Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not always be the case. As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data

Point-of-Interest (POI) recommendation has been extensively studied and successfully applied in industry recently. However, most existing approaches build centralized models on the basis of collecting users’ data. Both private data and models are held by the recommender, which causes serious privacy concerns. In this article, we propose a novel Privacy preserving POI Recommendation (PriRec) framework

Canonical correlation analysis (CCA) is a typical and useful learning paradigm in big data analysis for capturing correlation across multiple views of the same objects. When dealing with data with additional ordinal information, traditional CCA suffers from poor performance due to ignoring the ordinal relationships within the data. Such data is becoming increasingly common, as either temporal or sequential

It is always deemed crucial to identify the key factors that could have significant impact on the stock market trend. Recently, an interesting phenomenon has emerged that some of President Trump’s posts in Twitter can surge into a dominant role on the stock market for a certain time period, although studies along this line are still in their infancy. Therefore, in this article, we study whether and

The current trend toward urbanization and adoption of flexible and innovative mobility technologies will have complex and difficult-to-predict effects on urban transportation systems. Comprehensive methodological frameworks that account for the increasingly uncertain future state of the urban mobility landscape do not yet exist. Furthermore, few approaches have enabled the massive ingestion of urban

As location-based services using mobile devices have become globally popular these days, social network analysis (especially, community detection) increasingly benefits from combining social relationships with geographic preferences. In this regard, this article addresses the emerging problem of geosocial community detection. We first formalize the problem of geosocial co-clustering, which co-clusters

Rumor spread in social media severely jeopardizes the credibility of online content. Thus, automatic debunking of rumors is of great importance to keep social media a healthy environment. While facing a dubious claim, people often dispute its truthfulness sporadically in their posts containing various cues, which can form useful evidence with long-distance dependencies. In this work, we propose to

Automatic and accurate semantic segmentation of pathological structures in medical images is challenging because of noisy disturbance, deformable shapes of pathology, and low contrast between soft tissues. Classical superpixel-based classification algorithms suffer from edge leakage due to complexity and heterogeneity inherent in medical images. Therefore, we propose a deep U-Net with superpixel region

Increasingly sophisticated image editing tools make it easy to modify images. Often these modifications are elaborate, convincing, and undetectable by even careful human inspection. These considerations have prompted the development of forensic algorithms and approaches to detect modifications done to an image. However, these detectors are model-driven (i.e., manipulation-specific) and the choice of

Multi-source domain adaptation has received considerable attention due to its effectiveness of leveraging the knowledge from multiple related sources with different distributions to enhance the learning performance. One of the fundamental challenges in multi-source domain adaptation is how to determine the amount of knowledge transferred from each source domain to the target domain. To address this

Biometric authentication involves various technologies to identify individuals by exploiting their unique, measurable physiological and behavioral characteristics. However, traditional biometric authentication systems (e.g., face recognition, iris, retina, voice, and fingerprint) are at increasing risks of being tricked by biometric tools such as anti-surveillance masks, contact lenses, vocoder, or

Natural language generation has become a fundamental task in dialogue systems. RNN-based natural response generation methods encode the dialogue context and decode it into a response. However, they tend to generate dull and simple responses. In this article, we propose a novel framework, called KAWA-DRG (Knowledge-aware Attentive Wasserstein Adversarial Dialogue Response Generation) to model conversation-specific

Due to the ever-growing concerns over air pollution and energy security, more and more cities have started to replace their conventional taxi fleets with electric ones. Even though environmentally friendly, the rapid promotion of electric taxis raises problems to both taxi drivers and governments, e.g., prolonged waiting/charging time, unbalanced utilization of charging infrastructures, and inadequate

Object segmentation and object tracking are fundamental research areas in the computer vision community. These two topics are difficult to handle some common challenges, such as occlusion, deformation, motion blur, scale variation, and more. The former contains heterogeneous object, interacting object, edge ambiguity, and shape complexity; the latter suffers from difficulties in handling fast motion

With the explosive growth of web resources, an increasingly important task in recommender systems is to provide high-quality personalized services by learning users’ preferences from historically observed information. As an effective preference learning technology, collaborative filtering has been widely extended to model the one-class or implicit feedback data, which is known as one-class collaborative

In this article, we propose a novel temporal pattern mining problem, named high-utility temporal pattern mining, to fulfill the needs of various applications. Different from classical temporal pattern mining aimed at discovering frequent temporal patterns, high-utility temporal pattern mining is to find each temporal pattern whose utility is greater than or equal to the minimum-utility threshold. To

Although the performance of automatically generating high-resolution realistic images from text descriptions has been significantly boosted, many challenging issues in image synthesis have not been fully investigated, due to shapes variations, viewpoint changes, pose changes, and the relations of multiple objects. In this article, we propose a novel end-to-end approach for text-to-image synthesis with

Acquiring traffic condition information is of great significance in transportation guidance, urban planning, and route recommendation. To date, traffic density data are generally acquired by road sound analysis, video data analysis, or in-vehicle network communication, which are usually financially or temporally expensive. Another way to get traffic conditions is to collect track data by crowdsourcing

This paper proposed an method to select EEG channels based on EEG shapelet learning, to reduce the setup time and inconvenience for subjects and to improve the applicable performance of Brian-Computer Interfaces (BCIs). This method transformed multi-channel EEG signals into EEG shapalet space and then selected top-k EEG channels that minimized a logistic loss-embedded optimization function. Meanwhile

Feature representation and feature extraction are two crucial procedures in text mining. Convolutional Neural Networks (CNN) have shown overwhelming success for text mining tasks since it is capable of efficiently extracting n-gram features from source data. However, CNN has its own weaknesses on feature representation and feature extraction. A certain amount of filters in CNN are inevitably duplicate

Because review fraud is now a common occurrence in virtually all major e-commerce platforms, a number of excellent algorithms to detect review fraud have been developed by the research community. We propose the Sockpuppet-based Targeted Attack on Reviewing Systems (STARS for short) whose goal is to compromise review fraud detectors. STARS is a realistic attack that will likely be used by review fraudsters

Deep Neural Networks (DNNs) are widely used in many Artificial Intelligence (AI) applications. They have demonstrated state-of-the-art accuracy on many AI tasks. For this high accuracy to occur, DNNs require to have the right parameter values. This is achieved by a process known as \textit{training}. The training of large amounts of data via many iterations comes at a high cost in regards to computation

Entity recommendation, providing users with an improved search experience by proactively recommending related entities to a given query, has become an indispensable feature of today's Web search engine. However, most existing studies on entity recommendation typically do not take into account a user's full search history or completely ignore such information. As a consequence, they may be insensitive

Recent hurricane events have caused unprecedented amounts of damage and severely threatened our public safety and economy mainly through the damage they in?ict on critical infrastructure systems. The most observable (and severe) impact of these hurricanes is the loss of electric power in many regions, which causes the breakdown of essential public services. Understanding the power outages and how they

In this paper, we study solder paste inspection (SPI), an important stage that is used in the semiconductor manufacturing industry, where abnormal boards should be detected. A highly accurate SPI can substantially reduce human expert involvement as well as reduce the waste in disposing of the boards in good condition. A key difference today is that, because of increasing demand in board customization

Large networks are becoming a widely used abstraction for studying complex systems in a broad set of disciplines, ranging from social network analysis to molecular biology and neuroscience. Despite an increasing need to analyze and manipulate large networks, only a limited number of tools are available for this task. Here, we describe Stanford Network Analysis Platform (SNAP), a general-purpose, high-performance

Modeling physical activity propagation, such as activity level and intensity, is a key to preventing obesity from cascading through communities, and to helping spread wellness and healthy behavior in a social network. However, there have not been enough scientific and quantitative studies to elucidate how social communication may deliver physical activity interventions. In this work, we introduce a

Transfer learning aims to improve performance on a target task by utilizing previous knowledge learned from source tasks. In this paper we introduce a novel heterogeneous transfer learning technique, Feature- Space Remapping (FSR), which transfers knowledge between domains with different feature spaces. This is accomplished without requiring typical feature-feature, feature instance, or instance-instance

We study the problem of learning classification models from complex multivariate temporal data encountered in electronic health record systems. The challenge is to define a good set of features that are able to represent well the temporal aspect of the data. Our method relies on temporal abstractions and temporal pattern mining to extract the classification features. Temporal pattern mining usually

We employ Add Health data to show that friendship networks, constructed from mutual friendship nominations, are important in building weight perception, setting weight goals and measuring social marginalization among adolescents and young adults. We study the relationship between individuals' perceived weight status, actual weight status, weight status relative to friends' weight status and weight

One of the principal goals in medicine is to determine and implement the best treatment for patients through fastidious estimation of the effects and benefits of therapeutic procedures. The inherent complexities of physiological and pathological networks that span across orders of magnitude in time and length scales, however, represent fundamental hurdles in determining effective treatments for patients