Computer Sciences Commons^™

Marina: Faster Non-Convex Distributed Learning With Compression, Eduard Gorbunov, Konstantin Burlachenko, Zhize Li, Peter Richtarik

Research Collection School Of Computing and Information Systems

We develop and analyze MARINA: a new communication efficient method for non-convex distributed learning over heterogeneous datasets. MARINA employs a novel communication compression strategy based on the compression of gradient differences that is reminiscent of but different from the strategy employed in the DIANA method of Mishchenko et al. (2019). Unlike virtually all competing distributed first-order methods, including DIANA, ours is based on a carefully designed biased gradient estimator, which is the key to its superior theoretical and practical performance. The communication complexity bounds we prove for MARINA are evidently better than those of all previous first-order methods. Further, we …

Privacy-Preserving Cloud-Assisted Data Analytics, Wei Bao

Graduate Theses and Dissertations

Nowadays industries are collecting a massive and exponentially growing amount of data that can be utilized to extract useful insights for improving various aspects of our life. Data analytics (e.g., via the use of machine learning) has been extensively applied to make important decisions in various real world applications. However, it is challenging for resource-limited clients to analyze their data in an efficient way when its scale is large. Additionally, the data resources are increasingly distributed among different owners. Nonetheless, users' data may contain private information that needs to be protected.

Cloud computing has become more and more popular in …

Signal Processing And Data Analysis For Real-Time Intermodal Freight Classification Through A Multimodal Sensor System., Enrique J. Sanchez Headley

Graduate Theses and Dissertations

Identifying freight patterns in transit is a common need among commercial and municipal entities. For example, the allocation of resources among Departments of Transportation is often predicated on an understanding of freight patterns along major highways. There exist multiple sensor systems to detect and count vehicles at areas of interest. Many of these sensors are limited in their ability to detect more specific features of vehicles in traffic or are unable to perform well in adverse weather conditions. Despite this limitation, to date there is little comparative analysis among Laser Imaging and Detection and Ranging (LIDAR) sensors for freight detection …

Users’ Reception Of Product Recommendations: Analyses Based On Eye Tracking Data, Feiyan Jia, Yani Shi, Choon Ling Sia, Chuan-Hoo Tan, Fiona Fui-Hoon Nah, Keng Siau

Research Collection School Of Computing and Information Systems

Based on eye tracking technology, we study consumers’ overall attention to recommendations appearing at different time settings (i.e., early, mid, and late) and their attention to different information contained in each recommendation, such as recommendation signs, product descriptions, and reviews. By investigating consumers’ eye movement patterns and attention distributions on recommendations, we open the “black box” of why consumers’ reception to recommendations appearing at different time settings varies. The product preference construction literature and mindset theory help to explain why the early recommendations receive the most attention. The need for justification helps to explain why the late recommendations should receive …

Addressing The ‘Unseens’: Digital Wellbeing In The Remote Workplace, Holtjona Galanxhi, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

The ubiquity of sophisticated devices, along with uninterrupted access to the Internet and organizational computerized systems, allows for the “anyplace” workplace to be established. Technology has the potential to deliberately or inadvertently impact psychological wellbeing. Specific psychological demands are inadvertently imposed on remote employees whose permanent online presence is required. Hence, it is important to understand factors affecting digital wellbeing and steps that can be taken to maximize the wellbeing of remote employees. This paper provides suggestions for future research on studying the digital wellbeing of (fully or partially) remote employees. A research framework is proposed to demonstrate the different …

Design And Development Of Techniques To Ensure Integrity In Fog Computing Based Databases, Abdulwahab Fahad S. Alazeb

Graduate Theses and Dissertations

The advancement of information technology in coming years will bring significant changes to the way sensitive data is processed. But the volume of generated data is rapidly growing worldwide. Technologies such as cloud computing, fog computing, and the Internet of things (IoT) will offer business service providers and consumers opportunities to obtain effective and efficient services as well as enhance their experiences and services; increased availability and higher-quality services via real-time data processing augment the potential for technology to add value to everyday experiences. This improves human life quality and easiness. As promising as these technological innovations, they are prone …

An Automated Method To Enrich And Expand Consumer Health Vocabularies Using Glove Word Embeddings, Mohammed Ibrahim

Graduate Theses and Dissertations

Clear language makes communication easier between any two parties. However, a layman may have difficulty communicating with a professional due to not understanding the specialized terms common to the domain. In healthcare, it is rare to find a layman knowledgeable in medical jargon, which can lead to poor understanding of their condition and/or treatment. To bridge this gap, several professional vocabularies and ontologies have been created to map laymen medical terms to professional medical terms and vice versa. Many of the presented vocabularies are built manually or semi-automatically requiring large investments of time and human effort and consequently the slow …

Promoting Diversity In Academic Research Communities Through Multivariate Expert Recommendation, Omar Salman

Graduate Theses and Dissertations

Expert recommendation is the process of identifying individuals who have the appropriate knowledge and skills to achieve a specific task. It has been widely used in the educational environment mainly in the hiring process, paper-reviewer assignment, and assembling conference program committees. In this research, we highlight the problem of diversity and fair representation of underrepresented groups in expertise recommendation, factors that current expertise recommendation systems rarely consider. We introduce a novel way to model experts in academia by considering demographic attributes in addition to skills. We use the h-index score to quantify skills for a researcher and we identify five …

A Machine Learning Approach To Understanding Emerging Markets, Namita Balani

Graduate Theses and Dissertations

Logistic providers have learned to efficiently serve their existing customer bases with optimized routes and transportation resource allocation. The problem arises when there is potential for logistics growth in an emerging market with no previous data. The purpose of this work is to use industry data for previously known and well-documented markets to apply data analytic techniques such as machine learning to investigate the uncertainty in a new market. The thesis looks into machine learning techniques to predict miles per stop given historical data. It mainly focuses on Random Forest Regression Analysis, but concludes that additional techniques, such as Polynomial …

Designing A Health Coach-Augmented Mhealth System For The Secondary Prevention Of Coronary Heart Disease, Avijit Sengupta

USF Tampa Graduate Theses and Dissertations

This dissertation presents research that employs design science research (DSR) methodology to develop and evaluate a high-fidelity prototype of a home-based cardiac rehabilitation (HBCR) system to support self-management of chronic cardiovascular diseases like coronary heart disease (CHD) and to offer secondary prevention against other chronic diseases with similar risk factors. While the population of coronary heart disease (CHD) patients requiring cardiac rehabilitation (CR) continues to expand, lack of access and other barriers to center based cardiac rehabilitation (CBCR) presents a huge challenge. A mobile phone and wearable device based technological system can offer an HBCR program for CHD. By following …

Designing Targeted Mobile Advertising Campaigns, Kimia Keshanian

USF Tampa Graduate Theses and Dissertations

With the proliferation of smart, handheld devices, there has been a multifold increase in the ability of firms to target and engage with customers through mobile advertising. Therefore, not surprisingly, mobile advertising campaigns have become an integral aspect of firms’ brand building activities, such as improving the awareness and overall visibility of firms' brands. In addition, retailers are increasingly using mobile advertising for targeted promotional activities that increase in-store visits and eventual sales conversions. However, in recent years, mobile or in general online advertising campaigns have been facing one major challenge and one major threat that can negatively impact the …

Counting And Sampling Small Structures In Graph And Hypergraph Data Streams, Themistoklis Haris

Dartmouth College Undergraduate Theses

In this thesis, we explore the problem of approximating the number of elementary substructures called simplices in large k-uniform hypergraphs. The hypergraphs are assumed to be too large to be stored in memory, so we adopt a data stream model, where the hypergraph is defined by a sequence of hyperedges.

First we propose an algorithm that (ε, δ)-estimates the number of simplices using O(m^1+1/k / T) bits of space. In addition, we prove that no constant-pass streaming algorithm can (ε, δ)- approximate the number of simplices using less than O( m ^1+1/k / T ) bits of space. Thus …

A Configurable Social Network For Running Irb-Approved Experiments, Mihovil Mandic

Dartmouth College Undergraduate Theses

Our world has never been more connected, and the size of the social media landscape draws a great deal of attention from academia. However, social networks are also a growing challenge for the Institutional Review Boards concerned with the subjects’ privacy. These networks contain a monumental variety of personal information of almost 4 billion people, allow for precise social profiling, and serve as a primary news source for many users. They are perfect environments for influence operations that are becoming difficult to defend against. Motivated to study online social influence via IRB-approved experiments, we designed and implemented a flexible, scalable, …

Minimizing The Regret Of An Influence Provider, Yipeng Zhang, Yuchen Li, Zhifeng Bao, Baihua Zheng

Research Collection School Of Computing and Information Systems

Influence maximization has been studied extensively from the perspective of the influencer. However, the influencer typically purchases influence from a provider, for example in the form of purchased advertising. In this paper, we study the problem from the perspective of the influence provider. Specifically, we focus on influence providers who sell Out-of-Home (OOH) advertising on billboards. Given a set of requests from influencers, how should an influence provider allocate resources to minimize regret, whether due to forgone revenue from influencers whose needs were not met or due to over-provisioning of resources to meet the needs of influencers? We formalize this …

Multi-View Collaborative Network Embedding, Sezin Kircali Ata, Yuan Fang, Min Wu, Jiaqi Shi, Chee Keong Kwoh, Xiaoli Li

Research Collection School Of Computing and Information Systems

Real-world networks often exist with multiple views, where each view describes one type of interaction among a common set of nodes. For example, on a video-sharing network, while two user nodes are linked, if they have common favorite videos in one view, then they can also be linked in another view if they share common subscribers. Unlike traditional single-view networks, multiple views maintain different semantics to complement each other. In this article, we propose Multi-view collAborative Network Embedding (MANE), a multi-view network embedding approach to learn low-dimensional representations. Similar to existing studies, MANE hinges on diversity and collaboration—while diversity enables …

Catch You With Cache: Out-Of-Vm Introspection To Trace Malicious Executions, Chao Su, Xuhua Ding, Qinghai Zeng

Research Collection School Of Computing and Information Systems

Out-of-VM introspection is an imperative part of security analysis. The legacy methods either modify the system, introducing enormous overhead, or rely heavily on hardware features, which are neither available nor practical in most cloud environments. In this paper, we propose a novel analysis method, named as Catcher, that utilizes CPU cache to perform out-of-VM introspection. Catcher does not make any modifications to the target program and its running environment, nor demands special hardware support. Implemented upon Linux KVM, it natively introspects the target's virtual memory. More importantly, it uses the cache-based side channel to infer the target control flow. To …

Iquant: Interactive Quantitative Investment Using Sparse Regression Factors, Xuanwu Yue, Qiao Gu, Deyun Wang, Huamin Qu, Yong Wang

Research Collection School Of Computing and Information Systems

The model-based investing using financial factors is evolving as a principal method for quantitative investment. The main challenge lies in the selection of effective factors towards excess market returns. Existing approaches, either hand-picking factors or applying feature selection algorithms, do not orchestrate both human knowledge and computational power. This paper presents iQUANT, an interactive quantitative investment system that assists equity traders to quickly spot promising financial factors from initial recommendations suggested by algorithmic models, and conduct a joint refinement of factors and stocks for investment portfolio composition. We work closely with professional traders to assemble empirical characteristics of “good” factors …

Knowledge And Anxiety About Covid-19 In The State Of Qatar, And The Middle East And North Africa Region—A Cross Sectional Study, Sathyanarayanan Doraiswamy, Sohaila Cheema, Maisonneuve Patrick, Amit Abraham, Ingmar Weber, Jisun An, Albert B. Lowenfels, Ravinder Mamtani

Research Collection School Of Computing and Information Systems

While the coronavirus disease 2019 (COVID-19) pandemic wreaked havoc across the globe, we have witnessed substantial mis- and disinformation regarding various aspects of the disease. We conducted a cross-sectional study using a self-administered questionnaire for the general public (recruited via social media) and healthcare workers (recruited via email) from the State of Qatar, and the Middle East and North Africa region to understand the knowledge of and anxiety levels around COVID-19 (April–June 2020) during the early stage of the pandemic. The final dataset used for the analysis comprised of 1658 questionnaires (53.0% of 3129 received questionnaires; 1337 [80.6%] from the …

Boosting Video Representation Learning With Multi-Faceted Integration, Zhaofan Qiu, Yao Ting, Chong-Wah Ngo, Xiao-Ping Zhang, Dong Wu, Tao Mei

Research Collection School Of Computing and Information Systems

Video content is multifaceted, consisting of objects, scenes, interactions or actions. The existing datasets mostly label only one of the facets for model training, resulting in the video representation that biases to only one facet depending on the training dataset. There is no study yet on how to learn a video representation from multifaceted labels, and whether multifaceted information is helpful for video representation learning. In this paper, we propose a new learning framework, MUlti-Faceted Integration (MUFI), to aggregate facets from different datasets for learning a representation that could reflect the full spectrum of video content. Technically, MUFI formulates the …

An Economic Analysis Of Rebates Conditional On Positive Reviews, Jianqing Chen, Zhiling Guo, Jian Huang

Research Collection School Of Computing and Information Systems

Strategic sellers on some online selling platforms have recently been using a conditional-rebate strategy to manipulate product reviews under which only purchasing consumers who post positive reviews online are eligible to redeem the rebate. A key concern for the conditional rebate is that it can easily induce fake reviews, which might be harmful to consumers and society. We develop a microbehavioral model capturing consumers’ review-sharing benefit, review-posting cost, and moral cost of lying to examine the seller’s optimal pricing and rebate decisions. We derive three equilibria: the no-rebate, organic-review equilibrium; the low-rebate, boosted-authentic-review equilibrium; and the high-rebate, partially-fake-review equilibrium. We …

Riding Through The Silver Tsunami: A Data Driven Approach To Improve Senior Citizens’ Engagement With Community Senior Activity Centres, Joshua Jie Feng Lam, Hwee-Pink Tan

Research Collection School Of Computing and Information Systems

In Singapore, 1 in 4 persons will be elderly by 2030 In preparation for the Silver Tsunami, the Singapore government and community care providers have collaborations to promote active, independent living amongst elders Current implementation of data driven population health is focused on well being indices using data collected from the general population There is no literature on the use of data analytics in assessing elder

Hierarchical Reinforcement Learning: A Comprehensive Survey, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan, Chai Quek

Research Collection School Of Computing and Information Systems

Hierarchical Reinforcement Learning (HRL) enables autonomous decomposition of challenging long-horizon decision-making tasks into simpler subtasks. During the past years, the landscape of HRL research has grown profoundly, resulting in copious approaches. A comprehensive overview of this vast landscape is necessary to study HRL in an organized manner. We provide a survey of the diverse HRL approaches concerning the challenges of learning hierarchical policies, subtask discovery, transfer learning, and multi-agent learning using HRL. The survey is presented according to a novel taxonomy of the approaches. Based on the survey, a set of important open problems is proposed to motivate the future …

On Predicting Personal Values Of Social Media Users Using Community-Specific Language Features And Personal Value Correlation, Amila Silva, Pei Chi Lo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Personal values have significant influence on individuals’ behaviors, preferences, and decision making. It is therefore not a surprise that personal values of a person could influence his or her social media content and activities. Instead of getting users to complete personal value questionnaire, researchers have looked into a non-intrusive and highly scalable approach to predict personal values using user-generated social media data. Nevertheless, geographical differences in word usage and profile information are issues to be addressed when designing such prediction models. In this work, we focus on analyzing Singapore users’ personal values, and developing effective models to predict their personal …

How-To Present News On Social Media: A Causal Analysis Of Editing News Headlines For Boosting User Engagement, Kunwoo Park, Haewoon Kwak, Jisun An, Sanjay Chawla

Research Collection School Of Computing and Information Systems

To reach a broader audience and optimize traffic toward news articles, media outlets commonly run social media accounts and share their content with a short text summary. Despite its importance of writing a compelling message in sharing articles, the research community does not own a sufficient understanding of what kinds of editing strategies effectively promote audience engagement. In this study, we aim to fill the gap by analyzing media outlets' current practices using a data-driven approach. We first build a parallel corpus of original news articles and their corresponding tweets that eight media outlets shared. Then, we explore how those …

Gpu-Accelerated Graph Label Propagation For Real-Time Fraud Detection, Chang Ye, Yuchen Li, Bingsheng He, Zhao Li, Jianling Sun

Research Collection School Of Computing and Information Systems

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 …

Cache-Efficient Fork-Processing Patterns On Large Graphs, Shengliang Lu, Shixuan Sun, Johns Paul, Yuchen Li, Bingsheng He

Research Collection School Of Computing and Information Systems

As large graph processing emerges, we observe a costly fork-processing pattern (FPP) that is common in many graph algorithms. The unique feature of the FPP is that it launches many independent queries from different source vertices on the same graph. For example, an algorithm in analyzing the network community profile can execute Personalized PageRanks that start from tens of thousands of source vertices at the same time. We study the efficiency of handling FPPs in state-of-the-art graph processing systems on multi-core architectures, including Ligra, Gemini, and GraphIt. We find that those systems suffer from severe cache miss penalty because of …

Self-Adaptive Graph Traversal On Gpus, Mo Sha, Yuchen Li, Kian-Lee Tan

Research Collection School Of Computing and Information Systems

GPU’s massive computing power offers unprecedented opportunities to enable large graph analysis. Existing studies proposed various preprocessing approaches that convert the input graphs into dedicated structures for GPU-based optimizations. However, these dedicated approaches incur significant preprocessing costs as well as weak programmability to build general graph applications. In this paper, we introduce SAGE, a self-adaptive graph traversal on GPUs, which is free from preprocessing and operates on ubiquitous graph representations directly. We propose Tiled Partitioning and Resident Tile Stealing to fully exploit the computing power of GPUs in a runtime and self-adaptive manner. We also propose Sampling-based Reordering to further …

Minimum Coresets For Maxima Representation Of Multidimensional Data, Yanhao Wang, Michael Mathioudakis, Yuchen Li, Kian-Lee Tan

Research Collection School Of Computing and Information Systems

Coresets are succinct summaries of large datasets such that, for a given problem, the solution obtained from a coreset is provably competitive with the solution obtained from the full dataset. As such, coreset-based data summarization techniques have been successfully applied to various problems, e.g., geometric optimization, clustering, and approximate query processing, for scaling them up to massive data. In this paper, we study coresets for the maxima representation of multidimensional data: Given a set �� of points in R �� , where �� is a small constant, and an error parameter �� ∈ (0, 1), a subset �� ⊆ �� …

On M-Impact Regions And Standing Top-K Influence Problems, Bo Tang, Kyriakos Mouratidis, Mingji Han

Research Collection School Of Computing and Information Systems

In this paper, we study the ��-impact region problem (mIR). In a context where users look for available products with top-�� queries, mIR identifies the part of the product space that attracts the most user attention. Specifically, mIR determines the kind of attribute values that lead a (new or existing) product to the top-�� result for at least a fraction of the user population. mIR has several applications, ranging from effective marketing to product improvement. Importantly, it also leads to (exact and efficient) solutions for standing top-�� impact problems, which were previously solved heuristically only, or whose current solutions face …

Marrying Top-K With Skyline Queries: Relaxing The Preference Input While Producing Output Of Controllable Size, Kyriakos Mouratidis, Keming Li, Bo Tang

Research Collection School Of Computing and Information Systems

The two most common paradigms to identify records of preference in a multi-objective setting rely either on dominance (e.g., the skyline operator) or on a utility function defined over the records’ attributes (typically, using a top-�� query). Despite their proliferation, each of them has its own palpable drawbacks. Motivated by these drawbacks, we identify three hard requirements for practical decision support, namely, personalization, controllable output size, and flexibility in preference specification. With these requirements as a guide, we combine elements from both paradigms and propose two new operators, ORD and ORU. We perform a qualitative study to demonstrate how they …