Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences Commons™

Open Access. Powered by Scholars. Published by Universities.®

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 4531 - 4560 of 9025

Full-Text Articles in Computer Sciences

Face Detection Using Deep Learning: An Improved Faster Rcnn Approach, Xudong Sun, Pengcheng Wu, Steven C. H. Hoi Jul 2018

Face Detection Using Deep Learning: An Improved Faster Rcnn Approach, Xudong Sun, Pengcheng Wu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

In this paper, we present a new face detection scheme using deep learning and achieve the state-of-the-art detection performance on the well-known FDDB face detection benchmark evaluation. In particular, we improve the state-of-the-art Faster RCNN framework by combining a number of strategies, including feature concatenation, hard negative mining, multi-scale training, model pre-training, and proper calibration of key parameters. As a consequence, the proposed scheme obtained the state-of-the-art face detection performance and was ranked as one of the best models in terms of ROC curves of the published methods on the FDDB benchmark

Go to article

Modeling Contemporaneous Basket Sequences With Twin Networks For Next-Item Recommendation, Duc Trong Le, Hady W. Lauw, Yuan Fang Jul 2018

Modeling Contemporaneous Basket Sequences With Twin Networks For Next-Item Recommendation, Duc Trong Le, Hady W. Lauw, Yuan Fang

Research Collection School Of Computing and Information Systems

Our interactions with an application frequently leave a heterogeneous and contemporaneous trail of actions and adoptions (e.g., clicks, bookmarks, purchases). Given a sequence of a particular type (e.g., purchases)-- referred to as the target sequence, we seek to predict the next item expected to appear beyond this sequence. This task is known as next-item recommendation. We hypothesize two means for improvement. First, within each time step, a user may interact with multiple items (a basket), with potential latent associations among them. Second, predicting the next item in the target sequence may be helped by also learning from another supporting sequence …

Go to article

Pacela: A Neural Framework For User Visitation In Location-Based Social Networks, Thanh Nam Doan, Ee-Peng Lim Jul 2018

Pacela: A Neural Framework For User Visitation In Location-Based Social Networks, Thanh Nam Doan, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Check-in prediction using location-based social network data is an important research problem for both academia and industry since an accurate check-in predictive model is useful to many applications, e.g. urban planning, venue recommendation, route suggestion, and context-aware advertising. Intuitively, when considering venues to visit, users may rely on their past observed visit histories as well as some latent attributes associated with the venues. In this paper, we therefore propose a check-in prediction model based on a neural framework called Preference and Context Embeddings with Latent Attributes (PACELA). PACELA learns the embeddings space for the user and venue data as well …

Go to article

Online Deep Learning: Learning Deep Neural Networks On The Fly, Doyen Sahoo, Hong Quang Pham, Jing Lu, Steven C. H. Hoi Jul 2018

Online Deep Learning: Learning Deep Neural Networks On The Fly, Doyen Sahoo, Hong Quang Pham, Jing Lu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch setting, requiring the entire training data to be made available prior to the learning task. This is not scalable for many real-world scenarios where new data arrives sequentially in a stream. We aim to address an open challenge of “Online Deep Learning” (ODL) for learning DNNs on the fly in an online setting. Unlike traditional online learning that often optimizes some convex objective function with respect to a shallow model (e.g., a linear/kernel-based hypothesis), ODL is more challenging as the optimization objective is non-convex, and regular DNN with …

Go to article

Privacy-Preserving Mining Of Association Rule On Outsourced Cloud Data From Multiple Parties, Lin Liu, Jinshu Su, Rongmao Chen, Ximeng Liu, Xiaofeng Wang, Shuhui Chen, Ho-Fung Fung Leung Jul 2018

Privacy-Preserving Mining Of Association Rule On Outsourced Cloud Data From Multiple Parties, Lin Liu, Jinshu Su, Rongmao Chen, Ximeng Liu, Xiaofeng Wang, Shuhui Chen, Ho-Fung Fung Leung

Research Collection School Of Computing and Information Systems

It has been widely recognized as a challenge to carry out data analysis and meanwhile preserve its privacy in the cloud. In this work, we mainly focus on a well-known data analysis approach namely association rule mining. We found that the data privacy in this mining approach have not been well considered so far. To address this problem, we propose a scheme for privacy-preserving association rule mining on outsourced cloud data which are uploaded from multiple parties in a twin-cloud architecture. In particular, we mainly consider the scenario where the data owners and miners have different encryption keys that are …

Go to article

Efficient Representative Subset Selection Over Sliding Windows, Yanhao Wang, Yuchen Li, Kian-Lee Tan Jul 2018

Efficient Representative Subset Selection Over Sliding Windows, Yanhao Wang, Yuchen Li, Kian-Lee Tan

Research Collection School Of Computing and Information Systems

Representative subset selection (RSS) is an important tool for users to draw insights from massive datasets. Existing literature models RSS as submodular maximization to capture the "diminishing returns" property of representativeness, but often only has a single constraint, which limits its applications to many real-world problems. To capture the recency issue and support various constraints, we formulate dynamic RSS as maximizing submodular functions subject to general d -knapsack constraints (SMDK) over sliding windows. We propose a KnapWindow framework (KW) for SMDK. KW utilizes KnapStream (KS) for SMDK in append-only streams as a subroutine. It maintains a sequence of checkpoints and …

Go to article

Technology-Enabled Medication Adherence For Seniors Living In The Community: Experiences, Lessons, And The Road Ahead, Hwee Xian Tan, Hwee-Pink Tan, Huiguang Liang Jul 2018

Technology-Enabled Medication Adherence For Seniors Living In The Community: Experiences, Lessons, And The Road Ahead, Hwee Xian Tan, Hwee-Pink Tan, Huiguang Liang

Research Collection School Of Computing and Information Systems

Medication non-adherence in seniors can lead to severe health complications, including morbidity, mortality and decreased quality of life. In view of ageing populations worldwide, there is significant interest among the healthcare sector and researchers to improve medication adherence rates for seniors. However, existing studies in the literature focus primarily on identifying the predictors of medication non-adherence. In this paper, we present our work on technology-enabled medication adherence for 24 community-dwelling seniors over a period of more than 2 years. We leverage Internet of Things (IoT) devices to track inferred medication consumption in the seniors’ homes, and provide quasi real-time alerts …

Go to article

Distributed K-Nearest Neighbor Queries In Metric Spaces, Xin Ding, Yuanliang Zhang, Lu Chen, Yunjun Gao, Baihua Zheng Jul 2018

Distributed K-Nearest Neighbor Queries In Metric Spaces, Xin Ding, Yuanliang Zhang, Lu Chen, Yunjun Gao, Baihua Zheng

Research Collection School Of Computing and Information Systems

Metric k nearest neighbor (MkNN) queries have applications in many areas such as multimedia retrieval, computational biology, and location-based services. With the growing volumes of data, a distributed method is required. In this paper, we propose an Asynchronous Metric Distributed System (AMDS), which uniformly partitions the data with the pivot-mapping technique to ensure the load balancing, and employs publish/subscribe communication model to asynchronously process large scale of queries. The employment of asynchronous processing model also improves robustness and efficiency of AMDS. In addition, we develop an efficient estimation based MkNN method using AMDS to improve the query efficiency. Extensive experiments …

Go to article

Identifying Elderlies At Risk Of Becoming More Depressed With Internet-Of-Things, Jiajue Ou, Huiguang Liang, Hwee Xian Tan Jul 2018

Identifying Elderlies At Risk Of Becoming More Depressed With Internet-Of-Things, Jiajue Ou, Huiguang Liang, Hwee Xian Tan

Research Collection School Of Computing and Information Systems

Depression in the elderly is common and dangerous. Current methods to monitor elderly depression, however, are costly, time-consuming and inefficient. In this paper, we present a novel depression-monitoring system that infers an elderly’s changes in depression level based on his/her activity patterns, extracted from wireless sensor data. To do so, we build predictive models to learn the relationship between depression level changes and behaviors using historical data. We also deploy the system for a group of elderly, in their homes, and run the experiments for more than one year. Our experimental study gives encouraging results, suggesting that our IoT system …

Go to article

Unobtrusive Detection Of Frailty In Older Adults, Nadee Goonawardene, Hwee-Pink Tan, Lee Buay Tan Jul 2018

Unobtrusive Detection Of Frailty In Older Adults, Nadee Goonawardene, Hwee-Pink Tan, Lee Buay Tan

Research Collection School Of Computing and Information Systems

Sensor technologies have gained attention as an effective means to monitor physical and mental wellbeing of elderly. In this study, we examined the possibility of using passive in-home sensors to detect frailty in older adults based on their day-to-day in-home living pattern. The sensor-based elderly monitoring system consists of PIR motion sensors and a door contact sensor attached to the main door. A set of pre-defined features associated with elderly’s day-to-day living patterns were derived based on sensor data of 46 elderly gathered over two different time periods. A series of feature vectors depicting different behavioral aspects were derived to …

Go to article

Situation-Aware Authenticated Video Broadcasting Over Train-Trackside Wifi Networks, Yongdong Wu, Dengpan Ye, Zhuo Wei, Qian Wang, William Tan, Robert H. Deng Jul 2018

Situation-Aware Authenticated Video Broadcasting Over Train-Trackside Wifi Networks, Yongdong Wu, Dengpan Ye, Zhuo Wei, Qian Wang, William Tan, Robert H. Deng

Research Collection School Of Computing and Information Systems

Live video programmes can bring in better travel experience for subway passengers and earn abundant advertisement revenue for subway operators. However, because the train-trackside channels for video dissemination are easily accessible to anyone, the video traffic are vulnerable to attacks which may cause deadly tragedies. This paper presents a situation-aware authenticated video broadcasting scheme in the railway network which consists of train, on-board sensor, trackside GSM-R (Global System for Mobile Communications-Railway) device, WiFi AP (Access Point), and train control center. Specifically, the scheme has four modules: (1) a train uses its on-board sensors to obtain its speed, location, and RSSI …

Go to article

Deeptravel: A Neural Network Based Travel Time Estimation Model With Auxiliary Supervision, Hanyuan Zhang, Hao Wu, Weiwei Sun, Baihua Zheng Jul 2018

Deeptravel: A Neural Network Based Travel Time Estimation Model With Auxiliary Supervision, Hanyuan Zhang, Hao Wu, Weiwei Sun, Baihua Zheng

Research Collection School Of Computing and Information Systems

Estimating the travel time of a path is of great importance to smart urban mobility. Existing approaches are either based on estimating the time cost of each road segment or designed heuristically in a non-learning-based way. The former is not able to capture many cross-segment complex factors while the latter fails to utilize the existing abundant temporal labels of the data, i.e., the time stamp of each trajectory point. In this paper, we leverage on new development of deep neural networks and propose a novel auxiliary supervision model, namely DeepTravel, that can automatically and effectively extract different features, as well …

Go to article

Taxis Strike Back: A Field Trial Of The Driver Guidance System, Shih-Fen Cheng, Shashi Shekhar Jha, Rishikeshan Rajendram Jul 2018

Taxis Strike Back: A Field Trial Of The Driver Guidance System, Shih-Fen Cheng, Shashi Shekhar Jha, Rishikeshan Rajendram

Research Collection School Of Computing and Information Systems

Traditional taxi fleet operators world-over have been facing intense competitions from various ride-hailing services such as Uber and Grab (specific to the Southeast Asia region). Based on our studies on the taxi industry in Singapore, we see that the emergence of Uber and Grab in the ride-hailing market has greatly impacted the taxi industry: the average daily taxi ridership for the past two years has been falling continuously, by close to 20% in total. In this work, we discuss how efficient real-time data analytics and large-scale multi-agent optimization technology could potentially help taxi drivers compete against more technologically advanced service …

Go to article

A Driver Guidance System For Taxis In Singapore, Shashi Shekhar Jha, Shih-Fen Cheng, Meghna Lowalekar, Nicholas Wong, Rishikeshan Rajendram, Pradeep Varakantham, Nghia Troung Troung, Firmansyah Bin Abd Rahman Jul 2018

A Driver Guidance System For Taxis In Singapore, Shashi Shekhar Jha, Shih-Fen Cheng, Meghna Lowalekar, Nicholas Wong, Rishikeshan Rajendram, Pradeep Varakantham, Nghia Troung Troung, Firmansyah Bin Abd Rahman

Research Collection School Of Computing and Information Systems

Traditional taxi fleet operators world-over have been facing intense competitions from various ride-hailing services such as Uber and Grab.Based on our studies on the taxi industry in Singapore, we see that the emergence of Uber and Grab in the ride-hailing market has greatly impacted the taxi industry: the average daily taxi ridership for the past two years has been falling continuously, by close to 20% in total. In this work, we discuss how efficient real-time data analytics and large-scale multiagent optimization technology could help taxi drivers compete against more technologically advanced service platforms. Our system has been in field trial …

Go to article

Online Active Learning With Expert Advice, Shuji Hao, Peiying Hu, Peilin Zhao, Steven C. H. Hoi, Chunyan Miao Jul 2018

Online Active Learning With Expert Advice, Shuji Hao, Peiying Hu, Peilin Zhao, Steven C. H. Hoi, Chunyan Miao

Research Collection School Of Computing and Information Systems

In literature, learning with expert advice methods usually assume that a learner always obtain the true label of every incoming training instance at the end of each trial. However, in many real-world applications, acquiring the true labels of all instances can be both costly and time consuming, especially for large-scale problems. For example, in the social media, data stream usually comes in a high speed and volume, and it is nearly impossible and highly costly to label all of the instances. In this article, we address this problem with active learning with expert advice, where the ground truth of an …

Go to article

Adopt: Combining Parameter Tuning And Adaptive Operator Ordering For Solving A Class Of Orienteering Problems, Aldy Gunawan, Hoong Chuin Lau, Kun Lu Jul 2018

Adopt: Combining Parameter Tuning And Adaptive Operator Ordering For Solving A Class Of Orienteering Problems, Aldy Gunawan, Hoong Chuin Lau, Kun Lu

Research Collection School Of Computing and Information Systems

Two fundamental challenges in local search based metaheuristics are how to determine parameter configurations and design the underlying Local Search (LS) procedure. In this paper, we propose a framework in order to handle both challenges, called ADaptive OPeraTor Ordering (ADOPT). In this paper, The ADOPT framework is applied to two metaheuristics, namely Iterated Local Search (ILS) and a hybridization of Simulated Annealing and ILS (SAILS) for solving two variants of the Orienteering Problem: the Team Dependent Orienteering Problem (TDOP) and the Team Orienteering Problem with Time Windows (TOPTW). This framework consists of two main processes. The Design of Experiment (DOE) …

Go to article

Searching For The X-Factor: Exploring Corpus Subjectivity For Word Embeddings, Maksim Tkachenko, Chong Cher Chia, Hady W. Lauw Jul 2018

Searching For The X-Factor: Exploring Corpus Subjectivity For Word Embeddings, Maksim Tkachenko, Chong Cher Chia, Hady W. Lauw

Research Collection School Of Computing and Information Systems

We explore the notion of subjectivity, and hypothesize that word embeddings learnt from input corpora of varying levels of subjectivity behave differently on natural language processing tasks such as classifying a sentence by sentiment, subjectivity, or topic. Through systematic comparative analyses, we establish this to be the case indeed. Moreover, based on the discovery of the outsized role that sentiment words play on subjectivity-sensitive tasks such as sentiment classification, we develop a novel word embedding SentiVec which is infused with sentiment information from a lexical resource, and is shown to outperform baselines on such tasks.

Go to article

Disease Gene Classification With Metagraph Representations, Sezin Kircali Ata, Yuan Fang, Min Wu, Xiao-Li Li, Xiaokui Xiao Jul 2018

Disease Gene Classification With Metagraph Representations, Sezin Kircali Ata, Yuan Fang, Min Wu, Xiao-Li Li, Xiaokui Xiao

Research Collection School Of Computing and Information Systems

This chapter is based on exploiting the network-based representations of proteins, metagraphs, in protein-protein interaction network to identify candidate disease-causing proteins. Protein-protein interaction (PPI) networks are effective tools in studying the functional roles of proteins in the development of various diseases. However, they are insufficient without the support of additional biological knowledge for proteins such as their molecular functions and biological processes. To enhance PPI networks, we utilize biological properties of individual proteins as well. More specifically, we integrate keywords from UniProt database describing protein properties into the PPI network and construct a novel heterogeneous PPI-Keyword (PPIK) network consisting …

Go to article

A Bayesian Latent Variable Model Of User Preferences With Item Context, Aghiles Salah, Hady W. Lauw Jul 2018

A Bayesian Latent Variable Model Of User Preferences With Item Context, Aghiles Salah, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Personalized recommendation has proven to be very promising in modeling the preference of users over items. However, most existing work in this context focuses primarily on modeling user-item interactions, which tend to be very sparse. We propose to further leverage the item-item relationships that may reflect various aspects of items that guide users’ choices. Intuitively, items that occur within the same “context” (e.g., browsed in the same session, purchased in the same basket) are likely related in some latent aspect. Therefore, accounting for the item’s context would complement the sparse user-item interactions by extending a user’s preference to other items …

Go to article

Experiences & Challenges With Server-Side Wifi Indoor Localization Using Existing Infrastructure, Dheryta Jaisinghani, Rajesh Krishna Balan, Vinayak Naik, Archan Misra, Youngki Lee Jul 2018

Experiences & Challenges With Server-Side Wifi Indoor Localization Using Existing Infrastructure, Dheryta Jaisinghani, Rajesh Krishna Balan, Vinayak Naik, Archan Misra, Youngki Lee

Research Collection School Of Computing and Information Systems

Real-world deployments of WiFi-based indoor localization in large public venues are few and far between as most state-of-the-art solutions require either client or infrastructure-side changes. Hence, even though high location accuracy is possible with these solutions, they are not practical due to cost and/or client adoption reasons. Majority of the public venues use commercial controller-managed WLAN solutions, that neither allow client changes nor infrastructure changes. In fact, for such venues we have observed highly heterogeneous devices with very low adoption rates for client-side apps. In this paper, we present our experiences in deploying a scalable location system for such venues. …

Go to article

Deep Specification Mining, Tien-Duy B. Le, David Lo Jul 2018

Deep Specification Mining, Tien-Duy B. Le, David Lo

Research Collection School Of Computing and Information Systems

Formal specifications are essential but usually unavailable in software systems. Furthermore, writing these specifications is costly and requires skills from developers. Recently, many automated techniques have been proposed to mine specifications in various formats including finite-state automaton (FSA). However, more works in specification mining are needed to further improve the accuracy of the inferred specifications. In this work, we propose Deep Specification Miner (DSM), a new approach that performs deep learning for mining FSA-based specifications. Our proposed approach uses test case generation to generate a richer set of execution traces for training a Recurrent Neural Network Based Language Model (RNNLM). …

Go to article

Summarizing Source Code With Transferred Api Knowledge, Xing Hu, Ge Li, Xin Xia, David Lo, Shuai Lu, Zhi Jin Jul 2018

Summarizing Source Code With Transferred Api Knowledge, Xing Hu, Ge Li, Xin Xia, David Lo, Shuai Lu, Zhi Jin

Research Collection School Of Computing and Information Systems

Code summarization, aiming to generate succinct natural language description of source code, is extremely useful for code search and code comprehension. It has played an important role in software maintenance and evolution. Previous approaches generate summaries by retrieving summaries from similar code snippets. However, these approaches heavily rely on whether similar code snippets can be retrieved, how similar the snippets are, and fail to capture the API knowledge in the source code, which carries vital information about the functionality of the source code. In this paper, we propose a novel approach, named TL-CodeSum, which successfully uses API knowledge learned in …

Go to article

Characterizing Common And Domain-Specific Package Bugs: A Case Study On Ubuntu, Xiaoxue Ren, Qiao Huang, Xin Xia, Zhenchang Xing, Lingfeng Bao, David Lo Jul 2018

Characterizing Common And Domain-Specific Package Bugs: A Case Study On Ubuntu, Xiaoxue Ren, Qiao Huang, Xin Xia, Zhenchang Xing, Lingfeng Bao, David Lo

Research Collection School Of Computing and Information Systems

Ubuntu is an open source software platform that runs everywhere from the smartphone, the tablet and the PC to the server and the cloud. In Ubuntu, there are many self-contained or third-party software packages for different use, and a bug report in Ubuntu could affect one or more packages simultaneously. Identifying the common package bugs in Ubuntu can help both developers and users better understand the packages they are developing or using, and also provide further guidelines to developers of similar packages in the future. In this paper, we perform a large-scale empirical study of common package bugs on Ubuntu …

Go to article

Striving To Earn More: A Survey Of Work Strategies And Tool Use Among Crowd Workers, Toni Kaplan, Susumu Saito, Kotaro Hara, Jeffrey P. Bigham Jul 2018

Striving To Earn More: A Survey Of Work Strategies And Tool Use Among Crowd Workers, Toni Kaplan, Susumu Saito, Kotaro Hara, Jeffrey P. Bigham

Research Collection School Of Computing and Information Systems

Earning money is a primary motivation for workers on Amazon Mechanical Turk, but earning a good wage is difficult because work that pays well is not easily identified and can be time-consuming to find. We explored the strategies that both low- and high-earning workers use to find and complete tasks via a survey of 360 workers. Nearly all workers surveyed had earning money as their primary goal, and workers used many of the same tools (browser extensions and scripts) and strategies in an attempt to earn more money, regardless of earning level. However, high-earning workers used more tools, were more …

Go to article

Detecting Personal Intake Of Medicine From Twitter, Debanjan Mahata, Jasper Friedrichs, Rajiv Ratn Shah, Jing Jiang Jul 2018

Detecting Personal Intake Of Medicine From Twitter, Debanjan Mahata, Jasper Friedrichs, Rajiv Ratn Shah, Jing Jiang

Research Collection School Of Computing and Information Systems

Mining social media messages such as tweets, blogs, and Facebook posts for health and drug related information has received significant interest in pharmacovigilance research. Social media sites (e.g., Twitter), have been used for monitoring drug abuse, adverse reactions to drug usage, and analyzing expression of sentiments related to drugs. Most of these studies are based on aggregated results from a large population rather than specific sets of individuals. In order to conduct studies at an individual level or specific groups of people, identifying posts mentioning intake of medicine by the user is necessary. Toward this objective we develop a classifier …

Go to article

Probabilistic Guided Exploration For Reinforcement Learning In Self-Organizing Neural Networks, Peng Wang, Weigui Jair Zhou, Di Wang, Ah-Hwee Tan Jul 2018

Probabilistic Guided Exploration For Reinforcement Learning In Self-Organizing Neural Networks, Peng Wang, Weigui Jair Zhou, Di Wang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Exploration is essential in reinforcement learning, which expands the search space of potential solutions to a given problem for performance evaluations. Specifically, carefully designed exploration strategy may help the agent learn faster by taking the advantage of what it has learned previously. However, many reinforcement learning mechanisms still adopt simple exploration strategies, which select actions in a pure random manner among all the feasible actions. In this paper, we propose novel mechanisms to improve the existing knowledgebased exploration strategy based on a probabilistic guided approach to select actions. We conduct extensive experiments in a Minefield navigation simulator and the results …

Go to article

A Survey On Sensor Calibration In Air Pollution Monitoring Deployments, Balz Maah, Zimu Zhou, Lothar Thiele Jul 2018

A Survey On Sensor Calibration In Air Pollution Monitoring Deployments, Balz Maah, Zimu Zhou, Lothar Thiele

Research Collection School Of Computing and Information Systems

Air pollution is a major concern for public health and urban environments. Conventional air pollution monitoring systems install a few highly accurate, expensive stations at representative locations. Their sparse coverage and low spatial resolution are insufficient to quantify urban air pollution and its impacts on human health and environment. Advances in lowcost portable air pollution sensors have enabled air pollution monitoring deployments at scale to measure air pollution at high spatiotemporal resolution. However, it is challenging to ensure the accuracy of these low-cost sensor deployments because the sensors are more error-prone than high-end sensing infrastructures and they are often deployed …

Go to article

Rumor Detection On Twitter With Tree-Structured Recursive Neural Networks, Jing Ma, Wei Gao, Kam-Fai Wong Jul 2018

Rumor Detection On Twitter With Tree-Structured Recursive Neural Networks, Jing Ma, Wei Gao, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Sentiment expression in microblog posts can be affected by user’s personal character, opinion bias, political stance and so on. Most of existing personalized microblog sentiment classification methods suffer from the insufficiency of discriminative tweets for personalization learning. We observed that microblog users have consistent individuality and opinion bias in different languages. Based on this observation, in this paper we propose a novel user-attention-based Convolutional Neural Network (CNN) model with adversarial cross-lingual learning framework. The user attention mechanism is leveraged in CNN model to capture user’s language-specific individuality from the posts. Then the attention-based CNN model is incorporated into a novel …

Go to article

Understanding Generalization And Optimization Performance Of Deep Cnns, Pan Zhou, Jiashi Feng Jul 2018

Understanding Generalization And Optimization Performance Of Deep Cnns, Pan Zhou, Jiashi Feng

Research Collection School Of Computing and Information Systems

This work aims to provide understandings on the remarkable success of deep convolutional neural networks (CNNs) by theoretically analyzing their generalization performance and establishing optimization guarantees for gradient descent based training algorithms. Specifically, for a CNN model consisting of l convolutional layers and one fully connected layer, we prove that its generalization error is bounded by O( p θ%/n e ) where θ denotes freedom degree of the network parameters and %e = O(log(Ql i=1 bi(ki − si + 1)/p) + log(bl+1)) encapsulates architecture parameters including the kernel size ki , stride si , pooling size p and parameter magnitude …

Go to article

Knowledge-Aware Attentive Neural Network For Ranking Question Answer Pairs, Ying Shen, Yang Deng, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei Jul 2018

Knowledge-Aware Attentive Neural Network For Ranking Question Answer Pairs, Ying Shen, Yang Deng, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei

Research Collection School Of Computing and Information Systems

Ranking question answer pairs has attracted increasing attention recently due to its broad applications such as information retrieval and question answering (QA). Significant progresses have been made by deep neural networks. However, background information and hidden relations beyond the context, which play crucial roles in human text comprehension, have received little attention in recent deep neural networks that achieve the state of the art in ranking QA pairs. In the paper, we propose KABLSTM, a Knowledge-aware Attentive Bidirectional Long Short-Term Memory, which leverages external knowledge from knowledge graphs (KG) to enrich the representational learning of QA sentences. Specifically, we develop …

Go to article

First Prev Next Last