Meta-Learning On Heterogeneous Information Networks For Cold-Start Recommendation,
2020
Singapore Management University
Meta-Learning On Heterogeneous Information Networks For Cold-Start Recommendation, Yuanfu Lu, Yuan Fang, Chuan Shi
Research Collection School Of Computing and Information Systems
Cold-start recommendation has been a challenging problem due to sparse user-item interactions for new users or items. Existing efforts have alleviated the cold-start issue to some extent, most of which approach the problem at the data level. Earlier methods often incorporate auxiliary data as user or item features, while more recent methods leverage heterogeneous information networks (HIN) to capture richer semantics via higher-order graph structures. On the other hand, recent meta-learning paradigm sheds light on addressing cold-start recommendation at the model level, given its ability to rapidly adapt to new tasks with scarce labeled data, or in the context of …
Aim 2020 Challenge On Video Extreme Super-Resolution: Methods And Results,
2020
Singapore Management University
Aim 2020 Challenge On Video Extreme Super-Resolution: Methods And Results, D. Fuoli, Zhiwu Huang, S. Gu, R. Timofte, A. Raventos, A. Esfandiari, S. Karout, X. Xu, X. Li, X. Xiong, J. Wang, Michelini P. Navarrete, W. Zhang, D. Zhang, H. Zhu, D. Xia, H. Chen, J. Gu, Z. Zhang, T. Zhao
Research Collection School Of Computing and Information Systems
This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020. Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details. The task in this challenge is to upscale videos with an extreme factor of 16, which results in more serious degradations that also affect the structural integrity of the videos. A single pixel in the lowresolution (LR) domain corresponds to 256 pixels in the high-resolution (HR) domain. …
A Fast Anderson-Chebyshev Acceleration For Nonlinear Optimization,
2020
Singapore Management University
A Fast Anderson-Chebyshev Acceleration For Nonlinear Optimization, Zhize Li, Jian Li
Research Collection School Of Computing and Information Systems
Anderson acceleration (or Anderson mixing) is an efficient acceleration method for fixed point iterations $x_{t+1}=G(x_t)$, e.g., gradient descent can be viewed as iteratively applying the operation $G(x) \triangleq x-\alpha\nabla f(x)$. It is known that Anderson acceleration is quite efficient in practice and can be viewed as an extension of Krylov subspace methods for nonlinear problems. In this paper, we show that Anderson acceleration with Chebyshev polynomial can achieve the optimal convergence rate $O(\sqrt{\kappa}\ln\frac{1}{\epsilon})$, which improves the previous result $O(\kappa\ln\frac{1}{\epsilon})$ provided by (Toth and Kelley, 2015) for quadratic functions. Moreover, we provide a convergence analysis for minimizing general nonlinear problems. Besides, …
Measuring Privacy Concerns With Government Surveillance And Right-To-Be-Forgotten In Nomological Net Of Trust And Willingness-To-Share,
2020
Singapore Management University
Measuring Privacy Concerns With Government Surveillance And Right-To-Be-Forgotten In Nomological Net Of Trust And Willingness-To-Share, Gaurav Bansal, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
In the post Snowden revelations era, concerns related to government surveillance and oversight have come to the forefront. The ability of the Internet to remember “everything” (or forget anything) also raises a privacy concern associated with the “right to be forgotten”. Hence, in this paper, we propose and examine privacy concerns by extending the Hong and Thong’s (2013) model with the addition of two dimensions: right to be forgotten as well as government surveillance and oversight. We tested two different measurement models using privacy concerns as a second-order and a third-order construct within a nomological net that includes trusting beliefs …
Interface Design Of Web-Based Educational Platforms For Young Students,
2020
Singapore Management University
Interface Design Of Web-Based Educational Platforms For Young Students, Lurong He, Fiona Fui-Hoon Nah
Research Collection School Of Computing and Information Systems
With the outbreak of the Covid-19 pandemic, almost all the school programs in the United States are closed. Most educational programs have moved online. Both teachers and students are facing challenges adapting to this new teaching and learning mode. This paper will focus on the interface design of webbased educational platforms for students and teachers from elementary and middle schools. The age of students from elementary and middle schools typically ranges from 5 to 13 years old. Their computer literacy level is still preliminary. So traditional online teaching platforms may not be appropriate for them. The design of learning systems …
Social Participation Performance Of Wheelchair Users Using Clustering And Geolocational Sensor's Data,
2020
Singapore Management University
Social Participation Performance Of Wheelchair Users Using Clustering And Geolocational Sensor's Data, Yukun Yin, Kar Way Tan
Research Collection School Of Computing and Information Systems
For wheelchair users, social participation and physical mobility play a significant part in determining their mental health and quality of life outcomes. However, little is known about how wheelchair users move about and engage in social interactions within their life-spaces. In this project, we investigate the social participation performance of the wheelchair users based on a combination of geolocational and lifestyle survey data collected over a period of three months. This paper adopts a multi-variate approach combining geolocational travel patterns and various factors such as independence, willingness and self-perception to provide multi-faceted analysis to their lifestyles. We provide profiles of …
Feature Pyramid Transformer,
2020
Nanjing University of Science and Technology
Feature Pyramid Transformer, Dong Zhang, Hanwang Zhang, Jinhui Tang, Meng Wang, Xian-Sheng Hua, Qianru Sun
Research Collection School Of Computing and Information Systems
Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN’s increasing receptive fields or actively encoded by non-local convolution. Yet, the non-local spatial interactions are not across scales, and thus they fail to capture the non-local contexts of objects (or parts) residing in different scales. To this end, we propose a fully active feature interaction across both space and scales, called Feature Pyramid Transformer (FPT). It transforms any feature pyramid into another feature pyramid of the same size but with richer contexts, by using …
An Ensemble Of Epoch-Wise Empirical Bayes For Few-Shot Learning,
2020
Max Planck Institute for Informatics
An Ensemble Of Epoch-Wise Empirical Bayes For Few-Shot Learning, Yaoyao Liu, Bernt Schiele, Qianru Sun
Research Collection School Of Computing and Information Systems
Few-shot learning aims to train efficient predictive models with a few examples. The lack of training data leads to poor models that perform high-variance or low-confidence predictions. In this paper, we propose to meta-learn the ensemble of epoch-wise empirical Bayes models (E3BM) to achieve robust predictions. “Epoch-wise'' means that each training epoch has a Bayes model whose parameters are specifically learned and deployed. ”Empirical'' means that the hyperparameters, e.g., used for learning and ensembling the epoch-wise models, are generated by hyperprior learners conditional on task-specific data. We introduce four kinds of hyperprior learners by considering inductive vs. transductive, and epoch-dependent …
Learning Transferrable Parameters For Long-Tailed Sequential User Behavior Modeling,
2020
Zhejiang University
Learning Transferrable Parameters For Long-Tailed Sequential User Behavior Modeling, Jianwen Yin, Chenghao Liu, Weiqing Wang, Jianling Sun, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
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 …
A Unified Framework For Sparse Online Learning,
2020
Tencent AL Lab
A Unified Framework For Sparse Online Learning, Peilin Zhao, Dayong Wong, Pengcheng Wu, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
The amount of data in our society has been exploding in the era of big data. This article aims to address several open challenges in big data stream classification. Many existing studies in data mining literature follow the batch learning setting, which suffers from low efficiency and poor scalability. To tackle these challenges, we investigate a unified online learning framework for the big data stream classification task. Different from the existing online data stream classification techniques, we propose a unified Sparse Online Classification (SOC) framework. Based on SOC, we derive a second-order online learning algorithm and a cost-sensitive sparse online …
Accelerating Exact Constrained Shortest Paths On Gpus,
2020
National University of Singapore
Accelerating Exact Constrained Shortest Paths On Gpus, Shengliang Lu, Bingsheng He, Yuchen Li, Hao Fu
Research Collection School Of Computing and Information Systems
The recently emerging applications such as software-defined networks and autonomous vehicles require efficient and exact solutions for constrained shortest paths (CSP), which finds the shortest path in a graph while satisfying some user-defined constraints. Compared with the common shortest path problems without constraints, CSP queries have a significantly larger number of subproblems. The most widely used labeling algorithm becomes prohibitively slow and impractical. Other existing approaches tend to find approximate solutions and build costly indices on graphs for fast query processing, which are not suitable for emerging applications with the requirement of exact solutions. A natural question is whether and …
Impact Of Socioeconomic Status On Trust In Artificial Intelligence,
2020
Singapore Management University
Impact Of Socioeconomic Status On Trust In Artificial Intelligence, Linrui Han, Keng Siau
Research Collection School Of Computing and Information Systems
Artificial intelligence (AI) will have a major impact on both our daily lifestyle and the job market. Although AI can bring a lot of benefits, people are still concerned with the development of AI in many aspects. To better utilize technology, the first thing is to trust the technology (Siau & Shen, 2003; Siau & Wang, 2018). Trust will also influence the use and acceptance of technologies such as mobile technologies and AI (Siau & Shen, 2006; Stephanidis et al. 2019). If people do not trust AI, they cannot capitalize on the advantages of AI to create more benefits (Wang …
Covid-19 Pandemic Management And Control: Effects Of Information And Communication Technologies,
2020
Singapore Management University
Covid-19 Pandemic Management And Control: Effects Of Information And Communication Technologies, Keng Siau, Linrui Han
Research Collection School Of Computing and Information Systems
In late 2019, a new coronavirus, COVID-19, was reported in Wuhan, China. The origin of this virus is still debated. Nevertheless, this new coronavirus spreads like wildfire and is now a global pandemic. Different countries have responded to the pandemic in different ways with varying results. In this research, we investigate the effects of information and communication technologies (ICT) on COVID-19 pandemic management and control. Information and communication technologies have impacted nearly every industry in the world from finance and banking to universities and nonprofit organizations (Siau and Long, 2009). The health care system, which is composed of hospitals, individual …
Covid-19 Pandemic: Balancing Privacy And Saving Lives In Technology Usage,
2020
Singapore Management University
Covid-19 Pandemic: Balancing Privacy And Saving Lives In Technology Usage, Weiyu Wang, Keng Siau
Research Collection School Of Computing and Information Systems
COVID-19 is sweeping across the globe. Some countries are collecting anonymized data to study the movement of people and others are providing more detailed information about individuals in addition to the movement data. Surveillance tools are widely used to stem the spread of the COVID-19. South Korea uses smartphone location data, surveillance camera footage, and credit card data to create a publicly available map that tracks the paths of COVID-19 patients. Austria’s network operators share anonymized location data with the government, but the data may remain at risk from re-identification in the future. The Polish government releases an app for …
Values Of Ethical Artificial Intelligence,
2020
Singapore Management University
Values Of Ethical Artificial Intelligence, Ran Liu, Keng Siau
Research Collection School Of Computing and Information Systems
Artificial Intelligence (AI) is impacting all fields, areas, and disciplines. It is difficult to think of a field that is not infiltrated by AI. AI witnesses groundbreaking advancement recently with the revolutions and evolutions of machine learning techniques (Siau and Yang, 2017; Hyder et al., 2019). With proper guidance and appropriate usage, AI can be one of the most powerful tools that can drastically transform the world. Because of the broad and deep impact of AI, the ethical issues surrounding AI are of great concern to many. As AI advances, it is important to ensure that AI is used and …
Love A Restaurant? Swipe Right On Foodrecce,
2020
Singapore Management University
Love A Restaurant? Swipe Right On Foodrecce, Hady W. Lauw, Smu Office Of Research
Research@SMU Infographics
A bunch of your friends wants to meet for dinner, but nobody can agree on where and what to eat? FoodRecce can help! FoodRecce is an app, developed under the Preferred.AI initiative, that provides recommendations on restaurants based on users' locations and past preferences.
Specialization: Do Your Job Well Helping Students Who Are Considering A Career In Programming Know How To Invest Their Time.,
2020
Brigham Young University, Provo
Specialization: Do Your Job Well Helping Students Who Are Considering A Career In Programming Know How To Invest Their Time., Scott Pulley
Marriott Student Review
The article examines the effects of specialization on the hiring process for undergraduates studying programming whether in information systems or computer science.
Novel Technique To Analyze The Effects Of Cognitive And Non-Cognitive Predictors On Students Course Withdrawal In College,
2020
The University of Texas at Tyler
Novel Technique To Analyze The Effects Of Cognitive And Non-Cognitive Predictors On Students Course Withdrawal In College, Mohammed Ali
Technology Faculty Publications and Presentations
A novel technique was applied to a college student database to identify the cognitive and non-cognitive factors that predict college students’ course withdrawal behaviors. Predictors such as high school grade point average (HSGPA), standardized test scores (ACT–American College Test or SAT-Scholastic Aptitude Test), number of credit hours enrolled, and age were analyzed in this study. Data mining software algorithms were used to study information about undergraduate students at a west-south-central state university in the United States. The study results revealed that two factors, number of enrolled credit hours, and a student’s age have the most effect on collegiate course withdrawal …
Lulling Waters: A Poetry Reading For Real-Time Music Generation Through Emotion Mapping,
2020
New York University
Lulling Waters: A Poetry Reading For Real-Time Music Generation Through Emotion Mapping, Ashley Muniz, Toshihisa Tsuruoka
Electronic Literature Organization Conference 2020
Through a poetic narrative, “Lulling Waters” tells the story of a whale overcoming the loss of his mother, who passed away from ingesting plastic, as he attempts to escape from the polluted oceanic world. The live performance of this poem utilizes a software system called Soundwriter, which was developed with the goal of enriching the oral storytelling experience through music. This video demonstrates how Soundwriter’s real-time hybrid system was able to analyze “Lulling Waters” through its lexical and auditory features. Emotionally salient words were given ratings based on arousal, valence, and dominance while the emotionally charged prosodic features of the …
Patterns Of Population Displacement During Mega-Fires In California Detected Using Facebook Disaster Maps,
2020
Chapman University
Patterns Of Population Displacement During Mega-Fires In California Detected Using Facebook Disaster Maps, Shenyue Jia, Seung Hee Kim, Son V. Nghiem, Paul Doherty, Menas Kafatos
Mathematics, Physics, and Computer Science Faculty Articles and Research
The Facebook Disaster Maps (FBDM) work presented here is the first time this platform has been used to provide analysis-ready population change products derived from crowdsourced data targeting disaster relief practices. We evaluate the representativeness of FBDM data using the Mann-Kendall test and emerging hot and cold spots in an anomaly analysis to reveal the trend, magnitude, and agglommeration of population displacement during the Mendocino Complex and Woolsey fires in California, USA. Our results show that the distribution of FBDM pre-crisis users fits well with the total population from different sources. Due to usage habits, the elder population is underrepresented …
