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

Artificial Intelligence and Robotics Commons™

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

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 1021 - 1050 of 1664

Full-Text Articles in Artificial Intelligence and Robotics

Sequence-To-Sequence Learning For Automated Software Artifact Generation, Zhongxin Liu, Xin Xia, David Lo Jun 2021

Sequence-To-Sequence Learning For Automated Software Artifact Generation, Zhongxin Liu, Xin Xia, David Lo

Research Collection School Of Computing and Information Systems

During the development and maintenance of a software system, developers produce many digital artifacts besides source code, e.g., requirement documents, code comments, change history, bug reports, etc. Such artifacts are valuable for developers to understand and maintain the software system. However, creating software artifacts can be burdensome and developers sometimes neglect to write and maintain important artifacts. This problem can be alleviated by software artifact generation tools, which can assist developers in creating software artifacts and automatically generate artifacts to replace existing empty ones. The focus of this chapter is automated software artifact generation (hereon, SAG) using seq2seq learning. This …

Go to article

A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method For Efficient Optimization And Generalization, Pan Zhou, Xiao-Tong Yuan, Lin Zhouchen, Steven C. H. Hoi Jun 2021

A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method For Efficient Optimization And Generalization, Pan Zhou, Xiao-Tong Yuan, Lin Zhouchen, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Despite the success of stochastic variance-reduced gradient (SVRG) algorithms in solving large-scale problems, their stochastic gradient complexity often scales linearly with data size and is expensive for huge data. Accordingly, we propose a hybrid stochastic-deterministic minibatch proximal gradient (HSDMPG) algorithm for strongly convex problems with linear prediction structure, e.g. least squares and logistic/softmax regression. HSDMPG enjoys improved computational complexity that is data-size-independent for large-scale problems. It iteratively samples an evolving minibatch of individual losses to estimate the original problem, and can efficiently minimize the sampled subproblems. For strongly convex loss of n components, HSDMPG attains an -optimization-error within O κ …

Go to article

Learning Contextual Causality Between Daily Events From Time-Consecutive Images, Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, Dan Roth Jun 2021

Learning Contextual Causality Between Daily Events From Time-Consecutive Images, Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, Dan Roth

Research Collection School Of Computing and Information Systems

Conventional textual-based causal knowledge acquisition methods typically require laborious and expensive human annotations. As a result, their scale is often limited. Moreover, as no context is provided during the annotation, the resulting causal knowledge records (e.g., ConceptNet) typically do not consider the context. In this paper, we move out of the textual domain to explore a more scalable way of acquiring causal knowledge and investigate the possibility of learning contextual causality from the visual signal. Specifically, we first propose a high-quality dataset Vis-Causal and then conduct experiments to demonstrate that with good language and visual representations, it is possible to …

Go to article

Working With Smart Machines: Insights On The Future Of Work, Thomas H. Davenport, Steven M. Miller May 2021

Working With Smart Machines: Insights On The Future Of Work, Thomas H. Davenport, Steven M. Miller

Research Collection School Of Computing and Information Systems

In this article, we share our observations on how and why AI-based systems are being deployed. We look at how these systems have been integrated into existing and new work processes, especially the implications for the changing nature of work and how it will be conducted in future with AI-based smart machines. This will help companies that are in the earlier stages of considering, planning, or deploying these systems to know what to expect from recent developments in practice. We draw our analysis from 24 case studies that we have recently completed on AI system usage in actual operational settings.

Go to article

A Smarter Way To Manage Mass Transit In A Smart City: Rail Network Management At Singapore’S Land Transport Authority, Steven M. Miller, Thomas H. Davenport May 2021

A Smarter Way To Manage Mass Transit In A Smart City: Rail Network Management At Singapore’S Land Transport Authority, Steven M. Miller, Thomas H. Davenport

Research Collection School Of Computing and Information Systems

There is no widely agreed upon definition of a supposed “Smart City.” Yet, when you see city employees — in this case city-state employees — working in what are obviously smarter ways, “you know it when you see it.” One such example of a smarter way to work in a smart city setting is the way that employees of the Land Transport Authority (LTA) in Singapore are using a new generation of data driven, AI-enabled support systems to manage the city’s urban rail network. We spoke to LTA officers Kong Wai, Ho (Director of Integrated Operations and Planning) and Chris …

Go to article

Approximate Difference Rewards For Scalable Multigent Reinforcement Learning, Arambam James Singh, Akshat Kumar, Hoong Chuin Lau May 2021

Approximate Difference Rewards For Scalable Multigent Reinforcement Learning, Arambam James Singh, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We address the problem ofmultiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains - air-traffic control and cooperative navigation, shows better solution quality than previous approaches.

Go to article

A Matheuristic Algorithm For The Vehicle Routing Problem With Cross-Docking, Aldy Gunawan, Audrey Tedja Widjaja, Pieter Vansteenwegen, Vincent F. Yu May 2021

A Matheuristic Algorithm For The Vehicle Routing Problem With Cross-Docking, Aldy Gunawan, Audrey Tedja Widjaja, Pieter Vansteenwegen, Vincent F. Yu

Research Collection School Of Computing and Information Systems

This paper studies the integration of the vehicle routing problem with cross-docking (VRPCD). The aim is to find a set of routes to deliver products from a set of suppliers to a set of customers through a cross-dock facility, such that the operational and transportation costs are minimized, without violating the vehicle capacity and time horizon constraints. A two-phase matheuristic based on column generation is proposed. The first phase focuses on generating a set of feasible candidate routes in both pickup and delivery processes by implementing an adaptive large neighborhood search algorithm. A set of destroy and repair operators are …

Go to article

Edgeduet: Tiling Small Object Detection For Edge Assisted Autonomous Mobile Vision, Xu Wang, Zheng Yang, Jiahang Wu, Yi Zhao, Zimu Zhou May 2021

Edgeduet: Tiling Small Object Detection For Edge Assisted Autonomous Mobile Vision, Xu Wang, Zheng Yang, Jiahang Wu, Yi Zhao, Zimu Zhou

Research Collection School Of Computing and Information Systems

Accurate, real-time object detection on resource-constrained devices enables autonomous mobile vision applications such as traffic surveillance, situational awareness, and safety inspection, where it is crucial to detect both small and large objects in crowded scenes. Prior studies either perform object detection locally on-board or offload the task to the edge/cloud. Local object detection yields low accuracy on small objects since it operates on low-resolution videos to fit in mobile memory. Offloaded object detection incurs high latency due to uploading high-resolution videos to the edge/cloud. Rather than either pure local processing or offloading, we propose to detect large objects locally while …

Go to article

Learning Index Policies For Restless Bandits With Application To Maternal Healthcare, Arpita Biswas, Gaurav Aggarwal, Pradeep Varakantham, Milind Tambe May 2021

Learning Index Policies For Restless Bandits With Application To Maternal Healthcare, Arpita Biswas, Gaurav Aggarwal, Pradeep Varakantham, Milind Tambe

Research Collection School Of Computing and Information Systems

In many community health settings, it is crucial to have a systematic monitoring and intervention process to ensure that the patients adhere to healthcare programs, such as periodic health checks or taking medications. When these interventions are expensive, they can be provided to only a fixed small fraction of the patients at any period of time. Hence, it is important to carefully choose the beneficiaries who should be provided with interventions and when. We model this scenario as a restless multi-armed bandit (RMAB) problem, where each beneficiary is assumed to transition from one state to another depending on the intervention …

Go to article

A Differential Testing Approach For Evaluating Abstract Syntax Tree Mapping Algorithms, Yuanrui Fan, Xin Xia, David Lo, Ahmed E. Hassan, Yuan Wang, Shanping Li May 2021

A Differential Testing Approach For Evaluating Abstract Syntax Tree Mapping Algorithms, Yuanrui Fan, Xin Xia, David Lo, Ahmed E. Hassan, Yuan Wang, Shanping Li

Research Collection School Of Computing and Information Systems

Abstract syntax tree (AST) mapping algorithms are widely used to analyze changes in source code. Despite the foundational role of AST mapping algorithms, little effort has been made to evaluate the accuracy of AST mapping algorithms, i.e., the extent to which an algorithm captures the evolution of code. We observe that a program element often has only one best-mapped program element. Based on this observation, we propose a hierarchical approach to automatically compare the similarity of mapped statements and tokens by different algorithms. By performing the comparison, we determine if eachof the compared algorithms generates inaccurate mappings for a statement …

Go to article

Unveiling The Mystery Of Api Evolution In Deep Learning Frameworks: A Case Study Of Tensorflow 2, Zejun Zhang, Yanming Yang, Xin Xia, David Lo, Xiaoxue Ren, John C. Grundy May 2021

Unveiling The Mystery Of Api Evolution In Deep Learning Frameworks: A Case Study Of Tensorflow 2, Zejun Zhang, Yanming Yang, Xin Xia, David Lo, Xiaoxue Ren, John C. Grundy

Research Collection School Of Computing and Information Systems

API developers have been working hard to evolve APIs to provide more simple, powerful, and robust API libraries. Although API evolution has been studied for multiple domains, such as Web and Android development, API evolution for deep learning frameworks has not yet been studied. It is not very clear how and why APIs evolve in deep learning frameworks, and yet these are being more and more heavily used in industry. To fill this gap, we conduct a large-scale and in-depth study on the API evolution of Tensorflow 2, which is currently the most popular deep learning framework. We first extract …

Go to article

Ship-Gan: Generative Modeling Based Maritime Traffic Simulator, Chaithanya Basrur, Arambam James Singh, Arunesh Sinha, Akshat Kumar May 2021

Ship-Gan: Generative Modeling Based Maritime Traffic Simulator, Chaithanya Basrur, Arambam James Singh, Arunesh Sinha, Akshat Kumar

Research Collection School Of Computing and Information Systems

Modeling vessel movement in a maritime environment is an extremely challenging task given the complex nature of vessel behavior. Several existing multiagent maritime decision making frameworks require access to an accurate traffic simulator. We develop a system using electronic navigation charts to generate realistic and high fidelity vessel traffic data using Generative Adversarial Networks (GANs). Our proposed Ship-GAN uses a conditional Wasserstein GAN to model a vessel's behavior. The generator can simulate the travel time of vessels across different maritime zones conditioned on vessels' speeds and traffic intensity. Furthermore, it can be used as an accurate simulator for prior decision …

Go to article

Dialogue State Tracking With Incremental Reasoning, Lizi Liao, Le Hong Long, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua May 2021

Dialogue State Tracking With Incremental Reasoning, Lizi Liao, Le Hong Long, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method outperforms the state-of-theart methods in terms of joint …

Go to article

Guest Editorial: Non-Iid Outlier Detection In Complex Contexts, Guansong Pang, Fabrizio Angiulli, Mihai Cucuringu, Huan Liu May 2021

Guest Editorial: Non-Iid Outlier Detection In Complex Contexts, Guansong Pang, Fabrizio Angiulli, Mihai Cucuringu, Huan Liu

Research Collection School Of Computing and Information Systems

Outlier detection, also known as anomaly detection, aims at identifying data instances that are rare or significantly different from the majority of instances. Due to its significance in many critical domains like cybersecurity, fintech, healthcare, public security, and AI safety, outlier detection has been one of the most active research areas in various communities, such as machine learning, data mining, computer vision, and statistics. Traditional outlier-detection techniques generally assume that data are independent and identically distributed (IID), which are significantly challenged in complex contexts where data are actually non-IID. These contexts are ubiquitous in not only graph data, sequence data, …

Go to article

Adaptive Operating Hours For Improved Performance Of Taxi Fleets, Rajiv Ranjan Kumar, Pradeep Varakantham, Shih-Fen Cheng May 2021

Adaptive Operating Hours For Improved Performance Of Taxi Fleets, Rajiv Ranjan Kumar, Pradeep Varakantham, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Taxi fleets and car aggregation systems are an important component of the urban public transportation system. Taxis and cars in taxi fleets and car aggregation systems (e.g., Uber) are dependent on a large number of self-controlled and profit-driven taxi drivers, which introduces inefficiencies in the system. There are two ways in which taxi fleet performance can be optimized: (i) Operational decision making: improve assignment of taxis/cars to customers, while accounting for future demand; (ii) strategic decision making: optimize operating hours of (taxi and car) drivers. Existing research has primarily focused on the operational decisions in (i) and we focus on …

Go to article

Efficient Retrieval Of Matrix Factorization-Based Top-K Recommendations: A Survey Of Recent Approaches, Dung D. Le, Hady W. Lauw Apr 2021

Efficient Retrieval Of Matrix Factorization-Based Top-K Recommendations: A Survey Of Recent Approaches, Dung D. Le, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Top-k recommendation seeks to deliver a personalized list of k items to each individual user. An established methodology in the literature based on matrix factorization (MF), which usually represents users and items as vectors in low-dimensional space, is an effective approach to recommender systems, thanks to its superior performance in terms of recommendation quality and scalability. A typical matrix factorization recommender system has two main phases: preference elicitation and recommendation retrieval. The former analyzes user-generated data to learn user preferences and item characteristics in the form of latent feature vectors, whereas the latter ranks the candidate items based on the …

Go to article

Mixed Dish Recognition With Contextual Relation And Domain Alignment, Lixi Deng, Jingjing Chen, Chong-Wah Ngo, Qianru Sun, Sheng Tang, Yongdong Zhang, Tat-Seng Chua Apr 2021

Mixed Dish Recognition With Contextual Relation And Domain Alignment, Lixi Deng, Jingjing Chen, Chong-Wah Ngo, Qianru Sun, Sheng Tang, Yongdong Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Mixed dish is a food category that contains different dishes mixed in one plate, and is popular in Eastern and Southeast Asia. Recognizing the individual dishes in a mixed dish image is important for health related applications, e.g. to calculate the nutrition values of the dish. However, most existing methods that focus on single dish classification are not applicable to the recognition of mixed dish images. The main challenge of mixed dish recognition comes from three aspects: a wide range of dish types, the complex dish combination with severe overlap between different dishes and the large visual variances of same …

Go to article

Cross-Topic Rumor Detection Using Topic-Mixtures, Weijieying Ren, Jing Jiang, Ling Min Serena Khoo, Hai Leong Chieu Apr 2021

Cross-Topic Rumor Detection Using Topic-Mixtures, Weijieying Ren, Jing Jiang, Ling Min Serena Khoo, Hai Leong Chieu

Research Collection School Of Computing and Information Systems

There has been much interest in rumor detection using deep learning models in recent years. A well-known limitation of deep learning models is that they tend to learn superficial patterns, which restricts their generalization ability. We find that this is also true for cross-topic rumor detection. In this paper, we propose a method inspired by the “mixture of experts” paradigm. We assume that the prediction of the rumor class label given an instance is dependent on the topic distribution of the instance. After deriving a vector representation for each topic, given an instance, we derive a “topic mixture” vector for …

Go to article

Multi-Domain Dialogue State Tracking With Recursive Inference, Lizi Liao, Tongyao Zhu, Le Hong Long, Tat-Seng Chua Apr 2021

Multi-Domain Dialogue State Tracking With Recursive Inference, Lizi Liao, Tongyao Zhu, Le Hong Long, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Multi-domain dialogue state tracking (DST) is a critical component for monitoring user goals during the course of an interaction. Existing approaches have relied on dialogue history indiscriminately or updated on the most recent turns incrementally. However, in spite of modeling it based on fixed ontology or open vocabulary, the former setting violates the interactive and progressing nature of dialogue, while the later easily gets affected by the error accumulation conundrum. Here, we propose a Recursive Inference mechanism (ReInf) to resolve DST in multi-domain scenarios that call for more robust and accurate tracking capability. Specifically, our agent reversely reviews the dialogue …

Go to article

Homophily Outlier Detection In Non-Iid Categorical Data, Guansong Pang, Longbing Cao, Ling Chen Apr 2021

Homophily Outlier Detection In Non-Iid Categorical Data, Guansong Pang, Longbing Cao, Ling Chen

Research Collection School Of Computing and Information Systems

Most of existing outlier detection methods assume that the outlier factors (i.e., outlierness scoring measures) of data entities (e.g., feature values and data objects) are Independent and Identically Distributed (IID). This assumption does not hold in real-world applications where the outlierness of different entities is dependent on each other and/or taken from different probability distributions (non-IID). This may lead to the failure of detecting important outliers that are too subtle to be identified without considering the non-IID nature. The issue is even intensified in more challenging contexts, e.g., high-dimensional data with many noisy features. This work introduces a novel outlier …

Go to article

Time Period-Based Top-K Semantic Trajectory Pattern Query, Munkh-Erdene Yadamjav, Farhana Murtaza Choudhury, Zhifeng Bao, Baihua Zheng Apr 2021

Time Period-Based Top-K Semantic Trajectory Pattern Query, Munkh-Erdene Yadamjav, Farhana Murtaza Choudhury, Zhifeng Bao, Baihua Zheng

Research Collection School Of Computing and Information Systems

The sequences of user check-ins form semantic trajectories that represent the movement of users through time, along with the types of POIs visited. Extracting patterns in semantic trajectories can be widely used in applications such as route planning and trip recommendation. Existing studies focus on the entire time duration of the data, which may miss some temporally significant patterns. In addition, they require thresholds to define the interestingness of the patterns. Motivated by the above, we study a new problem of finding top-k semantic trajectory patterns w.r.t. a given time period and categories by considering the spatial closeness of POIs. …

Go to article

Spectral Tensor Train Parameterization Of Deep Learning Layers, A. Obukhov, M. Rakhuba, A. Liniger, Zhiwu Huang, S. Georgoulis, D. Dai, Van Gool L. Apr 2021

Spectral Tensor Train Parameterization Of Deep Learning Layers, A. Obukhov, M. Rakhuba, A. Liniger, Zhiwu Huang, S. Georgoulis, D. Dai, Van Gool L.

Research Collection School Of Computing and Information Systems

We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permits taking computational shortcuts when computing mappings. Spectral properties are often subject to constraints in optimization problems, leading to better models and stability of optimization. We start by looking at the compact SVD parameterization of weight matrices and identifying redundancy sources in the parameterization. We further apply the Tensor Train (TT) decomposition to the compact SVD components, and propose a non-redundant differentiable parameterization of fixed TT-rank tensor manifolds, termed the Spectral Tensor Train Parameterization (STTP). We …

Go to article

How Do Users Answer Matlab Questions On Q&A Sites? A Case Study On Stack Overflow And Mathworks, Mahshid Naghashzadeh, Amir Hagshenas, Ashkan Sami, David Lo Mar 2021

How Do Users Answer Matlab Questions On Q&A Sites? A Case Study On Stack Overflow And Mathworks, Mahshid Naghashzadeh, Amir Hagshenas, Ashkan Sami, David Lo

Research Collection School Of Computing and Information Systems

MATLAB is an engineering programming language with various toolboxes that has a dedicated Question and Answer (Q&A) platform on the MathWorks website, which is similar to Stack Overflow (SO). Moreover, some MATLAB users ask their questions on SO. This paper aims to compare these two Q&A platforms to see what kind of questions are asked and how developers answer these questions in each platform. The result of our analysis on 80,382 MATLAB questions on SO and 266,367 questions on MathWorks show that MATLAB questions on topics ranging from the MATLAB software installation to questions related to programming received high votes …

Go to article

Is The Ground Truth Really Accurate? Dataset Purification For Automated Program Repair, Deheng Yang, Yan Lei, Xiaoguang Mao, David Lo, Huan Xie, Meng Yan Mar 2021

Is The Ground Truth Really Accurate? Dataset Purification For Automated Program Repair, Deheng Yang, Yan Lei, Xiaoguang Mao, David Lo, Huan Xie, Meng Yan

Research Collection School Of Computing and Information Systems

Datasets of real-world bugs shipped with human-written patches are intensively used in the evaluation of existing automated program repair (APR) techniques, wherein the human-written patches always serve as the ground truth, for manual or automated assessment approaches, to evaluate the correctness of test-suite adequate patches. An inaccurate human-written patch tangled with other code changes will pose threats to the reliability of the assessment results. Therefore, the construction of such datasets always requires much manual effort on isolating real bug fixes from bug fixing commits. However, the manual work is time-consuming and prone to mistakes, and little has been known on …

Go to article

Learning To Assess The Quality Of Stroke Rehabilitation Exercises, Min Hun Lee, Daniel P. Siewiorek, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez I Badia Mar 2021

Learning To Assess The Quality Of Stroke Rehabilitation Exercises, Min Hun Lee, Daniel P. Siewiorek, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez I Badia

Research Collection School Of Computing and Information Systems

Due to the limited number of therapists, task-oriented exercises are often prescribed for post-stroke survivors as in-home rehabilitation. During in-home rehabilitation, a patient may become unmotivated or confused to comply prescriptions without the feedback of a therapist. To address this challenge, this paper proposes an automated method that can achieve not only qualitative, but also quantitative assessment of stroke rehabilitation exercises. Specifically, we explored a threshold model that utilizes the outputs of binary classifiers to quantify the correctness of a movements into a performance score. We collected movements of 11 healthy subjects and 15 post-stroke survivors using a Kinect sensor …

Go to article

Deep Learning For Anomaly Detection: Challenges, Methods, And Opportunities, Guansong Pang, Longbing Cao, Charu Aggarwal Mar 2021

Deep Learning For Anomaly Detection: Challenges, Methods, And Opportunities, Guansong Pang, Longbing Cao, Charu Aggarwal

Research Collection School Of Computing and Information Systems

In this tutorial we aim to present a comprehensive survey of the advances in deep learning techniques specifically designed for anomaly detection (deep anomaly detection for short). Deep learning has gained tremendous success in transforming many data mining and machine learning tasks, but popular deep learning techniques are inapplicable to anomaly detection due to some unique characteristics of anomalies, e.g., rarity, heterogeneity, boundless nature, and prohibitively high cost of collecting large-scale anomaly data. Through this tutorial, audiences would gain a systematic overview of this area, learn the key intuitions, objective functions, underlying assumptions, advantages and disadvantages of different categories of …

Go to article

Accelerating Large-Scale Heterogeneous Interaction Graph Embedding Learning Via Importance Sampling, Yugang Ji, Mingyang Yin, Hongxia Yang, Jingren Zhou, Vincent W. Zheng, Chuan Shi, Yuan Fang Feb 2021

Accelerating Large-Scale Heterogeneous Interaction Graph Embedding Learning Via Importance Sampling, Yugang Ji, Mingyang Yin, Hongxia Yang, Jingren Zhou, Vincent W. Zheng, Chuan Shi, Yuan Fang

Research Collection School Of Computing and Information Systems

In real-world problems, heterogeneous entities are often related to each other through multiple interactions, forming a Heterogeneous Interaction Graph (HIG in short). While modeling HIGs to deal with fundamental tasks, graph neural networks present an attractive opportunity that can make full use of the heterogeneity and rich semantic information by aggregating and propagating information from different types of neighborhoods. However, learning on such complex graphs, often with millions or billions of nodes, edges, and various attributes, could suffer from expensive time cost and high memory consumption. In this paper, we attempt to accelerate representation learning on large-scale HIGs by adopting …

Go to article

Norm-Based Generalisation Bounds For Deep Multi-Class Convolutional Neural Networks, Antoine Ledent, Waleed Mustafa, Yunwen Lei, Marius Kloft Feb 2021

Norm-Based Generalisation Bounds For Deep Multi-Class Convolutional Neural Networks, Antoine Ledent, Waleed Mustafa, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

We show generalisation error bounds for deep learning with two main improvements over the state of the art. (1) Our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating the bounds in terms of the Frobenius-norm of the weight matrices, where previous bounds exhibit at least a squareroot dependence on the number of classes. (2) We adapt the classic Rademacher analysis of DNNs to incorporate weight sharing—a task of fundamental theoretical importance which was previously attempted only under very restrictive assumptions. In our results, each convolutional filter contributes only once …

Go to article

Fine-Grained Generalization Analysis Of Vector-Valued Learning, Liang Wu, Antoine Ledent, Yunwen Lei, Marius Kloft Feb 2021

Fine-Grained Generalization Analysis Of Vector-Valued Learning, Liang Wu, Antoine Ledent, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

Many fundamental machine learning tasks can be formulated as a problem of learning with vector-valued functions, where we learn multiple scalar-valued functions together. Although there is some generalization analysis on different specific algorithms under the empirical risk minimization principle, a unifying analysis of vector-valued learning under a regularization framework is still lacking. In this paper, we initiate the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size. Our discussions relax the existing assumptions on the restrictive constraint of hypothesis spaces, smoothness of loss …

Go to article

Model Uncertainty Guides Visual Object Tracking, Lijun Zhou, Antoine Ledent, Qintao Hu, Ting Liu, Jianlin Zhang, Marius Kloft Feb 2021

Model Uncertainty Guides Visual Object Tracking, Lijun Zhou, Antoine Ledent, Qintao Hu, Ting Liu, Jianlin Zhang, Marius Kloft

Research Collection School Of Computing and Information Systems

Model object trackers largely rely on the online learning of a discriminative classifier from potentially diverse sample frames. However, noisy or insufficient amounts of samples can deteriorate the classifiers' performance and cause tracking drift. Furthermore, alterations such as occlusion and blurring can cause the target to be lost. In this paper, we make several improvements aimed at tackling uncertainty and improving robustness in object tracking. Our first and most important contribution is to propose a sampling method for the online learning of object trackers based on uncertainty adjustment: our method effectively selects representative sample frames to feed the discriminative branch …

Go to article

First Prev Next Last