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

Digital Commons Network™

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

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 3271 - 3300 of 8597

Full-Text Articles in Entire DC Network

Pricing And Equilibrium In On-Demand Ride-Pooling Markets, Jintao Ke, Hai Yang, Xinwei Li, Hai Wang, Jieping Ye Sep 2020

Pricing And Equilibrium In On-Demand Ride-Pooling Markets, Jintao Ke, Hai Yang, Xinwei Li, Hai Wang, Jieping Ye

Research Collection School Of Computing and Information Systems

With the recent rapid growth of technology-enabled mobility services, ride-sourcing platforms, such as Uber and DiDi, have launched commercial on-demand ride-pooling programs that allow drivers to serve more than one passenger request in each ride. Without requiring the prearrangement of trip schedules, these programs match on-demand passenger requests with vehicles that have vacant seats. Ride-pooling programs are expected to offer benefits for both individual passengers in the form of cost savings and for society in the form of traffic alleviation and emission reduction. In addition to some exogenous variables and environments for ride-sourcing market, such as city size and population …

Go to article

How (Not) To Find Bugs: The Interplay Between Merge Conflicts, Co-Changes, And Bugs, Luis Amaral, Marcos C. Oliveira, Welder Luz, José Fortes, Rodrigo Bonifacio, Daniel Alencar, Eduardo Monteiro, Gustavo Pinto, David Lo Sep 2020

How (Not) To Find Bugs: The Interplay Between Merge Conflicts, Co-Changes, And Bugs, Luis Amaral, Marcos C. Oliveira, Welder Luz, José Fortes, Rodrigo Bonifacio, Daniel Alencar, Eduardo Monteiro, Gustavo Pinto, David Lo

Research Collection School Of Computing and Information Systems

Context: In a seminal work, Ball et al. [1] investigate if the information available in version control systems could be used to predict defect density, arguing that practitioners and researchers could better understand errors "if [our] version control system could talk". In the meanwhile, several research works have reported that conflict merge resolution is a time consuming and error-prone task, while other contributions diverge about the correlation between co-change dependencies and defect density. Problem: The correlation between conflicting merge scenarios and bugs has not been addressed before, whilst the correlation between co-change dependencies and bug density has been only investigated …

Go to article

An Empirical Study Of The Dependency Networks Of Deep Learning Libraries, Junxiao Han, Shuiguang Deng, David Lo, Chen Zhi, Jianwei Yin, Xin Xia Sep 2020

An Empirical Study Of The Dependency Networks Of Deep Learning Libraries, Junxiao Han, Shuiguang Deng, David Lo, Chen Zhi, Jianwei Yin, Xin Xia

Research Collection School Of Computing and Information Systems

Deep Learning techniques have been prevalent in various domains, and more and more open source projects in GitHub rely on deep learning libraries to implement their algorithms. To that end, they should always keep pace with the latest versions of deep learning libraries to make the best use of deep learning libraries. Aptly managing the versions of deep learning libraries can help projects avoid crashes or security issues caused by deep learning libraries. Unfortunately, very few studies have been done on the dependency networks of deep learning libraries. In this paper, we take the first step to perform an exploratory …

Go to article

Marble: Model-Based Robustness Analysis Of Stateful Deep Learning Systems, Xiaoning Du, Yi Li, Xiaofei Xie, Lei Ma, Yang Liu, Jianjun Zhao Sep 2020

Marble: Model-Based Robustness Analysis Of Stateful Deep Learning Systems, Xiaoning Du, Yi Li, Xiaofei Xie, Lei Ma, Yang Liu, Jianjun Zhao

Research Collection School Of Computing and Information Systems

State-of-the-art deep learning (DL) systems are vulnerable to adversarial examples, which hinders their potential adoption in safetyand security-critical scenarios. While some recent progress has been made in analyzing the robustness of feed-forward neural networks, the robustness analysis for stateful DL systems, such as recurrent neural networks (RNNs), still remains largely uncharted. In this paper, we propose Marble, a model-based approach for quantitative robustness analysis of real-world RNN-based DL systems. Marble builds a probabilistic model to compactly characterize the robustness of RNNs through abstraction. Furthermore, we propose an iterative refinement algorithm to derive a precise abstraction, which enables accurate quantification of …

Go to article

The Gap Of Semantic Parsing: A Survey On Automatic Math Word Problem Solvers, Dongxiang Zhang, Lei Wang, Luming Zhang, Bing Tian Dai, Heng Tao Shen Sep 2020

The Gap Of Semantic Parsing: A Survey On Automatic Math Word Problem Solvers, Dongxiang Zhang, Lei Wang, Luming Zhang, Bing Tian Dai, Heng Tao Shen

Research Collection School Of Computing and Information Systems

Solving mathematical word problems (MWPs) automatically is challenging, primarily due to the semantic gap between human-readable words and machine-understandable logics. Despite the long history dated back to the 1960s, MWPs have regained intensive attention in the past few years with the advancement of Artificial Intelligence (AI). Solving MWPs successfully is considered as a milestone towards general AI. Many systems have claimed promising results in self-crafted and small-scale datasets. However, when applied on large and diverse datasets, none of the proposed methods in the literature achieves high precision, revealing that current MWP solvers still have much room for improvement. This motivated …

Go to article

Weakly Paired Multi-Domain Image Translation, M.Y. Zhang, Zhiwu Huang, D.P. Paudel, J. Thoma, Gool L. Van Sep 2020

Weakly Paired Multi-Domain Image Translation, M.Y. Zhang, Zhiwu Huang, D.P. Paudel, J. Thoma, Gool L. Van

Research Collection School Of Computing and Information Systems

In this paper, we aim at studying the new problem of weakly paired multi-domain image translation. To this end, we collect a dataset that contains weakly paired images from multiple domains. Two images are considered to be weakly paired if they are captured from nearby locations and share an overlapping field of view. These images are possibly captured by two asynchronous cameras—often resulting in images from separate domains, e.g. summer and winter. Major motivations for using weakly paired images are: (i) performance improvement towards that of paired data; (ii) cheap labels and abundant data availability. For the first time in …

Go to article

Time-Warped Sparse Non-Negative Factorization For Functional Data Analysis, Chen Zhang, Steven C. H. Hoi, Fugee Tsung Sep 2020

Time-Warped Sparse Non-Negative Factorization For Functional Data Analysis, Chen Zhang, Steven C. H. Hoi, Fugee Tsung

Research Collection School Of Computing and Information Systems

This article proposes a novel time-warped sparse non-negative factorization method for functional data analysis. The proposed method on the one hand guarantees the extracted basis functions and their coefficients to be positive and interpretable, and on the other hand is able to handle weakly correlated functions with different features. Furthermore, the method incorporates time warping into factorization and hence allows the extracted basis functions of different samples to have temporal deformations. An efficient framework of estimation algorithms is proposed based on a greedy variable selection approach. Numerical studies together with case studies on real-world data demonstrate the efficacy and applicability …

Go to article

A Performance-Sensitive Malware Detection System Using Deep Learning On Mobile Devices, Ruitao Feng, Sen Chen, Xiaofei Xie, Guozhu Meng, Shang-Wei Lin, Yang Liu Sep 2020

A Performance-Sensitive Malware Detection System Using Deep Learning On Mobile Devices, Ruitao Feng, Sen Chen, Xiaofei Xie, Guozhu Meng, Shang-Wei Lin, Yang Liu

Research Collection School Of Computing and Information Systems

Currently, Android malware detection is mostly performed on server side against the increasing number of malware. Powerful computing resource provides more exhaustive protection for app markets than maintaining detection by a single user. However, apart from the applications (apps) provided by the official market (i.e., Google Play Store), apps from unofficial markets and third-party resources are always causing serious security threats to end-users. Meanwhile, it is a time-consuming task if the app is downloaded first and then uploaded to the server side for detection, because the network transmission has a lot of overhead. In addition, the uploading process also suffers …

Go to article

Dct: An Scalable Multi-Objective Module Clustering Tool, Ana Paula M. Tarchetti, Luis Henrique Vieira Amaral, Marcos C. Oliveira, Rodrigo Bonifacio, Gustavo Pinto, David Lo Sep 2020

Dct: An Scalable Multi-Objective Module Clustering Tool, Ana Paula M. Tarchetti, Luis Henrique Vieira Amaral, Marcos C. Oliveira, Rodrigo Bonifacio, Gustavo Pinto, David Lo

Research Collection School Of Computing and Information Systems

Maintaining complex software systems is a timeconsuming and challenging task. Practitioners must have a general understanding of the system’s decomposition and how the system’s developers have implemented the software features (probably cutting across different modules). Re-engineering practices are imperative to tackle these challenges. Previous research has shown the benefits of using software module clustering (SMC) to aid developers during re-engineering tasks (e.g., revealing the architecture of the systems, identifying how the concerns are spread among the modules of the systems, recommending refactorings, and so on). Nonetheless, although the literature on software module clustering has substantially evolved in the last 20 …

Go to article

The Impact Of Automated Feature Selection Techniques On The Interpretation Of Defect Models, Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Christoph Treude Sep 2020

The Impact Of Automated Feature Selection Techniques On The Interpretation Of Defect Models, Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Christoph Treude

Research Collection School Of Computing and Information Systems

The interpretation of defect models heavily relies on software metrics that are used to construct them. Prior work often uses feature selection techniques to remove metrics that are correlated and irrelevant in order to improve model performance. Yet, conclusions that are derived from defect models may be inconsistent if the selected metrics are inconsistent and correlated. In this paper, we systematically investigate 12 automated feature selection techniques with respect to the consistency, correlation, performance, computational cost, and the impact on the interpretation dimensions. Through an empirical investigation of 14 publicly-available defect datasets, we find that (1) 94–100% of the selected …

Go to article

Wait For It: Identifying 'On-Hold' Self-Admitted Technical Debt, Rungroj Maipradit, Christoph Treude, Hideaki Hata, Kenichi Matsumoto Sep 2020

Wait For It: Identifying 'On-Hold' Self-Admitted Technical Debt, Rungroj Maipradit, Christoph Treude, Hideaki Hata, Kenichi Matsumoto

Research Collection School Of Computing and Information Systems

Self-admitted technical debt refers to situations where a software developer knows that their current implementation is not optimal and indicates this using a source code comment. In this work, we hypothesize that it is possible to develop automated techniques to understand a subset of these comments in more detail, and to propose tool support that can help developers manage self-admitted technical debt more effectively. Based on a qualitative study of 333 comments indicating self-admitted technical debt, we first identify one particular class of debt amenable to automated management: on-hold self-admitted technical debt (on-hold SATD), i.e., debt which contains a condition …

Go to article

Human-Like Summaries From Heterogeneous And Time-Windowed Software Development Artefacts, Mahfouth Alghamdi, Christoph Treude, Markus Wagner Sep 2020

Human-Like Summaries From Heterogeneous And Time-Windowed Software Development Artefacts, Mahfouth Alghamdi, Christoph Treude, Markus Wagner

Research Collection School Of Computing and Information Systems

Automatic text summarisation has drawn considerable interest in the area of software engineering. It is challenging to summarise the activities related to a software project, (1) because of the volume and heterogeneity of involved software artefacts, and (2) because it is unclear what information a developer seeks in such a multi-document summary. We present the first framework for summarising multi-document software artefacts containing heterogeneous data within a given time frame. To produce human-like summaries, we employ a range of iterative heuristics to minimise the cosine-similarity between texts and high-dimensional feature vectors. A first study shows that users find the automatically …

Go to article

Cats Are Not Fish: Deep Learning Testing Calls For Out-Of-Distribution Awareness, David Berend, Xiaofei Xie, Lei Ma, Lingjun Zhou, Yang Liu, Chi Xu, Jianjun Zhao Sep 2020

Cats Are Not Fish: Deep Learning Testing Calls For Out-Of-Distribution Awareness, David Berend, Xiaofei Xie, Lei Ma, Lingjun Zhou, Yang Liu, Chi Xu, Jianjun Zhao

Research Collection School Of Computing and Information Systems

As Deep Learning (DL) is continuously adopted in many industrial applications, its quality and reliability start to raise concerns. Similar to the traditional software development process, testing the DL software to uncover its defects at an early stage is an effective way to reduce risks after deployment. According to the fundamental assumption of deep learning, the DL software does not provide statistical guarantee and has limited capability in handling data that falls outside of its learned distribution, i.e., out-of-distribution (OOD) data. Although recent progress has been made in designing novel testing techniques for DL software, which can detect thousands of …

Go to article

Efficient Fine-Grained Data Sharing Mechanism For Electronic Medical Record Systems With Mobile Devices, Hui Ma, Rui Zhang, Guomin Yang, Zishuai Zong, Kai He, Yuting Xiao Sep 2020

Efficient Fine-Grained Data Sharing Mechanism For Electronic Medical Record Systems With Mobile Devices, Hui Ma, Rui Zhang, Guomin Yang, Zishuai Zong, Kai He, Yuting Xiao

Research Collection School Of Computing and Information Systems

Sharing digital medical records on public cloud storage via mobile devices facilitates patients (doctors) to get (offer) medical treatment of high quality and efficiency. However, challenges such as data privacy protection, flexible data sharing, efficient authority delegation, computation efficiency optimization, are remaining toward achieving practical fine-grained access control in the Electronic Medical Record (EMR) system. In this work, we propose an innovative access control model and a fine-grained data sharing mechanism for EMR, which simultaneously achieves the above-mentioned features and is suitable for resource-constrained mobile devices. In the model, complex computation is outsourced to public cloud servers, leaving almost no …

Go to article

Smart Contract Repair, Xiao Liang Yu, Omar Al-Bataineh, David Lo, Abhik Roychoudhury Sep 2020

Smart Contract Repair, Xiao Liang Yu, Omar Al-Bataineh, David Lo, Abhik Roychoudhury

Research Collection School Of Computing and Information Systems

Smart contracts are automated or self-enforcing contracts that can be used to exchange assets without having to place trust in third parties. Many commercial transactions use smart contracts due to their potential benefits in terms of secure peer-to-peer transactions independent of external parties. Experience shows that many commonly used smart contracts are vulnerable to serious malicious attacks, which may enable attackers to steal valuable assets of involving parties. There is, therefore, a need to apply analysis and automated repair techniques to detect and repair bugs in smart contracts before being deployed. In this work, we present the first general-purpose automated …

Go to article

Accelerating All-Sat Computation With Short Blocking Clauses, Yueling Zhang, Geguang Pu, Jun Sun Sep 2020

Accelerating All-Sat Computation With Short Blocking Clauses, Yueling Zhang, Geguang Pu, Jun Sun

Research Collection School Of Computing and Information Systems

The All-SAT (All-SATisfiable) problem focuses on finding all satisfiable assignments of a given propositional formula, whose applications include model checking, automata construction, and logic minimization. A typical ALL-SAT solver is normally based on iteratively computing satisfiable assignments of the given formula. In this work, we introduce BASOLVER, a backbone-based All-SAT solver for propositional formulas. Compared to the existing approaches, BASOLVER generates shorter blocking clauses by removing backbone variables from the partial assignments and the blocking clauses. We compare BASOLVER with 4 existing ALL-SAT solvers, namely MBLOCKING, BC, BDD, and NBC. Experimental results indicate that although finding all the backbone variables …

Go to article

Towards Generating Thread-Safe Classes Automatically, Haichi Wang, Zan Wang, Jun Sun, Shuang Lin, Ayesha Sadiq, Yuan Fang Li Sep 2020

Towards Generating Thread-Safe Classes Automatically, Haichi Wang, Zan Wang, Jun Sun, Shuang Lin, Ayesha Sadiq, Yuan Fang Li

Research Collection School Of Computing and Information Systems

The existing concurrency model for Java (or C) requires programmers to design and implement thread-safe classes by explicitly acquiring locks and releasing locks. Such a model is error-prone and is the reason for many concurrency bugs. While there are alternative models like transactional memory, manually writing locks remains prevalent in practice. In this work, we propose AutoLock, which aims to solve the problem by fully automatically generating thread-safe classes. Given a class which is assumed to be correct with sequential clients, AutoLock automatically generates a thread-safe class which is linearizable, and does it in a way without requiring a specification …

Go to article

Towards Interpreting Recurrent Neural Networks Through Probabilistic Abstraction, Guoliang Dong, Jingyi Wang, Jun Sun, Yang Zhang, Xinyu Wang, Ting Dai, Jin Song Dong, Xingen Wang Sep 2020

Towards Interpreting Recurrent Neural Networks Through Probabilistic Abstraction, Guoliang Dong, Jingyi Wang, Jun Sun, Yang Zhang, Xinyu Wang, Ting Dai, Jin Song Dong, Xingen Wang

Research Collection School Of Computing and Information Systems

Neural networks are becoming a popular tool for solving many realworld problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex black-box models, which hinders humans from interpreting and consequently trusting them in making critical decisions. Towards interpreting neural networks, several approaches have been proposed to extract simple deterministic models from neural networks. The results are not encouraging (e.g., low accuracy and limited scalability), fundamentally due to the limited expressiveness of such simple models.In this work, we propose an approach to extract probabilistic automata for interpreting an important …

Go to article

Bus Frequency Optimization: When Waiting Time Matters In User Satisfaction, Songsong Mo, Zhifeng Bao, Baihua Zheng, Zhiyong Peng Sep 2020

Bus Frequency Optimization: When Waiting Time Matters In User Satisfaction, Songsong Mo, Zhifeng Bao, Baihua Zheng, Zhiyong Peng

Research Collection School Of Computing and Information Systems

Reorganizing bus frequency to cater for the actual travel demand can save the cost of the public transport system significantly. Many, if not all, existing studies formulate this as a bus frequency optimization problem which tries to minimize passengers’ average waiting time. However, many investigations have confirmed that the user satisfaction drops faster as the waiting time increases. Consequently, this paper studies the bus frequency optimization problem considering the user satisfaction. Specifically, for the first time to our best knowledge, we study how to schedule the buses such that the total number of passengers who could receive their bus services …

Go to article

Learning To Collaborate In Multi-Module Recommendation Via Multi-Agent Reinforcement Learning Without Communication, Xu He, An Bo, Yanghua Li, Haikai Chen, Rundong Wang, Xinrun Wang, Runsheng Yu, Xin Li, Zhirong Wang Sep 2020

Learning To Collaborate In Multi-Module Recommendation Via Multi-Agent Reinforcement Learning Without Communication, Xu He, An Bo, Yanghua Li, Haikai Chen, Rundong Wang, Xinrun Wang, Runsheng Yu, Xin Li, Zhirong Wang

Research Collection School Of Computing and Information Systems

With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page often consists of different independent modules. The ranking policies of these modules are decided by different teams and optimized individually without cooperation, which might result in competition between modules. Thus, the global policy of the whole page could be sub-optimal. In this paper, we propose a novel multi-agent cooperative reinforcement learning approach with the restriction that different modules cannot communicate. Our contributions are …

Go to article

A Fast Anderson-Chebyshev Acceleration For Nonlinear Optimization, Zhize Li, Jian Li Aug 2020

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, …

Go to article

A Unified Framework For Sparse Online Learning, Peilin Zhao, Dayong Wong, Pengcheng Wu, Steven C. H. Hoi Aug 2020

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 …

Go to article

Dual-Dropout Graph Convolutional Network For Predicting Synthetic Lethality In Human Cancers, Ruichu Cai, Xuexin Chen, Yuan Fang, Min Wu, Yuexing Hao Aug 2020

Dual-Dropout Graph Convolutional Network For Predicting Synthetic Lethality In Human Cancers, Ruichu Cai, Xuexin Chen, Yuan Fang, Min Wu, Yuexing Hao

Research Collection School Of Computing and Information Systems

Motivation: Synthetic lethality (SL) is a promising form of gene interaction for cancer therapy, as it is able to identify specific genes to target at cancer cells without disrupting normal cells. As high-throughput wet-lab settings are often costly and face various challenges, computational approaches have become a practical complement. In particular, predicting SLs can be formulated as a link prediction task on a graph of interacting genes. Although matrix factorization techniques have been widely adopted in link prediction, they focus on mapping genes to latent representations in isolation, without aggregating information from neighboring genes. Graph convolutional networks (GCN) can capture …

Go to article

A Systematic Density-Based Clustering Method Using Anchor Points, Yizhang Wang, Di Wang, Wei Pang, Ah-Hwee Tan, You Zhou Aug 2020

A Systematic Density-Based Clustering Method Using Anchor Points, Yizhang Wang, Di Wang, Wei Pang, Ah-Hwee Tan, You Zhou

Research Collection School Of Computing and Information Systems

Clustering is an important unsupervised learning method in machine learning and data mining. Many existing clustering methods may still face the challenge in self-identifying clusters with varying shapes, sizes and densities. To devise a more generic clustering method that considers all the aforementioned properties of the natural clusters, we propose a novel clustering algorithm named Anchor Points based Clustering (APC). The anchor points in APC are characterized by having a relatively large distance from data points with higher densities. We take anchor points as centers to obtain intermediate clusters, which can divide the whole dataset more appropriately so as to …

Go to article

A Multicut Outer-Approximation Approach For Competitive Facility Location Under Random Utilities, Tien Mai, Andrea Lodi Aug 2020

A Multicut Outer-Approximation Approach For Competitive Facility Location Under Random Utilities, Tien Mai, Andrea Lodi

Research Collection School Of Computing and Information Systems

This work concerns the maximum capture facility location problem with random utilities, i.e., the problem of seeking to locate new facilities in a competitive market such that the captured demand of users is maximized, assuming that each individual chooses among all available facilities according to a random utility maximization model. The main challenge lies in the nonlinearity of the objective function. Motivated by the convexity and separable structure of such an objective function, we propose an enhanced implementation of the outer approximation scheme. Our algorithm works in a cutting plane fashion and allows to separate the objective function into a …

Go to article

Rethinking Pruning For Accelerating Deep Inference At The Edge, Dawei Gao, Xiaoxi He, Zimu Zhou, Yongxin Tong, Ke Xu, Lothar Thiele Aug 2020

Rethinking Pruning For Accelerating Deep Inference At The Edge, Dawei Gao, Xiaoxi He, Zimu Zhou, Yongxin Tong, Ke Xu, Lothar Thiele

Research Collection School Of Computing and Information Systems

There is a growing trend to deploy deep neural networks at the edge for high-accuracy, real-time data mining and user interaction. Applications such as speech recognition and language understanding often apply a deep neural network to encode an input sequence and then use a decoder to generate the output sequence. A promising technique to accelerate these applications on resource-constrained devices is network pruning, which compresses the size of the deep neural network without severe drop in inference accuracy. However, we observe that although existing network pruning algorithms prove effective to speed up the prior deep neural network, they lead to …

Go to article

Adaptive Task Sampling For Meta-Learning, Chenghao Liu, Zhihao Wang, Doyen Sahoo, Yuan Fang, Kun Zhang, Steven C. H. Hoi Aug 2020

Adaptive Task Sampling For Meta-Learning, Chenghao Liu, Zhihao Wang, Doyen Sahoo, Yuan Fang, Kun Zhang, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time by randomly sampling classes in meta-training data to construct fewshot tasks for episodic training. While a rich line of work focuses solely on how to extract meta-knowledge across tasks, we exploit the complementary problem on how to generate informative tasks. We argue that the randomly sampled tasks could be sub-optimal and uninformative (e.g., the task of classifying “dog” from “laptop” is often trivial) to the meta-learner. …

Go to article

Prevalence, Contents And Automatic Detection Of Kl-Satd, Leevi Rantala, Mika Mantyla, David Lo Aug 2020

Prevalence, Contents And Automatic Detection Of Kl-Satd, Leevi Rantala, Mika Mantyla, David Lo

Research Collection School Of Computing and Information Systems

When developers use different keywords such as TODO and FIXME in source code comments to describe self-admitted technical debt (SATD), we refer it as Keyword-Labeled SATD (KL-SATD). We study KL-SATD from 33 software repositories with 13,588 KL-SATD comments. We find that the median percentage of KL-SATD comments among all comments is only 1,52%. We find that KL-SATD comment contents include words expressing code changes and uncertainty, such as remove, fix, maybe and probably. This makes them different compared to other comments. KL-SATD comment contents are similar to manually labeled SATD comments of prior work. Our machine learning classifier using logistic …

Go to article

An Analysis Of Sketched Irls For Accelerated Sparse Residual Regression, Daichi Iwata, Michael Waechter, Wen-Yan Lin, Yasuyuki Matsushita Aug 2020

An Analysis Of Sketched Irls For Accelerated Sparse Residual Regression, Daichi Iwata, Michael Waechter, Wen-Yan Lin, Yasuyuki Matsushita

Research Collection School Of Computing and Information Systems

This paper studies the problem of sparse residual regression, i.e., learning a linear model using a norm that favors solutions in which the residuals are sparsely distributed. This is a common problem in a wide range of computer vision applications where a linear system has a lot more equations than unknowns and we wish to find the maximum feasible set of equations by discarding unreliable ones. We show that one of the most popular solution methods, iteratively reweighted least squares (IRLS), can be significantly accelerated by the use of matrix sketching. We analyze the convergence behavior of the proposed method …

Go to article

Commanding And Re-Dictation: Developing Eyes-Free Voice-Based Interaction For Editing Dictated Text, Debjyoti Ghosh, Can Liu, Shengdong Zhao, Kotaro Hara Aug 2020

Commanding And Re-Dictation: Developing Eyes-Free Voice-Based Interaction For Editing Dictated Text, Debjyoti Ghosh, Can Liu, Shengdong Zhao, Kotaro Hara

Research Collection School Of Computing and Information Systems

Existing voice-based interfaces have limited support for text editing, especially when seeing the text is difficult, e.g., while walking or cooking. This research develops voice interaction techniques for eyes-free text editing. First, with a Wizard-of-Oz study, we identified two primary user strategies: using commands, e.g., “replace go with goes” and re-dictating over an erroneous portion, e.g., correcting “he go there” by saying “he goes there.” To support these user strategies with an actual system implementation, we developed two eyes-free voice interaction techniques, Commanding and Re-dictation, and evaluated them with a controlled experiment. Results showed that while Re-dictation performs significantly better …

Go to article

First Prev Next Last