Linux kernel stable versions serve the needs of users who value stability of the kernel over new features. The quality of such stable versions depends on the initiative of kernel developers and maintainers to propagate bug fixing patches to the stable versions. Thus, it is desirable to consider to what extent this process can be automated. A previous approach relies on words from commit messages and a small set of manually constructed code features. This approach, however, shows only moderate accuracy. In this paper, we investigate whether deep learning can provide a more accurate solution. We propose PatchNet, a hierarchical deep learning-based approach capable of automatically extracting features from commit messages and commit code and using them to identify stable patches. PatchNet contains a deep hierarchical structure that mirrors the hierarchical and sequential structure of commit code, making it distinctive from the existing deep learning models on source code. Experiments on 82,403 recent Linux patches confirm the superiority of PatchNet against various state-of-the-art baselines, including the one recently-adopted by Linux kernel maintainers.

Social collaborative platforms such as GitHub and Stack Overflow have been increasingly used to improve work productivity via collaborative efforts. To improve user experiences in these platforms, it is desirable to have a recommender system that can suggest not only items (e.g., a GitHub repository) to a user, but also activities to be performed on the suggested items (e.g., forking a repository). To this end, we propose a new approach dubbed Keen2Act, which decomposes the recommendation problem into two stages: the Keen and Act steps. The Keen step identifies, for a given user, a (sub)set of items in which he/she is likely to be interested. The Act step then recommends to the user which activities to perform on the identified set of items. This decomposition provides a practical approach to tackling complex activity recommendation tasks while producing higher recommendation quality. We evaluate our proposed approach using two real-world datasets and obtain promising results whereby Keen2Act outperforms several baseline models.

Developers often spend much effort and resources to debug a program. To help the developers debug, numerous information retrieval (IR)-based and spectrum-based bug localization techniques have been devised. IR-based techniques process textual information in bug reports, while spectrum-based techniques process program spectra (i.e., a record of which program elements are executed for each test case). While both techniques ultimately generate a ranked list of program elements that likely contain a bug, they only consider one source of information-either bug reports or program spectra-which is not optimal. In light of this deficiency, this paper presents a new approach dubbed Network-clustered Multi-modal Bug Localization (NetML), which utilizes multi-modal information from both bug reports and program spectra to localize bugs. NetML facilitates an effective bug localization by carrying out a joint optimization of bug localization error and clustering of both bug reports and program elements (i.e., methods). The clustering is achieved through the incorporation of network Lasso regularization, which incentivizes the model parameters of similar bug reports and similar program elements to be close together. To estimate the model parameters of both bug reports and methods, NetML employs an adaptive learning procedure based on Newton method that updates the parameters on a per-feature basis. Extensive experiments on 355 real bugs from seven software systems have been conducted to benchmark NetML against various state-of-the-art localization methods. The results show that NetML surpasses the best-performing baseline by 31.82, 22.35, 19.72, and 19.24 percent, in terms of the number of bugs successfully localized when a developer inspects the top 1, 5, and 10 methods and Mean Average Precision (MAP), respectively.

Analyzing job hopping behavior is important for understanding job preference and career progression of working individuals. When analyzed at the workforce population level, job hop analysis helps to gain insights of talent flow among different jobs and organizations. Traditionally, surveys are conducted on job seekers and employers to study job hop behavior. Beyond surveys, job hop behavior can also be studied in a highly scalable and timely manner using a data-driven approach in response to fast-changing job landscape. Fortunately, the advent of online professional networks (OPNs) has made it possible to perform a large-scale analysis of talent flow. In this paper, we present a new data analytics framework to analyze the talent flow patterns of close to 1 million working professionals from three different countries/regions using their publicly accessible profiles in an established OPN. As OPN data are originally generated for professional networking applications, our proposed framework repurposes the same data for a different analytics task. Prior to performing job hop analysis, we devise a job title normalization procedure to mitigate the amount of noise in the OPN data. We then devise several metrics to measure the amount of work experience required to take up a job, to determine that the duration of a job’s existence (also known as the job age), and the correlation between the above metric and propensity of hopping. We also study how job hop behavior is related to job promotion/demotion. Lastly, we perform connectivity analysis at job and organization levels to derive insights on talent flow as well as job and organizational competitiveness.

Traffic speed is a key indicator for the efficiency of an urban transportation system. Accurate modeling of the spatiotemporally varying traffic speed thus plays a crucial role in urban planning and development. This paper addresses the problem of efficient fine-grained traffic speed prediction using big traffic data obtained from static sensors. Gaussian processes (GPs) have been previously used to model various traffic phenomena, including flow and speed. However, GPs do not scale with big traffic data due to their cubic time complexity. In this work, we address their efficiency issues by proposing localGPs to learn from and make predictions for correlated subsets of data. The main idea is to quickly group speed variables in both spatial and temporal dimensions into a finite number of clusters, so that future and unobserved traffic speed queries can be heuristically mapped to one of such clusters. A local GP corresponding to that cluster can then be trained on the fly to make predictions in real-time. We call this method localization. We use non-negative matrix factorization for localization and propose simple heuristics for cluster mapping. We additionally leverage on the expressiveness of GP kernel functions to model road network topology and incorporate side information. Extensive experiments using real-world traffic data collected in the two U.S. cities of Pittsburgh and Washington, D.C., show that our proposed local GPs significantly improve both runtime performances and prediction accuracies compared to the baseline global and local GPs.

The advent of the Web brought about major changes in the way people search for jobs and companies look for suitable candidates. As more employers and recruitment firms turn to the Web for job candidate search, an increasing number of people turn to the Web for uploading and creating their online resumes. Resumes are often the first source of information about candidates and also the first item of evaluation in candidate selection. Thus, it is imperative that resumes are complete, free of errors and well-organized. We present an automated resume evaluation tool called “CareerMapper”. Our tool is designed to conduct a thorough review of a user's LinkedIn profile and provide best recommendations for improved online resumes by analyzing a large number of online user profiles.

The abundance of algorithms developed to solve different problems has given rise to an important research question: How do we choose the best algorithm for a given problem? Known as algorithm selection, this issue has been prevailing in many domains, as no single algorithm can perform best on all problem instances. Traditional algorithm selection and portfolio construction methods typically treat the problem as a classification or regression task. In this paper, we present a new approach that provides a more natural treatment of algorithm selection and portfolio construction as a ranking task. Accordingly, we develop a Ranking-Based Algorithm Selection (RAS) method, which employs a simple polynomial model to capture the ranking of different solvers for different problem instances. We devise an efficient iterative algorithm that can gracefully optimize the polynomial coefficients by minimizing a ranking loss function, which is derived from a sound probabilistic formulation of the ranking problem. Experiments on the SAT 2012 competition dataset show that our approach yields competitive performance to that of more sophisticated algorithm selection methods.

Debugging often takes much effort and resources. To help developers debug, numerous information retrieval (IR)-based and spectrum-based bug localization techniques have been proposed. IR-based techniques process textual information in bug reports, while spectrum-based techniques process program spectra (i.e., a record of which program elements are executed for each test case). Both eventually generate a ranked list of program elements that are likely to contain the bug. However, these techniques only consider one source of information, either bug reports or program spectra, which is not optimal. To deal with the limitation of existing techniques, in this work, we propose a new multi-modal technique that considers both bug reports and program spectra to localize bugs. Our approach adaptively creates a bug-specific model to map a particular bug to its possible location, and introduces a novel idea of suspicious words that are highly associated to a bug. We evaluate our approach on 157 real bugs from four software systems, and compare it with a state-of-the-art IR-based bug localization method, a state-of-the-art spectrum-based bug localization method, and three state-of-the-art multi-modal feature location methods that are adapted for bug localization. Experiments show that our approach can outperform the baselines by at least 47.62%, 31.48%, 27.78%, and 28.80% in terms of number of bugs successfully localized when a developer inspects 1, 5, and 10 program elements (i.e., Top 1, Top 5, and Top 10), and Mean Average Precision (MAP) respectively.

Mobile advertising has recently seen dramatic growth, fueled by the global proliferation of mobile phones and devices. The task of predicting ad response is thus crucial for maximizing business revenue. However, ad response data change dynamically over time, and are subject to cold-start situations in which limited history hinders reliable prediction. There is also a need for a robust regression estimation for high prediction accuracy, and good ranking to distinguish the impacts of different ads. To this end, we develop a Hierarchical Importance-aware Factorization Machine (HIFM), which provides an effective generic latent factor framework that incorporates importance weights and hierarchical learning. Comprehensive empirical studies on a real-world mobile advertising dataset show that HIFM outperforms the contemporary temporal latent factor models. The results also demonstrate the efficacy of the HIFM's importance-aware and hierarchical learning in improving the overall prediction and prediction in cold-start scenarios, respectively.

The problem of recommending items to users is relevant to many applications and the problem has often been solved using methods developed from Collaborative Filtering (CF). Collaborative Filtering model-based methods such as Matrix Factorization have been shown to produce good results for static rating-type data, but have not been applied to time-stamped item adoption data. In this paper, we adopted a Dynamic Matrix Factorization (DMF) technique to derive different temporal factorization models that can predict missing adoptions at different time steps in the users' adoption history. This DMF technique is an extension of the Non-negative Matrix Factorization (NMF) based on the well-known class of models called Linear Dynamical Systems (LDS). By evaluating our proposed models against NMF and TimeSVD++ on two real datasets extracted from ACM Digital Library and DBLP, we show empirically that DMF can predict adoptions more accurately than the NMF for several prediction tasks as well as outperforming TimeSVD++ in some of the prediction tasks. We further illustrate the ability of DMF to discover evolving research interests for a few author examples.

In service-based industries, churn poses a significant threat to the integrity of the user communities and profitability of the service providers. As such, research on churn prediction methods has been actively pursued, involving either intrinsic, user profile factors or extrinsic, social factors. However, existing approaches often address each type of factors separately, thus lacking a comprehensive view of churn behaviors. In this paper, we propose a new churn prediction approach based on collective classification (CC), which accounts for both the intrinsic and extrinsic factors by utilizing the local features of, and dependencies among, individuals during prediction steps. We evaluate our CC approach using real data provided by an established mobile social networking site, with a primary focus on prediction of churn in chat activities. Our results demonstrate that using CC and social features derived from interaction records and network structure yields substantially improved prediction in comparison to using conventional classification and user profile features only.

The existence of many pattern recognition systems (PRSs) and their relative merits and drawbacks highlights the need for a metalearning framework that can find the best PRS method for a given task. To address this issue, a hyperparameter evolutionary optimization (HPEO) framework was previously devised, initially using a genetic algorithm to tune external PRS parameters in a modular fashion, decoupled from its internal components. To further improve the effectiveness of HPEO and improve the diversity of the hyperparameter solutions found, this paper presents an extension that realizes cross-generation learning with an adaptive history network (AHN), which promotes exploring new regions in the search space while avoiding regions that have been searched extensively. The proposed approach, termed HPEO-AHN, is particularly suitable for tuning powerful but complex PRSs such as neuro-fuzzy systems (NFS). Preliminary experiments with two state-of-the-art NFSs optimized using the new approach have shown encouraging results.

Fuzzy and neuro-fuzzy systems are increasingly among the key technologies employed in many real-world applications. However, traditional neuro-fuzzy systems are generally still lacking the scalability traits required in the face of large-scale data and the capability to incorporate new information without catastrophically disrupting the existing knowledge base. This work aims at addressing these issues by proposing a novel neuro-fuzzy system termed dual consolidation network (DCN) that models the complementary interactions between hippocampus and neocortex regions in the human brain to consolidate and exploit knowledge effectively. This approach allows the DCN to handle data sets with high-dimensional features and/or a very large number of samples efficiently, as well as to minimize interference when acquiring new information. Preliminary experiments employing DCN on large-scale biomedical data have shown encouraging results.

Artificial intelligence research is now flourishing which aims at achieving general, human-level intelligence. Accordingly, cognitive architectures are increasingly employed as blueprints for building intelligent agents to be endowed with various perceptive and cognitive abilities. This paper presents a novel integrated neuro-cognitive architecture (INCA) which emulate the putative functional aspects of various salient brain sub-systems via a learning memory modeling approach. The strength of INCA lies in self-organizing connectionist learning to induce high-level symbolic knowledge autonomously, and support for meta-cognitive functions. Its overall operations are governed by its consolidation and inference cycles, which posit a human-plausible way for forming and exploiting knowledge.

Localist networks and especially neuro-fuzzy systems constitute promising techniques for data comprehension, but generally exhibit poor system interpretability and generalization ability. This paper aims at addressing the issues through a novel localist reduced fuzzy cerebellar model articulation controller (RFCMAC), that models the two-stage development of cortical memories in the human brain to compress and refine the formulated (fuzzy) rule base respectively. The proposed mechanisms allow the RFCMAC associative memory to induce a concise, interpretable rule base, and at the same time to improve generalization, fostering in turn system scalability and robustness. Experimental results on several benchmark tasks have demonstrated the potential of the proposed system as an effective tool for understanding data.

This paper proposes a novel generic meta-level parameter optimization framework to address the problem of determining the optimal parameters of pattern recognition systems. The proposed framework is currently implemented to control the parameters of neuro-fuzzy system, a subclass of pattern recognition system, by employing a genetic algorithm (GA) as the core optimization technique. Two neuro-fuzzy systems i.e., generic self-organizing fuzzy neural network realizing Yager inference (GenSoFNN-Yager) and reduced fuzzy cerebellar model articulation computer realizing the Yager inference (RFCMAC-Yager), are employed as the test prototypes to evaluate the proposed framework. Experimental results on several classification and regression problems have shown the efficacy and robustness of the proposed approach.

Recent advances in cognitive neuroscience have revealed the role of hippocampal region as a mediator for explicit memory, which is crucial for human cognitive processes and for developing machine intelligence. This paper presents the novel Generic Self-organizing Fuzzy Neural Network realizing Yager inference (GENSOFNN-YAGER) that is built specifically to model the functional aspects of hippocampus as explicit memory and to emulate human decision making abilities. The main feature of the Yager inference is that, when the input matches the rule antecedent exactly, the resultant output matches the consequent exactly, in a way similar to that of human reasoning. The presented experimental results show the effectiveness of the proposed system.

This paper presents part of the research work carried out at the Centre for Computational Intelligence at NTU to develop novel technologies for the routing, navigation, and control of intelligent cars. One objective is to endow the cars with the ability to autonomously drive on various types of roads and realize manoeuvres such as reverse and parallel parking, three-point turns, etc. Our approach is to design a self-training system that makes use of human expertise to automatically derive a working car control system. A new neuro-fuzzy architecture known as the GenSoYager fuzzy neural network has been realized and integrated with our car-driving simulator for training and testing purposes. The GenSoYagerFNN has proven so far superior to other trained networks in detecting parking slots and accomplishing reverse parking manoeuvres. The approach described has also been validated using a microprocessor controlled model car.