Smart contracts have revolutionized the credit landscape. However, their security remains intensely scrutinized due to numerous hacking incidents and inherent logical challenges. One well-known issue is reentrancy vulnerability, exemplified by DAO attacks that lead to substantial economic losses. Previous approaches have employed rule-based and deep learning-based (DL) algorithms to detect and repair reentrancy vulnerability. Large language models (LLM) have been distinguished in recent years for their excellent understanding of text and code. However, less attention has been paid to LLM-based reentrancy vulnerability detection and repair, and direct prompt-based approaches often suffer from inefficiencies and high false positives. To overcome the above shortcomings, this paper proposes a hybrid model framework combining LLM with DL to enhance the detection and repair of reentrancy vulnerabilities. This unified framework comprises three crucial phases: the data processing phase, the vulnerability detection phase, and the vulnerability repair phase. Extensive experimental results validate the superiority of our approach over state-of-the-art baselines, and ablation studies demonstrate the effectiveness of each component. Our approach demonstrates significant improvements in vulnerability detection, with increases of 3.51% in accuracy, 2.31% in recall, 0.42% in precision, and 0.85% in F1-score. Furthermore, our approach can achieve a notable 9.62% enhancement in the repair rate. Finally, we also conducted a user study to emphasize its potential to fortify the security of smart contracts.

Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal forecasting. However, these methods face challenges due to the severe cross-domain gap or in-domain heterogeneity. This paper explores a new road to building a TSF foundation model from rich, high-quality natural images. Our key insight is that a visual masked autoencoder, pre-trained on the ImageNet dataset, can naturally be a numeric series forecaster. By reformulating TSF as an image reconstruction task, we bridge the gap between image pre-training and TSF downstream tasks. Surprisingly, without further adaptation in the time series domain, the proposed VisionTS could achieve better zero-shot forecast performance than existing TSF foundation models. With fine-tuning for one epoch, VisionTS could further improve the forecasting and achieve state-of-the-art performance in most cases. Extensive experiments reveal intrinsic similarities between images and real-world time series, suggesting that visual models may offer a "free lunch" for TSF and highlight the potential for future cross-modality research. Our code is available in the https://github.com/Keytoyze/VisionTS.

Utilizing code snippets on Stack Overflow (SO) is a common practice among developers for problem-solving. Although SO code snippets serve as valuable resources, it is important to acknowledge their imperfections, reusing problematic code snippets can lead to the introduction of suboptimal or buggy code into software projects. SO comments often point out weaknesses of a post and provide valuable insights to improve the quality of answers, while SO comments are usually missed and/or ignored, leaving these problematic code snippets untouched. In this work, we first investigate the task of automatic SO posts updating based on their associated comments. We introduce a novel framework, named SOUP (Stack Overflow Updator for Post) for this task. SOUP addresses two key tasks: Valid Comment-Edit Prediction (VCP) and Automatic Post Updating (APU). We fine-tuned a large language model, CodeLlama, using low-rank adaptation techniques to complete the VCP task, and constructed a dataset containing 78k valid comment-edit pairs for the APU task. Subsequently, we tested the performance of multiple large language models on the APU task. Extensive experimental results show the promising performance of our model over a set of benchmarks. Moreover, we also perform an in-the-wild evaluation on Stack Overflow, we submitted 50 edits generated by our approach to Stack Overflow posts and 21 of them have been verified and accepted by SO maintainers, further proving the practical value of SOUP.

It is commonly believed that scaling language models should commit a significant space or time cost, by increasing the parameters (parameter scaling) or output tokens (inference-time scaling). We introduce another and more inference-efficient scaling paradigm: increasing the model's parallel computation during both training and inference time. We apply $P$ diverse and learnable transformations to the input, execute forward passes of the model in parallel, and dynamically aggregate the $P$ outputs. This method, namely parallel scaling (ParScale), scales parallel computation by reusing existing parameters and can be applied to any model structure, optimization procedure, data, or task. We theoretically propose a new scaling law and validate it through large-scale pre-training, which shows that a model with $P$ parallel streams is similar to scaling the parameters by $\mathcal O(\log P)$ while showing superior inference efficiency. For example, ParScale can use up to 22$\times$ less memory increase and 6$\times$ less latency increase compared to parameter scaling that achieves the same performance improvement. It can also recycle an off-the-shelf pre-trained model into a parallelly scaled one by post-training on a small amount of tokens, further reducing the training budget. The new scaling law we discovered potentially facilitates the deployment of more powerful models in low-resource scenarios, and provides an alternative perspective for the role of computation in machine learning. Our code and 67 trained model checkpoints are publicly available at https://github.com/QwenLM/ParScale and https://huggingface.co/ParScale.

Prompt tuning for pre-trained language models (PLMs) has been an effective approach for few-shot text classification. To make a prediction, a typical prompt tuning method employs a template wrapping the input text into a cloze question, and a verbalizer mapping the output embedding to labels. However, current methods typically depend on handcrafted templates and verbalizers, which require much domain-specific prior knowledge by human efforts. In this work, we investigate how to build a good human-free prompt tuning using soft prompt templates and soft verbalizers, which can be learned directly from data. To address the challenge of data scarcity, we integrate a set of trainable bases for sentence representation to transfer the contextual information into a low-dimensional space. By jointly pre-training the soft prompts and the bases using contrastive learning, the projection space can catch critical semantics at the sentence level, which could be transferred to various downstream tasks. To better bridge the gap between downstream tasks and the pre-training procedure, we formulate the few-shot classification tasks as another contrastive learning problem. We name this Jointly Pretrained Template and Verbalizer (JPTV). Extensive experiments show that this human-free prompt tuning can achieve comparable or even better performance than manual prompt tuning.

Software vulnerabilities pose significant risks to the security and integrity of software systems. Although prior studies have explored vulnerability detection using deep learning and pre-trained models, these approaches often fail to provide the detailed explanations necessary for developers to understand and remediate vulnerabilities effectively. The advent of large language models (LLMs) has introduced transformative potential due to their advanced generative capabilities and ability to comprehend complex contexts, offering new possibilities for addressing these challenges. In this paper, we propose LLMVulExp, an automated framework designed to specialize LLMs for the dual tasks of vulnerability detection and explanation. To address the challenges of acquiring high-quality annotated data and injecting domain-specific knowledge, LLMVulExp leverages prompt-based techniques for annotating vulnerability explanations and fine-tunes LLMs using instruction tuning with Low-Rank Adaptation (LoRA), enabling LLMVulExp to detect vulnerability types in code while generating detailed explanations, including the cause, location, and repair suggestions. Additionally, we employ a Chain-of-Thought (CoT) based key code extraction strategy to focus LLMs on analyzing vulnerability-prone code, further enhancing detection accuracy and explanatory depth.We conducted experiments across multiple vulnerability detection settings on three benchmark datasets, demonstrating the effectiveness of our method. This study highlights the feasibility of utilizing LLMs for real-world vulnerability detection and explanation tasks, providing critical insights into their adaptation and application in software security.

While existing code large language models (code LLMs) exhibit impressive capabilities in code generation, their autoregressive sequential generation inherently lacks reversibility.This limitation hinders them from timely correcting previous missing statements during coding as humans do, often leading to error propagation and suboptimal performance.We introduce JUMPCODER, a novel model-agnostic framework that enables human-like online modification and non-sequential generation to augment code LLMs.The key idea behind JUMP-CODER is to insert new code into the currently generated code when necessary during generation, which is achieved through an auxiliary infilling model that works in tandem with the code LLM.Since identifying the best infill position beforehand is intractable, we adopt an infill-first, judge-later strategy, which experiments with filling at the k most critical positions following the generation of each line, and uses an Abstract Syntax Tree (AST) parser alongside the Generation Model Scoring to effectively judge the validity of each potential infill.Extensive experiments using six state-ofthe-art code LLMs across multiple and multilingual benchmarks consistently indicate significant improvements over all baselines.Our code is public at https://github.com/ Keytoyze/JumpCoder.

Auto-scaling is crucial for achieving elasticity in cloud databases as well as other cloud systems. Predictive auto-scaling, which leverages forecasting techniques to adjust resources based on predicted workload, has been widely adopted. However, the inherent inaccuracy of forecasting presents a significant challenge, potentially causing resource under-provisioning. To address this challenge, we propose robust predictive auto-scaling that considers the uncertainty in forecasts. Unlike previous predictive approaches that rely on single-valued forecasts, we leverage probabilistic forecasting techniques to generate quan-tile forecasts, providing a more comprehensive understanding of the potential future workloads. By formulating the auto-scaling problem as a robust optimization problem, we enable the implementation of auto-scaling strategies with customizable levels of robustness, which can be determined by considering various quantile levels of forecasts. Moreover, we enhance the adaptability of our strategy by incorporating different quantile levels through-out the entire decision horizon, allowing for dynamic adjustments in the conservatism of our auto-scaling decisions. This enables us to strike a balance between resource efficiency and system robustness. Through extensive experiments, we demonstrate the effectiveness of our approach in achieving robust auto-scaling in cloud databases, while maintaining reasonable resource efficiency.

Unbiased Learning to Rank (ULTR) aims to train unbiased ranking models from biased click logs, by explicitly modeling a generation process for user behavior and fitting click data based on examination hypothesis. Previous research found empirically that the true latent relevance is mostly recoverable through click fitting. However, we demonstrate that this is not always achievable, resulting in a significant reduction in ranking performance. This research investigates the conditions under which relevance can be recovered from click data in the first principle. We initially characterize a ranking model as identifiable if it can recover the true relevance up to a scaling transformation, a criterion sufficient for the pairwise ranking objective. Subsequently, we investigate an equivalent condition for identifiability, articulated as a graph connectivity test problem: the recovery of relevance is feasible if and only if the identifiability graph (IG), derived from the underlying structure of the dataset, is connected. The presence of a disconnected IG may lead to degenerate cases and suboptimal ranking performance. To tackle this challenge, we introduce two methods, namely node intervention and node merging, designed to modify the dataset and restore the connectivity of the IG. Empirical results derived from a simulated dataset and two real-world LTR benchmark datasets not only validate our proposed theory, but also demonstrate the effectiveness of our methods in alleviating data bias when the relevance model is unidentifiable.

Automatically generating high-quality code descriptions greatly improves the readability and maintainability of the codebase. Recently, retrieval augmented code-to-text generation has proven to be an effective solution, which has achieved state-of-the-art results on various benchmarks. It brings out the potential to leverage large unlabeled code descriptions to further improve the generation quality. Despite the promising performance, retrieval-augmented models however suffer from being deluded by inconducive retrieved references, due to irrelevant or even misleading information contained therein. To this end, we design PinNet, a new framework for code-to-text generation. PinNet relies on a discriminator to measure how well the retrievals match the semantics of the input code. Remarkably, the hidden representation of the reference before the output layer of the discriminator can be leveraged to significantly improve the code-to-text generation by modifying the attention weights. It essentially pays high attention to valuable information and eliminates misleadingness. To effectively execute this idea, we also propose a novel contrastive learning method to quantify the semantical similarities between unlabeled references. Using extensive experiments on code summarization and SQL-to-text generation, we demonstrate that the proposed method can significantly outperform all of the baselines.

Selecting the best code solution from multiple generated ones is an essential task in code generation, which can be achieved by using some reliable validators (e.g., developer-written test cases) for assistance. Since reliable test cases are not always available and can be expensive to build in practice, researchers propose to automatically generate test cases to assess code solutions. However, when both code solutions and test cases are plausible and not reliable, selecting the best solution becomes challenging. Although some heuristic strategies have been proposed to tackle this problem, they lack a strong theoretical guarantee and it is still an open question whether an optimal selection strategy exists. Our work contributes in two ways. First, we show that within a Bayesian framework, the optimal selection strategy can be defined based on the posterior probability of the observed passing states between solutions and tests. The problem of identifying the best solution is then framed as an integer programming problem. Second, we propose an efficient approach for approximating this optimal (yet uncomputable) strategy, where the approximation error is bounded by the correctness of prior knowledge. We then incorporate effective prior knowledge to tailor code generation tasks. Both theoretical and empirical studies confirm that existing heuristics are limited in selecting the best solutions with plausible test cases. Our proposed approximated optimal strategy ℬ4 significantly surpasses existing heuristics in selecting code solutions generated by large language models (LLMs) with LLM-generated tests, achieving a relative performance improvement by up to 50% over the strongest heuristic and 246% over the random selection in the most challenging scenarios. Our code is publicly available at https://github.com/ZJU-CTAG/B4.

Recent years have witnessed the success of introducing deep learning models to time series forecasting. From a data generation perspective, we illustrate that existing models are susceptible to distribution shifts driven by temporal contexts, whether observed or unobserved. Such context-driven distribution shift (CDS) introduces biases in predictions within specific contexts and poses challenges for conventional training paradigms. In this paper, we introduce a universal calibration methodology for the detection and adaptation of CDS with a trained model. To this end, we propose a novel CDS detector, termed the "residual-based CDS detector" or "Reconditionor", which quantifies the model's vulnerability to CDS by evaluating the mutual information between prediction residuals and their corresponding contexts. A high Reconditionor score indicates a severe susceptibility, thereby necessitating model adaptation. In this circumstance, we put forth a straightforward yet potent adapter framework for model calibration, termed the "sample-level contextualized adapter" or "SOLID". This framework involves the curation of a contextually similar dataset to the provided test sample and the subsequent fine-tuning of the model's prediction layer with a limited number of steps. Our theoretical analysis demonstrates that this adaptation strategy can achieve an optimal bias-variance trade-off. Notably, our proposed Reconditionor and SOLID are model-agnostic and readily adaptable to a wide range of models. Extensive experiments show that SOLID consistently enhances the performance of current forecasting models on real-world datasets, especially on cases with substantial CDS detected by the proposed Reconditionor, thus validating the effectiveness of the calibration approach.

Graph contrastive learning often faces challenges when data augmentations compromise the graph's critical attributes, introducing the risk of generating noise-positive pairs. Although recent methods have attempted to address these issues, they either fall short of ensuring effective data augmentation or suffer from excessive computational demands. The advent of full-attention graph Transformers, with their enhanced capacity for graph representation learning, has sparked significant interest. Despite their potential, employing full-attention graph Transformers for contrastive learning can introduce issues such as noisy redundancies. In this work, we propose the Graph Attention Contrastive Learning (GACL) model, which innovatively combines a full-attention transformer with a message-passing graph neural network as its encoder. To mitigate the noise associated with full-attention mechanisms, we apply a denoising modification. Our GACL model effectively tackles the challenges associated with full-attention mechanisms and introduces a novel approach for data augmentation. Moreover, we propose the concept of effective mutual information to theoretically underpin our methodology. Utilizing this framework, we explore the impact of the denoising matrix within GACL's contrastive learning process and delve into comprehensive discussions on its implications. Empirical assessments underscore GACL's exceptional performance, establishing it as a state-of-the-art solution in graph contrastive learning.

Graph label propagation (LP) is a core component in many downstream applications such as fraud detection, recommendation and image segmentation. In this paper, we proposeGLP, a GPU-based framework to enable efficientLPprocessing on large-scale graphs. By investigating the data processing pipeline in a large e-commerce platform, we have identified two key challenges on integrating GPU-acceleratedLPprocessing to the pipeline: (1) programmability for evolving application logics; (2) demand for real-time performance. Motivated by these challenges, we offer a set of expressive APIs that data engineers can customize and deploy efficientLPalgorithms on GPUs with ease. To achieve better performance, we propose novel GPU-centric optimizations by leveraging the community as well as power-law properties of large graphs. Further, we significantly reduce the expensive data transfer cost between CPUs and GPUs by enablingLPprocessing on compressed graphs. Extensive experiments have confirmed the effectiveness of our proposed approaches over the state-of-the-art GPU methods. Furthermore, our proposed solution supports a real billion-scale graph workload for fraud detection and achieves 13.2× speedup to the current in-house solution running on a high-end multicore machine with compressed graphs.

Smart contracts are essential for executing computing logic on blockchain networks. However, they are also susceptible to various vulnerabilities. In recent years, the detection of smart contract vulnerabilities has become a significant concern due to the substantial losses caused by hacker attacks. Traditional vulnerability detection approaches rely on expert rules, which often suffer from limitations in accuracy and completeness. Deep learning-based methods offer better coverage of vulnerabilities but may overlook certain vulnerability characteristics and suffer from overfitting during training. In this paper, we propose a novel approach called ConvMHSA-SCVD, which combines knowledge-driven and data-driven algorithms together to detect smart contract vulnerabilities. By incorporating feature selection, data balancing, and a combination of multi-channel convolution and multi-head self-attention neural networks, our ConvMHSA-SCVD achieves effective vulnerability detection in smart contracts. Extensive experiments demonstrate that our approach outperforms the state-of-the-art method in accuracy and F1 score, with improvements ranging from 0.4% to 3.84% and 1.28% to 1.90%, respectively.

Recent studies have highlighted the limitations of message-passing based graph neural networks (GNNs), e.g., limited model expressiveness, over-smoothing, over-squashing, etc. To alleviate these issues, Graph Transformers (GTs) have been proposed which work in the paradigm that allows message passing to a larger coverage even across the whole graph. Hinging on the global range attention mechanism, GTs have shown a superpower for representation learning on homogeneous graphs. However, the investigation of GTs on heterogeneous information networks (HINs) is still under-exploited. In particular, on account of the existence of heterogeneity, HINs show distinct data characteristics and thus require different treatment. To bridge this gap, in this paper we investigate the representation learning on HINs with Graph Transformer, and propose a novel model named HINormer, which capitalizes on a larger-range aggregation mechanism for node representation learning. In particular, assisted by two major modules, i.e., a local structure encoder and a heterogeneous relation encoder, HINormer can capture both the structural and heterogeneous information of nodes on HINs for comprehensive node representations. We conduct extensive experiments on four HIN benchmark datasets, which demonstrate that our proposed model can outperform the state-of-the-art.

Cloud-native databases have become the de-facto choice for mission-critical applications on the cloud due to the need for high availability, resource elasticity, and cost efficiency. Meanwhile, driven by the increasing connectivity between data generation and analysis, users prefer a single database to efficiently process both OLTP and OLAP workloads, which enhances data freshness and reduces the complexity of data synchronization and the overall business cost. In this paper, we summarize five crucial design goals for a cloud-native HTAP database based on our experience and customers' feedback, i.e., transparency, competitive OLAP performance, minimal perturbation on OLTP workloads, high data freshness, and excellent resource elasticity. As our solution to realize these goals, we present PolarDB-IMCI, a cloud-native HTAP database system designed and deployed at Alibaba Cloud. Our evaluation results show that PolarDB-IMCI is able to handle HTAP efficiently on both experimental and production workloads; notably, it speeds up analytical queries up to ×149 on TPC-H (100GB). PolarDB-IMCI introduces low visibility delay and little performance perturbation on OLTP workloads (<5%), and resource elasticity can be achieved by scaling out in tens of seconds.

Natural language to SQL (NL2SQL) techniques provide a convenient interface to access databases, especially for non-expert users, to conduct various data analytics. Existing methods often employ either a rule-base approach or a deep learning based solution. The former is hard to generalize across different domains. Though the latter generalizes well, it often results in queries with syntactic or semantic errors, thus may be even not executable. In this work, we bridge the gap between the two and design a new framework to significantly improve both accuracy and runtime. In particular, we develop a novel CatSQL sketch, which constructs a template with slots that initially serve as placeholders, and tightly integrates with a deep learning model to fill in these slots with meaningful contents based on the database schema. Compared with the widely used sequence-to-sequence-based approaches, our sketch-based method does not need to generate keywords which are boilerplates in the template, and can achieve better accuracy and run much faster. Compared with the existing sketch-based approaches, our CatSQL sketch is more general and versatile, and can leverage the values already filled in on certain slots to derive the rest ones for improved performance. In addition, we propose the Semantics Correction technique, which is the first that leverages database domain knowledge in a deep learning based NL2SQL solution. Semantics Correction is a post-processing routine, which checks the initially generated SQL queries by applying rules to identify and correct semantic errors. This technique significantly improves the NL2SQL accuracy. We conduct extensive evaluations on both single-domain and cross-domain benchmarks and demonstrate that our approach significantly outperforms the previous ones in terms of both accuracy and throughput. In particular, on the state-of-the-art NL2SQL benchmark Spider, our CatSQL prototype outperforms the best of the previous solutions by 4 points on accuracy, while still achieving a throughput up to 63 times higher.

Unbiased learning to rank (ULTR) aims to train an unbiased ranking model from biased user click logs. Most of the current ULTR methods are based on the examination hypothesis (EH), which assumes that the click probability can be factorized into two scalar functions, one related to ranking features and the other related to bias factors. Unfortunately, the interactions among features, bias factors and clicks are complicated in practice, and usually cannot be factorized in this independent way. Fitting click data with EH could lead to model misspecification and bring the approximation error.

Using Unbiased Learning to Rank (ULTR) to train the ranking model with biased click logs has attracted increased research interest. The key idea is to explicitly model the user's observation behavior when building the ranker with a large number of click logs. Considering the simplicity, recent efforts are mainly based on the position bias hypothesis, in which the observation only depends on the position. However, this hypothesis does not hold in many scenarios due to the neglect of the distinct characteristics of individuals in the same position. On the other hand, directly modeling observation bias for each individual is quite challenging, since the effects of each individual's features on relevance and observation are entangled. It is difficult to ravel out this coupled effect and thus obtain a correct relevance model from click data. To address this issue, we first present the concept of coupling effect for individual-level ULTR. Then, we develop the novel Lipschitz and Bernoulli Decoupling (LBD) model to decouple the effects on relevance and observation at the individual level. We prove theoretically that our proposed method could recover the correct relevance order for the ranking objective. Empirical results on two LTR benchmark datasets show that the proposed model outperforms the state-of-the-art baselines and verify its effectiveness in debiasing data.

The prevalence of graph structures attracts a surge of investigation on graph data, enabling several downstream tasks such as multi-graph classification. However, in the multi-graph setting, graphs usually follow a long-tailed distribution in terms of their sizes, i.e., the number of nodes. In particular, a large fraction of tail graphs usually have small sizes. Though recent graph neural networks (GNNs) can learn powerful graph-level representations, they treat the graphs uniformly and marginalize the tail graphs which suffer from the lack of distinguishable structures, resulting in inferior performance on tail graphs. To alleviate this concern, in this paper we propose a novel graph neural network named SOLT-GNN, to close the representational gap between the head and tail graphs from the perspective of knowledge transfer. In particular, SOLT-GNN capitalizes on the co-occurrence substructures exploitation to extract the transferable patterns from head graphs. Furthermore, a novel relevance prediction function is proposed to memorize the pattern relevance derived from head graphs, in order to predict the complements for tail graphs to attain more comprehensive structures for enrichment. We conduct extensive experiments on five benchmark datasets, and demonstrate that our proposed model can outperform the state-of-the-art baselines.

A significant fraction of data in cloud storage is rarely accessed, referred to as cold data. Accurately identifying and efficiently managing cold data on cost-effective storages is one of the major challenges for cloud providers, which balances between reducing the cost and improving the system performance. To this end, we propose SA-LSM to use (S)urvival (A)nalysis for Log-Structure Merge Tree (LSM-tree) key-value (KV) stores. Conventionally, the data layout of LSM-tree is determined jointly by the write and the compaction operations. However, this process by default does not fully utilize the access information of data records, leading to a suboptimal data layout that negatively impacts the system performance. SA-LSM utilizes the survival analysis, a statistical learning algorithm commonly used in biostatistics, to optimize the data layout. When put into perspective of LSM-tree with proper adoptions, SA-LSM can accurately predict cold data using the historical semantic information and access traces. As a concrete realization, we implement our proposal in X-Engine, a commercial-strength open-source LSM-tree storage engine. To make the deployment more flexible, we also design a non-intrusive architecture that offloads CPU-intensive work, e.g., model training and inference, to an external service. Extensive experiments on real-world workloads show that it can decrease the tail latency by up to 78.9% compared to the state-of-the-art techniques. The generality of this approach and the significant performance improvement show great potentials in a variety of related applications.

The hash table is a fundamental structure that has been implemented on graphics processing units (GPUs) to accelerate a wide range of analytics workloads. Most existing works have focused on static scenarios and occupy large GPU memory to maximize the insertion efficiency. In many cases, data stored in hash tables get updated dynamically, and existing approaches use unnecessarily large memory resources. One naïve solution is to rebuild a hash table (known as rehashing) whenever it is either filled or mostly empty. However, this approach renders significant overheads for rehashing. In this paper, we propose a novel dynamic cuckoo hash table technique on GPUs, known as DyCuckoo. We devise a resizing strategy for dynamic scenarios without rehashing the entire table that ensures a guaranteed filled factor. The strategy trades search performance with resizing efficiency, and this tradeoff can be configured by users. To further improve efficiency, we propose a 2-in-d cuckoo hashing scheme that ensures a maximum of two lookups for find and delete operations, while retaining similar performance for insertions as a general cuckoo hash. Extensive experiments have validated the proposed design's effectiveness over several state-of-the-art hash table implementations on GPUs. DyCuckoo achieves superior efficiency while enables fine-grained memory control, which is not available in existing GPU hash table approaches.

Listwise collaborative filtering, which directly predicts a ranking list of items for the given user, achieves superior accuracy performance since it is aligned with the ultimate goals of recommender systems.However, in corpus with the enormous number of items, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full corpus retrieval extremely difficult.In this paper, we propose a binarized collaborative filtering method, called Discrete Listwise Collaborative Filtering (DLCF), to represent users and items as binary codes for fast recommendation.As such, the proposed method could accelerate the retrieval procedure, since the user-item similarity could be efficiently computed via Hamming distance.We further adopt the discrete coordinate descent method to jointly optimize our proposed model.Extensive experiments performed on three real-world datasets demonstrate that 1) DLCF significantly outperforms the state-of-the-art binarized recommendation methods, and 2) DLCF shows very competitive ranking accuracy compared to its real-valued version while significantly improving the retrieval efficiency.

Counterfactual Learning to Rank (CLTR) becomes an attractive research topic due to its capability of training ranker with click logs. However, CLTR inherently suffers from a large amount of bias caused by confounders, variables that affect both the observation (examination) behavior and click behavior. Recent efforts to correct bias mostly focus on position bias, which assumes that each observation in a ranking list is isolated and only depends on the position. Though effective, users often engage with documents in an interactive manner. Ignoring the interactions between observations/clicks would incur a large interactional observation bias no matter how much data is collected. In this work, we leverage the embedding method to develop an Interactional Observation-Based Model (IOBM) to estimate the observation probability. We argue that while there exist complex observed and unobserved confounders for observation/click interactions, it is sufficient to use the embedding as a proxy confounder to uncover the relevant information for the prediction of the observation propensity. Moreover, the embedding could offer an alternative to the fully specified generative model for observation and decouples the complex interaction structure of observations/clicks. In our IOBM, we first learn the individual observation embedding to capture position and click information. Then, we learn the interactional observation embedding to uncover their local interaction structure. To filter out irrelevant information and reduce contextual bias, we utilize query context information and propose the intra-observation attention and the inter-observation attention, respectively. We conduct extensive experiments on two LTR benchmark datasets, demonstrating that the proposed IOBM consistently achieves better performance over the baseline models in various click situations and verifying its effectiveness of eliminating interactional observation bias.

Fraud detection is a pressing challenge for most financial and commercial platforms. In this paper, we study the processing pipeline of fraud detection in a large e-commerce platform of TaoBao. Graph label propagation (LP) is a core component in this pipeline to detect suspicious clusters from the user-interaction graph.Furthermore, the run-time of the LP component occupies 75% overhead of TaoBao's automated detection pipeline. To enable real-time fraud detection, we propose a GPU-based framework, called GLP, to support large-scale LP workloads in enterprises.We have identified two key challenges when integrating GPU acceleration into TaoBao's data processing pipeline: (1)programmability for evolving fraud detection logics; (2)demand for real-time performance. Motivated by these challenges, we offer a set of expressive APIs that data engineers can customize and deploy efficient LP algorithms on GPUs with ease. We propose novel GPU-centric optimizations by leveraging the community as well as power-law properties of large graphs. Extensive experiments have confirmed the effectiveness of our proposed optimizations. With a single GPU, GLP supports a real billion-scale graph workload from the fraud detection pipeline of TaoBao and achieves 8.2x speedup to the current in-house distributed solution running on high-end multicore machines.

Application Programming Interfaces (APIs) typically come with usage constraints. The violations of these constraints (i.e. API misuses) can cause significant problems in software development. Existing methods mine frequent API usage patterns from codebase to detect API misuses. They make a naive assumption that API usage that deviates from the most-frequent API usage is a misuse. However, there is a big knowledge gap between API usage patterns and API usage constraints in terms of comprehensiveness, explainability and best practices. Inspired by this, we propose a novel approach named KGAMD (API-Misuse Detector Driven by Fine-Grained API-Constraint Knowledge Graph) that detects API misuses directly against the API constraint knowledge, rather than API usage pat-terns. We first construct a novel API-constraint knowledge graph from API reference documentation with open information extraction methods. This knowledge graph explicitly models two types of API-constraint relations (call-order and condition-checking) and enriches return and throw relations with return conditions and exception triggers. Then, we develop the KGAMD tool that utilizes the knowledge graph to detect API misuses. There are three types of frequent API misuses we can detect - missing calls, missing condition checking and missing exception handling, while existing detectors mostly focus on only missing calls. Our quantitative evaluation and user study demonstrate that our KGAMD is promising in helping developers avoid and debug API misuses

Nowadays, driven by the increasing concern on diet and health, food computing has attracted enormous attention from both industry and research community. One of the most popular research topics in this domain is Food Retrieval, due to its profound influence on health-oriented applications. In this paper, we focus on the task of cross-modal retrieval between food images and cooking recipes. We present Modality-Consistent Embedding Network (MCEN) that learns modality-invariant representations by projecting images and texts to the same embedding space. To capture the latent alignments between modalities, we incorporate stochastic latent variables to explicitly exploit the interactions between textual and visual features. Importantly, our method learns the cross-modal alignments during training but computes embeddings of different modalities independently at inference time for the sake of efficiency. Extensive experimental results clearly demonstrate that the proposed MCEN outperforms all existing approaches on the benchmark Recipe1M dataset and requires less computational cost.

API usage directives in official API documentation describe the contracts, constraints and guidelines for using APIs in natural language. Through the investigation of API misuse scenarios on Stack Overflow, we identify three barriers that hinder the understanding of the API usage directives, i.e., lack of specific usage context, indirect relationships to cooperative APIs, and confusing APIs with subtle differences. To overcome these barriers, we develop a text mining approach to discover the crowdsourced API misuse scenarios on Stack Overflow and extract from these scenarios erroneous code examples and patches, as well as related API and confusing APIs to construct demystification reports to help developers understand the official API usage directives described in natural language. We apply our approach to API usage directives in official Android API documentation and android-tagged discussion threads on Stack Overflow. We extract 159,116 API misuse scenarios for 23,969 API usage directives of 3138 classes and 7471 methods, from which we generate the demystification reports. Our manual examination confirms that the extracted information in the generated demystification reports are of high accuracy. By a user study of 14 developers on 8 API-misuse related error scenarios, we show that our demystification reports help developer understand and debug API-misuse related program errors faster and more accurately, compared with reading only plain API usage-directive sentences.

API misuses cause significant problem in software development. Existing methods detect API misuses against frequent API usage patterns mined from codebase. They make a naive assumption that API usage that deviates from the most-frequent API usage is a misuse. However, there is a big knowledge gap between API usage patterns and API usage caveats in terms of comprehensiveness, explainability and best practices. In this work, we propose a novel approach that detects API misuses directly against the API caveat knowledge, rather than API usage patterns. We develop open information extraction methods to construct a novel API-constraint knowledge graph from API reference documentation. This knowledge graph explicitly models two types of API-constraint relations (call-order and condition-checking) and enriches return and throw relations with return conditions and exception triggers. It empowers the detection of three types of frequent API misuses - missing calls, missing condition checking and missing exception handling, while existing detectors mostly focus on only missing calls. As a proof-of-concept, we apply our approach to Java SDK API Specification. Our evaluation confirms the high accuracy of the extracted API-constraint relations. Our knowledge-driven API misuse detector achieves 0.60 (68/113) precision and 0.28 (68/239) recall for detecting Java API misuses in the API misuse benchmark MuBench. This performance is significantly higher than that of existing pattern-based API misused detectors. A pilot user study with 12 developers shows that our knowledge-driven API misuse detection is very promising in helping developers avoid API misuses and debug the bugs caused by API misuses.

Sequential user behavior modeling plays a crucial role in online user-oriented services, such as product purchasing, news feed consumption, and online advertising. The performance of sequential modeling heavily depends on the scale and quality of historical behaviors. However, the number of user behaviors inherently follows a long-tailed distribution, which has been seldom explored. In this work, we argue that focusing on tail users could bring more benefits and address the long tails issue by learning transferrable parameters from both optimization and feature perspectives. Specifically, we propose a gradient alignment optimizer and adopt an adversarial training scheme to facilitate knowledge transfer from the head to the tail. Such methods can also deal with the cold-start problem of new users. Moreover, it could be directly adaptive to various well-established sequential models. Extensive experiments on four real-world datasets verify the superiority of our framework compared with the state-of-the-art baselines.

Social recommendation, which aims at improving the performance of traditional recommender systems by considering social information, has attracted broad range of interests. As one of the most widely used methods, matrix factorization typically uses continuous vectors to represent user/item latent features. However, the large volume of user/item latent features results in expensive storage and computation cost, particularly on terminal user devices where the computation resource to operate model is very limited. Thus when taking extra social information into account, precisely extracting K most relevant items for a given user from massive candidates tends to consume even more time and memory, which imposes formidable challenges for efficient and accurate recommendations. A promising way is to simply binarize the latent features (obtained in the training phase) and then compute the relevance score through Hamming distance. However, such a two-stage hashing based learning procedure is not capable of preserving the original data geometry in the real-value space and may result in a severe quantization loss. To address these issues, this work proposes a novel discrete social recommendation (DSR) method which learns binary codes in a unified framework for users and items, considering social information. We further put the balanced and uncorrelated constraints on the objective to ensure the learned binary codes can be informative yet compact, and finally develop an efficient optimization algorithm to estimate the model parameters. Extensive experiments on three real-world datasets demonstrate that DSR runs nearly 5 times faster and consumes only with 1/37 of its real-value competitor’s memory usage at the cost of almost no loss in accuracy.

Neural Machine Translation (NMT) has achieved notable success in recent years.Such a framework usually generates translations in isolation.In contrast, human translators often refer to reference data, either rephrasing the intricate sentence fragments with common terms in source language, or just accessing to the golden translation directly.In this paper, we propose a Reference Network to incorporate referring process into translation decoding of NMT.To construct a reference book, an intuitive way is to store the detailed translation history with extra memory, which is computationally expensive.Instead, we employ Local Coordinates Coding (LCC) to obtain global context vectors containing monolingual and bilingual contextual information for NMT decoding.Experimental results on Chinese-English and English-German tasks demonstrate that our proposed model is effective in improving the translation quality with lightweight computation cost.

Developers often look for solutions to programming problems in community Q&A sites like Stack Overflow. Due to the crowdsourcing nature of these Q&A sites, many user-provided answers are wrong, less optimal or out-of-date. Relying on community-curated quality indicators (e.g., accepted answer, answer vote) cannot reliably identify these answer problems. Such problematic answers are often criticized by other users. However, these critiques are not readily discoverable when reading the posts. In this paper, we consider the answers being criticized and their critique posts as controversial discussions in community Q&A sites. To help developers notice such controversial discussions and make more informed choices of appropriate solutions, we design an automatic open information extraction approach for systematically discovering and summarizing the controversies in Stack Overflow and exploiting official API documentation to assist the understanding of the discovered controversies. We apply our approach to millions of java/android-tagged Stack overflow questions and answers and discover a large scale of controversial discussions in Stack Overflow. Our manual evaluation confirms that the extracted controversy information is of high accuracy. A user study with 18 developers demonstrates the usefulness of our generated controversy summaries in helping developers avoid the controversial answers and choose more appropriate solutions to programming questions.

Factorization Machine (FM) is a general supervised learning framework for many AI applications due to its powerful capability of feature engineering. Despite being extensively studied, existing FM methods have several limitations in common. First of all, most existing FM methods often adopt the squared loss in the modeling process, which can be very sensitive when the data for learning contains noises and outliers. Second, some recent FM variants often explore the low-rank structure of the feature interactions matrix by relaxing the low-rank minimization problem as a trace norm minimization, which cannot always achieve a tight approximation to the original one. To address the aforementioned issues, this paper proposes a new scheme of Robust Factorization Machine (RFM) by exploring a doubly capped norms minimization approach, which employs both a capped squared trace norm in achieving a tighter approximation of the rank minimization and a capped ℓ1-norm loss to enhance the robustness of the empirical loss minimization from noisy data. We develop an efficient algorithm with a rigorous convergence proof of RFM. Experiments on public real-world datasets show that our method outperforms the state-of-the-art FM methods significantly.

Efficiency is crucial to the online recommender systems, especially for the ones which needs to deal with tens of millions of users and items. Because representing users and items as binary vectors for Collaborative Filtering (CF) can achieve fast user-item affinity computation in the Hamming space, in recent years, we have witnessed an emerging research effort in exploiting binary hashing techniques for CF methods. However, CF with binary codes naturally suffers from low accuracy due to limited representation capability in each bit, which impedes it from modeling complex structure of the data.

Locally Linear Support Vector Machine (LLSVM) has been actively used in classification tasks due to its capability of classifying nonlinear patterns. However, existing LLSVM suffers from two drawbacks: (1) a particular and appropriate regularization for LLSVM has not yet been addressed; (2) it usually adopts a three-stage learning scheme composed of learning anchor points by clustering, learning local coding coordinates by a predefined coding scheme, and finally learning for training classifiers. We argue that this decoupled approaches oversimplifies the original optimization problem, resulting in a large deviation due to the disparate purpose of each step. To address the first issue, we propose a novel diversified regularization which could capture infrequent patterns and reduce the model size without sacrificing the representation power. Based on this regularization, we develop a joint optimization algorithm among anchor points, local coding coordinates and classifiers to simultaneously minimize the overall classification risk, which is termed as Diversified and Unified Locally Linear Support Vector Machine (DU-LLSVM for short). To the best of our knowledge, DU-LLSVM is the first principled method that directly learns sparse local coding and can be easily generalized to other supervised learning models. Extensive experiments showed that DU-LLSVM consistently surpassed several state-of-the-art methods with a predefined local coding scheme (e.g. LLSVM) or a supervised anchor point learning (e.g. SAPL-LLSVM).

Developers introduce bugs during software development which reduce software reliability. Many of these bugs are commonly occurring and have been experienced by many other developers. Informing developers, especially novice ones, about commonly occurring bugs in a domain of interest (e.g., Java), can help developers comprehend program and avoid similar bugs in the future. Unfortunately, information about commonly occurring bugs are not readily available. To address this need, we propose a novel approach named RFEB which recommends frequently encountered bugs (FEBugs) that may affect many other developers. RFEB analyzes Stack Overflow which is the largest software engineering-specific Q&A communities. Among the plenty of questions posted in Stack Overflow, many of them provide the descriptions and solutions of different kinds of bugs. Unfortunately, the search engine that comes with Stack Overflow is not able to identify FEBugs well. To address the limitation of the search engine of Stack Overflow, we propose RFEB which is an integrated and iterative approach that considers both relevance and popularity of Stack Overflow questions to identify FEBugs. To evaluate the performance of RFEB, we perform experiments on a dataset from Stack Overflow which contains more than ten million posts. We compared our model with Stack Overflow's search engine on 10 domains, and the experiment results show that RFEB achieves the average NDCG10 score of 0.96, which improves Stack Overflow's search engine by 20%.

Factorization Machines (FMs) are a widely used method for efficiently using high-order feature interactions in classification and regression tasks. Unfortunately, despite increasing interests in FMs, existing work only considers high order information of the input features which limits their capacities in non-linear problems and fails to capture the underlying structures of more complex data. In this work, we present a novel Locally Linear Factorization Machines (LLFM) which overcomes this limitation by exploring local coding technique. Unlike existing local coding classifiers that involve a phase of unsupervised anchor point learning and predefined local coding scheme which is suboptimal as the class label information is not exploited in discovering the encoding and thus can result in a suboptimal encoding for prediction, we formulate a joint optimization over the anchor points, local coding coordinates and FMs variables to minimize classification or regression risk. Empirically, we demonstrate that our approach achieves much better predictive accuracy than other competitive methods which employ LLFM with unsupervised anchor point learning and predefined local coding scheme.

GitHub contains millions of repositories among which many are similar with one another (i.e., having similar source codes or implementing similar functionalities). Finding similar repositories on GitHub can be helpful for software engineers as it can help them reuse source code, build prototypes, identify alternative implementations, explore related projects, find projects to contribute to, and discover code theft and plagiarism. Previous studies have proposed techniques to detect similar applications by analyzing API usage patterns and software tags. However, these prior studies either only make use of a limited source of information or use information not available for projects on GitHub. In this paper, we propose a novel approach that can effectively detect similar repositories on GitHub. Our approach is designed based on three heuristics leveraging two data sources (i.e., GitHub stars and readme files) which are not considered in previous works. The three heuristics are: repositories whose readme files contain similar contents are likely to be similar with one another, repositories starred by users of similar interests are likely to be similar, and repositories starred together within a short period of time by the same user are likely to be similar. Based on these three heuristics, we compute three relevance scores (i.e., readme-based relevance, stargazer-based relevance, and time-based relevance) to assess the similarity between two repositories. By integrating the three relevance scores, we build a recommendation system called RepoPal to detect similar repositories. We compare RepoPal to a prior state-of-the-art approach CLAN using one thousand Java repositories on GitHub. Our empirical evaluation demonstrates that RepoPal achieves a higher success rate, precision and confidence over CLAN.

Autoregressive integrated moving average (ARIMA) is one of the most popular linear models for time series forecasting due to its nice statistical properties and great flexibility. However, its parameters are estimated in a batch manner and its noise terms are often assumed to be strictly bounded, which restricts its applications and makes it inefficient for handling large-scale real data. In this paper, we propose online learning algorithms for estimating ARIMA models under relaxed assumptions on the noise terms, which is suitable to a wider range of applications and enjoys high computational efficiency. The idea of our ARIMA method is to reformulate the ARIMA model into a task of full information online optimization (without random noise terms). As a consequence, we can online estimation of the parameters in an efficient and scalable way. Furthermore, we analyze regret bounds of the proposed algorithms, which guarantee that our online ARIMA model is provably as good as the best ARIMA model in hindsight. Finally, our encouraging experimental results further validate the effectiveness and robustness of our method.

This paper aims to investigate efficient and scalable machine learning algorithms for resolving Non-negative Matrix Factorization (NMF), which is important for many real-world applications, particularly for collaborative filtering and recommender systems. Unlike traditional batch learning methods, a recently proposed online learning technique named "NN-PA" tackles NMF by applying the popular Passive-Aggressive (PA) online learning, and found promising results. Despite its simplicity and high efficiency, NN-PA falls short in at least two critical limitations: (i) it only exploits the first-order information and thus may converge slowly especially at the beginning of online learning tasks; (ii) it is sensitive to some key parameters which are often difficult to be tuned manually, particularly in a practical online learning system. In this work, we present a novel family of online Adaptive Passive-Aggressive (APA) learning algorithms for NMF, named "NN-APA", which overcomes two critical limitations of NN-PA by (i) exploiting second-order information to enhance PA in making more informative updates at each iteration; and (ii) achieving the parameter auto-selection by exploring the idea of online learning with expert advice in deciding the optimal combination of the key parameters in NMF. We theoretically analyze the regret bounds of the proposed method and show its advantage over the state-of-the-art NN-PA method, and further validate the efficacy and scalability of the proposed technique through an extensive set of experiments on a variety of large-scale real recommender systems datasets.

In practice, some bugs have more impact than others and thus deserve more immediate attention. Due to tight schedule and limited human resource, developers may not have enough time to inspect all bugs. Thus, they often concentrate on bugs that are highly impactful. In the literature, high impact bugs are used to refer to the bugs which appear in unexpected time or locations and bring more unexpected effects, or break pre-existing functionalities and destroy the user experience. Unfortunately, identifying high impact bugs from the thousands of bug reports in a bug tracking system is not an easy feat. Thus, an automated technique that can identify high-impact bug reports can help developers to be aware of them early, rectify them quickly, and minimize the damages they cause. Considering that only a small proportion of bugs are high impact bugs, the identification of high impact bug reports is a difficult task. In this paper, we propose an approach to identify high impact bug reports by leveraging imbalanced learning strategies. We investigate the effectiveness of various imbalanced learning strategies built upon a number of well-known classification algorithms. In particular, we choose four widely used strategies for dealing with imbalanced data and use naive Bayes multinominal as the classification algorithm to conduct experiments on four datasets from four different open source projects. We perform an empirical study on a specific type of high impact bugs, i.e., surprise bugs, which were first studied by Shihab et al. The results show that under-sampling is the best imbalanced learning strategy with naive Bayes multinominal for high impact bug identification.

Traditionally, to better understand the design of a project, developers can reconstruct a class diagram from source code using a reverse engineering technique. However, the raw diagram is often perplexing because there are too many classes in it. Condensing the reverse engineered class diagram into a compact class diagram which contains only the important classes would enhance the understandability of the corresponding project. A number of recent works have proposed several supervised machine learning solutions that can be used for condensing reverse engineered class diagrams given a set of classes that are manually labeled as important or not. However, a challenge impacts the practicality of the proposed solutions, which is the expensive cost for manual labeling of training samples. More training samples will lead to better performance, but means higher manual labeling cost. Too much manual labeling will make the problem pointless since the aim is to automatically identify important classes. In this paper, to bridge this research gap, we propose a novel approach MCCondenser which only requires a small amount of training data but can still achieve a reasonably good performance. MCCondenser firstly selects a small proportion of all data, which are the most representative, as training data in an unsupervised way using k-means clustering. Next, it uses ensemble learning to handle the class imbalance problem so that a suitable classifier can be constructed based on the limited training data. To evaluate the performance of MCCondenser, we use datasets from nine open source projects, i.e., ArgoUML, JavaClient, JGAP, JPMC, Mars, Maze, Neuroph, Wro4J and xUML, containing a total of 2640 classes. We compare MCCondenser with two baseline approaches proposed by Thung et al., both of which are state-of-the-art approaches aimed to reduce the manual labeling cost. The experimental results show that MCCondenser can achieve an average AUC score of 0.73, which improves those of the two baselines by nearly 20% and 10% respectively.

Concern localization refers to the process of locating code units that match a particular textual description. It takes as input textual documents such as bug reports and feature requests and outputs a list of candidate code units that are relevant to the bug reports or feature requests. Many information retrieval (IR) based concern localization techniques have been proposed in the literature. These techniques typically represent code units and textual descriptions as a bag of tokens at one level of abstraction, e.g., each token is a word, or each token is a topic. In this work, we propose a multi-abstraction concern localization technique named MULAB. MULAB represents a code unit and a textual description at multiple abstraction levels. Similarity of a textual description and a code unit is now made by considering all these abstraction levels. We combine a vector space model and multiple topic models to compute the similarity and apply a genetic algorithm to infer semi-optimal topic model configurations. We have evaluated our solution on 136 concerns from 8 open source Java software systems. The experimental results show that MULAB outperforms the state-of-art baseline PR, which is proposed by Scanniello et al. in terms of effectiveness and rank.

Similar bugs are bugs that require handling of many common code files. Developers can often fix similar bugs with a shorter time and a higher quality since they can focus on fewer code files. Therefore, similar bug recommendation is a meaningful task which can improve development efficiency. Rocha et al. propose the first similar bug recommendation system named NextBug. Although NextBug performs better than a start-of-the-art duplicated bug detection technique REP, its performance is not optimal and thus more work is needed to improve its effectiveness. Technically, it is also rather simple as it relies only upon a standard information retrieval technique, i.e., cosine similarity. In the paper, we propose a novel approach to recommend similar bugs. The approach combines a traditional information retrieval technique and a word embedding technique, and takes bug titles and descriptions as well as bug product and component information into consideration. To evaluate the approach, we use datasets from two popular open-source projects, i.e., Eclipse and Mozilla, each of which contains bug reports whose bug ids range from [1,400000]. The results show that our approach improves the performance of NextBug statistically significantly and substantially for both projects.

Typically a user prefers an item (e.g., a movie) because she likes certain features of the item (e.g., director, genre, producer). This observation motivates us to consider a feature-centric recommendation approach to item recommendation: instead of directly predicting the rating on items, we predict the rating on the features of items, and use such ratings to derive the rating on an item. This approach offers several advantages over the traditional item-centric approach: it incorporates more information about why a user chooses an item, it generalizes better due to the denser feature rating data, it explains the prediction of item ratings through the predicted feature ratings. Another contribution is turning a principled item-centric solution into a feature-centric solution, instead of inventing a new algorithm that is feature-centric. This approach maximally leverages previous research. We demonstrate this approach by turning the traditional item-centric latent factor model into a feature-centric solution and demonstrate its superiority over item-centric approaches.

As location-based social network (LBSN) services become increasingly popular, trip recommendation that recommends a sequence of points of interest (POIs) to visit for a user emerges as one of many important applications of LBSNs. Personalized trip recommendation tailors to users' specific tastes by learning from past check-in behaviors of users and their peers. Finding the optimal trip that maximizes user's experiences for a given time budget constraint is an NP hard problem and previous solutions do not consider two practical and important constraints. One constraint is POI availability where a POI may be only available during a certain time window. Another constraint is uncertain traveling time where the traveling time between two POIs is uncertain. This work presents efficient solutions to personalized trip recommendation by incorporating these constraints to prune the search space. We evaluated the efficiency and effectiveness of our solutions on real life LBSN data sets.

To help developers better allocate testing and debugging efforts, many software defect prediction techniques have been proposed in the literature. These techniques can be used to predict classes that are more likely to be buggy based on past history of buggy classes. These techniques work well as long as a sufficient amount of data is available to train a prediction model. However, there is rarely enough training data for new software projects. To deal with this problem, cross-project defect prediction, which transfers a prediction model trained using data from one project to another, has been proposed and is regarded as a new challenge for defect prediction. So far, only a few cross-project defect prediction techniques have been proposed. To advance the state-of-the-art, in this work, we investigate 7 composite algorithms, which integrate multiple machine learning classifiers, to improve cross-project defect prediction. To evaluate the performance of the composite algorithms, we perform experiments on 10 open source software systems from the PROMISE repository which contain a total of 5,305 instances labeled as defective or clean. We compare the composite algorithms with CODEP Logistic, which is the latest cross-project defect prediction algorithm proposed by Panichella et al., in terms of two standard evaluation metrics: cost effectiveness and F-measure. Our experiment results show that several algorithms outperform CODEP Logistic: Max performs the best in terms of F-measure and its average F-measure outperforms that of CODEP Logistic by 36.88%. Bagging J48 performs the best in terms of cost effectiveness and its average cost effectiveness outperforms that of CODEP Logistic by 15.34%.

In recent years, to help developers reduce time and effort required to build highly secure software, a number of prediction models which are built on different kinds of features have been proposed to identify vulnerable source code files. In this paper, we propose a novel approach VULPREDICTOR to predict vulnerable files, it analyzes software metrics and text mining together to build a composite prediction model. VULPREDICTOR first builds 6 underlying classifiers on a training set of vulnerable and non-vulnerable files represented by their software metrics and text features, and then constructs a meta classifier to process the outputs of the 6 underlying classifiers. We evaluate our solution on datasets from three web applications including Drupal, PHPMyAdmin and Moodle which contain a total of 3,466 files and 223 vulnerabilities. The experiment results show that VULPREDICTOR can achieve F1 and EffectivenessRatio@20% scores of up to 0.683 and 75%, respectively. On average across the 3 projects, VULPREDICTOR improves the F1 and EffectivenessRatio@20% scores of the best performing state-of-the-art approaches proposed by Walden et al. by 46.53% and 14.93%, respectively.

Defect prediction is a very meaningful topic, particularly at change-level. Change-level defect prediction, which is also referred as just-in-time defect prediction, could not only ensure software quality in the development process, but also make the developers check and fix the defects in time. Nowadays, deep learning is a hot topic in the machine learning literature. Whether deep learning can be used to improve the performance of just-in-time defect prediction is still uninvestigated. In this paper, to bridge this research gap, we propose an approach Deeper which leverages deep learning techniques to predict defect-prone changes. We first build a set of expressive features from a set of initial change features by leveraging a deep belief network algorithm. Next, a machine learning classifier is built on the selected features. To evaluate the performance of our approach, we use datasets from six large open source projects, i.e., Bugzilla, Columba, JDT, Platform, Mozilla, and PostgreSQL, containing a total of 137,417 changes. We compare our approach with the approach proposed by Kamei et al. The experimental results show that on average across the 6 projects, Deeper could discover 32.22% more bugs than Kamei et al's approach (51.04% versus 18.82% on average). In addition, Deeper can achieve F1-scores of 0.22-0.63, which are statistically significantly higher than those of Kamei et al.'s approach on 4 out of the 6 projects.

User preferences change over time and capturing such changes is essential for developing accurate recommender systems. Despite its importance, only a few works in collaborative filtering have addressed this issue. In this paper, we consider evolving preferences and we model user dynamics by introducing and learning a transition matrix for each user's latent vectors between consecutive time windows. Intuitively, the transition matrix for a user summarizes the time-invariant pattern of the evolution for the user. We first extend the conventional probabilistic matrix factorization and then improve upon this solution through its fully Bayesian model. These solutions take advantage of the model complexity and scalability of conventional Bayesian matrix factorization, yet adapt dynamically to user's evolving preferences. We evaluate the effectiveness of these solutions through empirical studies on six large-scale real life data sets.

Information propagation in a microblog network aims to identify a set of seed users for propagating a target message to as many interested users as possible. This problem differs from the traditional influence maximization in two major ways: it has a content-rich target message for propagation and it treats each link in the network as communication on certain topics and emphasizes the topic relevance of such communication in propagating the target message. In realistic situations, however, the topics associated with a link are not explicitly expressed but are hidden in the microblogs previously exchanged through the link. In this paper, we present a topic-aware solution to information propagation in a microblog network. We first model the latent topic structure of the network using observed microblog messages published in the network. We then present two methods for estimating the propagation probability based on the topic relevance between a link and the target message. Once the propagation probability is estimated, we adopt the standard greedy algorithm for influence maximization to find seed users. This approach is topic-aware in that the target message finds its way of propagation according to its topic relevance to the latent topic structure in the network. Experiments conducted on real Twitter datasets suggest that the proposed methods are able to select right seed users.

With the prevalence of web services, services orchestration evolves from intra-enterprise integration to cross-domain integration and involves multiple networks. In traditional centralized SOA, the execution engine suffers from single point of failure and performance of composite services will be affected by the network conditions because of cross domain message transmissions. In this paper, we present a decentralized orchestration model for cross-domain multiple networks environment. Based on this model, we propose a Genetic Algorithm to find an optimization deployment solution for component services with minimum cross-domain network cost and thus increase the performance of composite services.

Web service composition is a low cost and efficient way to leverage the existing resource and implementation. In current Web service composition implementations, the issue of how to define the role for a new composite Web service has been little addressed. Adjusting the access control policy for a new composite Web service always causes substantial administration overhead from the security administrator. Furthermore, the distributed nature of Web service based applications makes traditional role mining methods obsolete. In this paper, we analyze the minimal role mining problem for Web service composition, and prove that this problem is NP-complete. We propose a sub-optimal greedy algorithm based on the analysis of necessary role mapping for interoperation across multiple domains. Simulation shows the effectiveness of our algorithm, and compared to the existing methods, our algorithm has significant performance advantages. We also demonstrate the practical application of our method in a real agent based Web service system. The results show that our method could find the minimal role mapping efficiently.

Little is known about how to preprocess the noise in legacy access control data when migrating to the Role-based Access Control model. This paper presents an experience report on the noise preprocess method of the legacy access control data of several financial systems. The main goal of this project is to improve the quality of the roles obtained via role mining.

We address why, and especially how, to represent field-oriented XML-based rule file in form validation for Web applications. Motivated by the decades-old problem of frequently changing requirements for software development, we propose a descriptive solution to validation on Web form data. By extracting all database-isolated rules, which are to be implemented on both client-side and server-side, into standalone rule file in a field-oriented format, management of business rules on either side can be simplified to a great extent. The main advantage of our approach is a consistency guarantee of validation logic performed by presentation and application layer, as well as prominent clarity in representation and notable flexibility in modification. It's a tailored replacement for traditional realization of hard-code, which results in redundant work, tight coupling structure, and highly possible inconformity of rules between both sides.

Many enterprise systems were developed in standalone model since the end of the last century. Reengineering standalone systems into distributed environment has become a critical problem, as the standalone software can not meet the requirements of the new market. Methods have been proposed on related topics based on two classical distributed solutions, the symmetrical model and the unsymmetrical model. In this paper we report the experience in reengineering a standalone financial trading system into the service-partition distributed environment, which offers distinct advantages on horizontal scalability and performance over two classical distributed solutions.

Many enterprise systems are developed in C++ language and most of them are standalone. Because the standalone software can not follow the new market environment, reengineering the standalone legacy systems into distributed environment becomes a critical problem. Some methods have been proposed on related topics such as design recovery, the identification of the component, modeling the interfaces of components and components allocation. Up to now, there does not exist a reengineering process for partition distributed environment, which will offer distinct advantages on horizontal scalability and performance over normal distributed solutions. This paper presents a new process to reengineer C++ legacy systems into the J2EE partition distributed environment. The process consists of four steps: translation from C++ to Java code; extraction of components using the cluster technology; modeling component interfaces and partition of the components in J2EE distribute environment. It has been applied to a large equity-trading legacy system which has proved to be successful.

Rapid developments in computer technology have resulted in greater reliance on distributed computing, typified by "client/server" or "subscriber/push" architectures. These servers provide central resource to individual clients on local area network or Internet systems. Unfortunately, frequent and unplanned network failures were routine, and downtime was not in hours, but in days. Cluster technology has solved the non-stop problem on local area network. However, most technologies including cluster today fail to ensure the non-stop Internet serving for its clients without stop while one or more servers have failed. With good performance on fault tolerance and availability, quorum system is very suitable to be applied in the distributed network system. In this paper, we modeled and developed a non-stop Internet service system based on a new quorum system, Circle Quorum System, for Boston Mutual Fund Broker, US. With three protocols, it provided highly available data services for clients on Internet.