuned on diverse TCM corpora, including classical texts, expert treatises, clinical records, and knowledge graphs. Tianyi is designed to assimilate interconnected and systematic TCM knowledge through a progressive learning manner. Additionally, we establish TCMEval, a comprehensive evaluation benchmark, to assess LLMs in TCM examinations, clinical tasks, domain-specific question-answering, and real-world trials. The extensive evaluations demonstrate the significant potential of Tianyi as an AI assistant in TCM clinical practice and research, bridging the gap between TCM knowledge and practical application.

Yi Xu, Zhiyuan Lu, Xiaochen Li et al.

The Transformer has proven to be a significant approach in feature interaction for CTR prediction, achieving considerable success in previous works. However, it also presents potential challenges in handling feature interactions. Firstly, Transformers may encounter information loss when capturing feature interactions. By relying on inner products to represent pairwise relationships, they compress raw interaction information, which can result in a degradation of fidelity. Secondly, due to the long-tail features distribution, feature fields with low information-abundance embeddings constrain the information abundance of other fields, leading to collapsed embedding matrices. To tackle these issues, we propose a Dual Attention Framework for Enhanced Feature Interaction, known as Dual Enhanced Attention. This framework integrates two attention mechanisms: the Combo-ID attention mechanism and the collapse-avoiding attention mechanism. The Combo-ID attention mechanism directly retains feature interaction pairs to mitigate information loss, while the collapse-avoiding attention mechanism adaptively filters out low information-abundance interaction pairs to prevent interaction collapse. Extensive experiments conducted on industrial datasets have shown the effectiveness of Dual Enhanced Attention.

Zhihao Liu, Jian Lou, Yuke Hu et al.

Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request the removal of their data from trained models. Machine unlearning provides a practical solution by removing the influence of specific data without full retraining. However, most existing methods lack a sound forgetting boundary, causing some samples to be under-forgotten, leaving residual leakage risks, while others remain over-forgotten at the expense of degraded utility. In this work, we propose EAGLE-PC (Entanglement-Awareness Guided Loss Reweighting with Proxy Constraint), a novel unlearning framework that addresses these limitations through two key components. First, entanglement-awareness guided loss reweighting determines the forgetting effort of each sample by measuring its similarity to retain samples in the embedding space, enabling more targeted and effective unlearning. Second, a proxy constraint leveraging ICL (In-Context Learning) generated test data softly regularizes the forgetting process, effectively mitigating over-forgetting. EAGLE-PC is compatible with existing gradient-based objectives and serves as a plug-and-play enhancement. We evaluate EAGLE-PC on the TOFU and MUSE benchmarks, showing consistent improvements in the forgetting-utility trade-off across multiple LLMs. Combined with the NPO+GD optimizer, it approaches full retraining performance, offering a scalable and robust unlearning solution.

Wenjie Bao, Jian Lou, Yuke Hu et al.

Transformer has become fundamental to a vast series of pre-trained large models that have achieved remarkable success across diverse applications. Machine unlearning, which focuses on efficiently removing specific data influences to comply with privacy regulations, shows promise in restricting updates to influence-critical parameters. However, existing parameter-efficient unlearning methods are largely devised in a module-oblivious manner, which tends to inaccurately identify these parameters and leads to inferior unlearning performance for Transformers. In this paper, we propose {\tt MAPE-Unlearn}, a module-aware parameter-efficient machine unlearning approach that uses a learnable pair of masks to pinpoint influence-critical parameters in the heads and filters of Transformers. The learning objective of these masks is derived by desiderata of unlearning and optimized through an efficient algorithm featured by a greedy search with a warm start. Extensive experiments on various Transformer models and datasets demonstrate the effectiveness and robustness of {\tt MAPE-Unlearn} for unlearning.

Ke Miao, Yuke Hu, Xiaochen Li et al.

This paper analyzes the limitations of existing unlearning evaluation metrics in terms of practicality, exactness, and robustness in real-world LLM unlearning scenarios. To overcome these limitations, we propose a new metric called Distribution Correction-based Unlearning Evaluation (DCUE). It identifies core tokens and corrects distributional biases in their confidence scores using a validation set. The evaluation results are quantified using the Kolmogorov-Smirnov test. Experimental results demonstrate that DCUE overcomes the limitations of existing metrics, which also guides the design of more practical and reliable unlearning algorithms in the future.

Xiaochen Li, Zheng-Xin Yong, Stephen H. Bach

Detoxifying multilingual Large Language Models (LLMs) has become crucial due to their increasing global use. In this work, we explore zero-shot cross-lingual generalization of preference tuning in detoxifying LLMs. Unlike previous studies that show limited cross-lingual generalization for other safety tasks, we demonstrate that Direct Preference Optimization (DPO) training with only English data can significantly reduce toxicity in multilingual open-ended generations. For example, the probability of mGPT-1.3B generating toxic continuations drops from 46.8% to 3.9% across 17 different languages after training. Our results also extend to other multilingual LLMs, such as BLOOM, Llama3, and Aya-23. Using mechanistic interpretability tools like causal intervention and activation analysis, we identified the dual multilinguality property of MLP layers in LLMs, which explains the cross-lingual generalization of DPO. Finally, we show that bilingual sentence retrieval can predict the cross-lingual transferability of DPO preference tuning.

Hichem Belgacem, Xiaochen Li, Domenico Bianculli et al.

Users frequently interact with software systems through data entry forms. However, form filling is time-consuming and error-prone. Although several techniques have been proposed to auto-complete or pre-fill fields in the forms, they provide limited support to help users fill categorical fields, i.e., fields that require users to choose the right value among a large set of options. In this paper, we propose LAFF, a learning-based automated approach for filling categorical fields in data entry forms. LAFF first builds Bayesian Network models by learning field dependencies from a set of historical input instances, representing the values of the fields that have been filled in the past. To improve its learning ability, LAFF uses local modeling to effectively mine the local dependencies of fields in a cluster of input instances. During the form filling phase, LAFF uses such models to predict possible values of a target field, based on the values in the already-filled fields of the form and their dependencies; the predicted values (endorsed based on field dependencies and prediction confidence) are then provided to the end-user as a list of suggestions. We evaluated LAFF by assessing its effectiveness and efficiency in form filling on two datasets, one of them proprietary from the banking domain. Experimental results show that LAFF is able to provide accurate suggestions with a Mean Reciprocal Rank value above 0.73. Furthermore, LAFF is efficient, requiring at most 317 ms per suggestion.

Xiaochen Li, Domenico Bianculli, Lionel C. Briand

The completeness (in terms of content) of financial documents is a fundamental requirement for investment funds. To ensure completeness, financial regulators have to spend significant time carefully checking every financial document based on relevant content requirements, which prescribe the information types to be included in financial documents (e.g., the description of shares' issue conditions and procedures). However, existing techniques provide limited support to help regulators automatically identify the text chunks related to financial information types, due to the complexity of financial documents. In this paper, we propose FITI to trace content requirements in financial documents with multi-granularity text analysis. Given a new financial document, FITI first selects a set of candidate sentences for efficient information type identification. Then, to rank candidate sentences, FITI uses a combination of rule-based and data-centric approaches, by leveraging information retrieval (IR) and machine learning (ML) techniques that analyze the words, sentences, and contexts related to an information type. Finally, a heuristic-based selector, which considers both the sentence ranking and domain-specific phrases, determines a list of sentences corresponding to each information type. We evaluated FITI by assessing its effectiveness in tracing financial content requirements in 100 real-world financial documents. Experimental results show that FITI is able to provide accurate identification with average precision, recall, and F1-score values of 0.824, 0.646, and 0.716, respectively. The overall accuracy of FITI significantly outperforms the best baseline (based on a transformer language model) by 0.266 in terms of F1-score. Furthermore, FITI can help regulators detect about 80% of missing information types in financial documents

Xiaochen Li, Weiran Liu, Hanwen Feng et al.

The shuffle model is recently proposed to address the issue of severe utility loss in Local Differential Privacy (LDP) due to distributed data randomization.In the shuffle model, a shuffler is utilized to break the link between the user identity and the message uploaded to the data analyst. Since less noise needs to be introduced to achieve the same privacy guarantee, following this paradigm, the utility of privacy-preserving data collection is improved. We propose DUMP (\underline{DUM}my-\underline{P}oint-based), a framework for privacy-preserving histogram estimation in the shuffle model. The core of DUMP is a new concept of \emph{dummy blanket}, which enables enhancing privacy by just introducing \textit{points }on the user side and further improving the utility of the shuffle model.We instantiate DUMP by proposing two protocols: pureDUMP and mixDUMP, and conduct a comprehensive experimental evaluation to compare them with existing protocols. The experimental results show that, under the same privacy guarantee, (1) the proposed protocols have significant improvements in communication efficiency over all existing multi-message protocols, by at least 3 orders of magnitude; (2) they achieve competitive utility, while the only known protocol (Ghazi \textit{et al.}, PMLR 2020) having better utility than ours employs hard-to-exactly-sample distributions which are vulnerable to floating-point attacks (CCS 2012).

Xiaochen Li, He Jiang, Yasutaka Kamei et al.

Developers increasingly rely on text matching tools to analyze the relation between natural language words and APIs. However, semantic gaps, namely textual mismatches between words and APIs, negatively affect these tools. Previous studies have transformed words or APIs into low-dimensional vectors for matching; however, inaccurate results were obtained due to the failure of modeling words and APIs simultaneously. To resolve this problem, two main challenges are to be addressed: the acquisition of massive words and APIs for mining and the alignment of words and APIs for modeling. Therefore, this study proposes Word2API to effectively estimate relatedness of words and APIs. Word2API collects millions of commonly used words and APIs from code repositories to address the acquisition challenge. Then, a shuffling strategy is used to transform related words and APIs into tuples to address the alignment challenge. Using these tuples, Word2API models words and APIs simultaneously. Word2API outperforms baselines by 10%-49.6% of relatedness estimation in terms of precision and NDCG. Word2API is also effective on solving typical software tasks, e.g., query expansion and API documents linking. A simple system with Word2API-expanded queries recommends up to 21.4% more related APIs for developers. Meanwhile, Word2API improves comparison algorithms by 7.9%-17.4% in linking questions in Question&Answer communities to API documents.

He Jiang, Xiaochen Li, Zhilei Ren et al.

Recent years have witnessed the growing demands for resolving numerous bug reports in software maintenance. Aiming to reduce the time testers/developers take in perusing bug reports, the task of bug report summarization has attracted a lot of research efforts in the literature. However, no systematic analysis has been conducted on attribute construction which heavily impacts the performance of supervised algorithms for bug report summarization. In this study, we first conduct a survey to reveal the existing methods for attribute construction in mining software repositories. Then, we propose a new method named Crowd-Attribute to infer new effective attributes from the crowdgenerated data in crowdsourcing and develop a new tool named Crowdsourcing Software Engineering Platform to facilitate this method. With Crowd-Attribute, we successfully construct 11 new attributes and propose a new supervised algorithm named Logistic Regression with Crowdsourced Attributes (LRCA). To evaluate the effectiveness of LRCA, we build a series of large scale data sets with 105,177 bug reports. Experiments over both the public data set SDS with 36 manually annotated bug reports and new large-scale data sets demonstrate that LRCA can consistently outperform the state-of-the-art algorithms for bug report summarization.

Xiaochen Li, He Jiang, Zhilei Ren et al.

Recent years, deep learning is increasingly prevalent in the field of Software Engineering (SE). However, many open issues still remain to be investigated. How do researchers integrate deep learning into SE problems? Which SE phases are facilitated by deep learning? Do practitioners benefit from deep learning? The answers help practitioners and researchers develop practical deep learning models for SE tasks. To answer these questions, we conduct a bibliography analysis on 98 research papers in SE that use deep learning techniques. We find that 41 SE tasks in all SE phases have been facilitated by deep learning integrated solutions. In which, 84.7% papers only use standard deep learning models and their variants to solve SE problems. The practicability becomes a concern in utilizing deep learning techniques. How to improve the effectiveness, efficiency, understandability, and testability of deep learning based solutions may attract more SE researchers in the future.

He Jiang, Hongjing Ma, Zhilei Ren et al.

In the Google Play store, an introduction page is associated with every mobile application (app) for users to acquire its details, including screenshots, description, reviews, etc. However, it remains a challenge to identify what items influence users most when downloading an app. To explore users' perspective, we conduct a survey to inquire about this question. The results of survey suggest that the participants pay most attention to the app description which gives users a quick overview of the app. Although there exist some guidelines about how to write a good app description to attract more downloads, it is hard to define a high quality app description. Meanwhile, there is no tool to evaluate the quality of app description. In this paper, we employ the method of crowdsourcing to extract the attributes that affect the app descriptions' quality. First, we download some app descriptions from Google Play, then invite some participants to rate their quality with the score from one (very poor) to five (very good). The participants are also requested to explain every score's reasons. By analyzing the reasons, we extract the attributes that the participants consider important during evaluating the quality of app descriptions. Finally, we train the supervised learning models on a sample of 100 app descriptions. In our experiments, the support vector machine model obtains up to 62% accuracy. In addition, we find that the permission, the number of paragraphs and the average number of words in one feature play key roles in defining a good app description.

He Jiang, Jingxuan Zhang, Xiaochen Li et al.

Developers prefer to utilize third-party libraries when they implement some functionalities and Application Programming Interfaces (APIs) are frequently used by them. Facing an unfamiliar API, developers tend to consult tutorials as learning resources. Unfortunately, the segments explaining a specific API scatter across tutorials. Hence, it remains a challenging issue to find the relevant segments. In this study, we propose a more accurate model to find the exact tutorial fragments explaining APIs. This new model consists of a text classifier with domain specific features. More specifically, we discover two important indicators to complement traditional text based features, namely co-occurrence APIs and knowledge based API extensions. In addition, we incorporate Word2Vec, a semantic similarity metric to enhance the new model. Extensive experiments over two publicly available tutorial datasets show that our new model could find up to 90% fragments explaining APIs and improve the state-of-the-art model by up to 30% in terms of F-measure.

Liming Nie, He Jiang, Zhilei Ren et al.

As code search is a frequent developer activity in software development practices, improving the performance of code search is a critical task. In the text retrieval based search techniques employed in the code search, the term mismatch problem is a critical language issue for retrieval effectiveness. By reformulating the queries, query expansion provides effective ways to solve the term mismatch problem. In this paper, we propose Query Expansion based on Crowd Knowledge (QECK), a novel technique to improve the performance of code search algorithms. QECK identifies software-specific expansion words from the high quality pseudo relevance feedback question and answer pairs on Stack Overflow to automatically generate the expansion queries. Furthermore, we incorporate QECK in the classic Rocchio's model, and propose QECK based code search method QECKRocchio. We conduct three experiments to evaluate our QECK technique and investigate QECKRocchio in a large-scale corpus containing real-world code snippets and a question and answer pair collection. The results show that QECK improves the performance of three code search algorithms by up to 64 percent in Precision, and 35 percent in NDCG. Meanwhile, compared with the state-of-the-art query expansion method, the improvement of QECK Rocchio is 22 percent in Precision, and 16 percent in NDCG.

He Jiang, Xiaochen Li, Zijiang Yang et al.

Driven by new software development processes and testing in clouds, system and integration testing nowadays tends to produce enormous number of alarms. Such test alarms lay an almost unbearable burden on software testing engineers who have to manually analyze the causes of these alarms. The causes are critical because they decide which stakeholders are responsible to fix the bugs detected during the testing. In this paper, we present a novel approach that aims to relieve the burden by automating the procedure. Our approach, called Cause Analysis Model, exploits information retrieval techniques to efficiently infer test alarm causes based on test logs. We have developed a prototype and evaluated our tool on two industrial datasets with more than 14,000 test alarms. Experiments on the two datasets show that our tool achieves an accuracy of 58.3% and 65.8%, respectively, which outperforms the baseline algorithms by up to 13.3%. Our algorithm is also extremely efficient, spending about 0.1s per cause analysis. Due to the attractive experimental results, our industrial partner, a leading information and communication technology company in the world, has deployed the tool and it achieves an average accuracy of 72% after two months of running, nearly three times more accurate than a previous strategy based on regular expressions.