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

OS and Networks Commons™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type

Articles 121 - 150 of 345

Full-Text Articles in OS and Networks

An Improved Learnable Evolution Model For Solving Multi-Objective Vehicle Routing Problem With Stochastic Demand, Yunyun Niu, Detian Kong, Rong Wen, Zhiguang Cao, Jianhua Xiao Aug 2021

An Improved Learnable Evolution Model For Solving Multi-Objective Vehicle Routing Problem With Stochastic Demand, Yunyun Niu, Detian Kong, Rong Wen, Zhiguang Cao, Jianhua Xiao

Research Collection School Of Computing and Information Systems

The multi-objective vehicle routing problem with stochastic demand (MO-VRPSD) is much harder to tackle than other traditional vehicle routing problems (VRPs), due to the uncertainty in customer demands and potentially conflicted objectives. In this paper, we present an improved multi-objective learnable evolution model (IMOLEM) to solve MO-VRPSD with three objectives of travel distance, driver remuneration and number of vehicles. In our method, a machine learning algorithm, i.e., decision tree, is exploited to help find and guide the desirable direction of evolution process. To cope with the key issue of "route failure" caused due to stochastic customer demands, we propose a …

Go to article

The 4th Workshop On Heterogeneous Information Network Analysis And Applications (Hena 2021), Chuan Shi, Yuan Fang, Yanfang Ye, Jiawei Zhang Aug 2021

The 4th Workshop On Heterogeneous Information Network Analysis And Applications (Hena 2021), Chuan Shi, Yuan Fang, Yanfang Ye, Jiawei Zhang

Research Collection School Of Computing and Information Systems

The 4th Workshop on Heterogeneous Information Network Analysis and Applications (HENA 2021) is co-located with the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. The goal of this workshop is to bring together researchers and practitioners in the field and provide a forum for sharing new techniques and applications in heterogeneous information network analysis. This workshop has an exciting program that spans a number of subtopics, such as heterogeneous network embedding and graph neural networks, data mining techniques on heterogeneous information networks, and applications of heterogeneous information network analysis. The workshop program includes several invited speakers, lively discussion …

Go to article

Neural Architecture Search Of Spd Manifold Networks, R.S. Sukthanker, Zhiwu Huang, S. Kumar, E. G. Endsjo, Y. Wu, Gool L. Van Aug 2021

Neural Architecture Search Of Spd Manifold Networks, R.S. Sukthanker, Zhiwu Huang, S. Kumar, E. G. Endsjo, Y. Wu, Gool L. Van

Research Collection School Of Computing and Information Systems

In this paper, we propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks, aiming to automate the design of SPD neural architectures. To address this problem, we first introduce a geometrically rich and diverse SPD neural architecture search space for an efficient SPD cell design. Further, we model our new NAS problem with a one-shot training process of a single supernet. Based on the supernet modeling, we exploit a differentiable NAS algorithm on our relaxed continuous search space for SPD neural architecture search. Statistical evaluation of our method on drone, action, and emotion recognition …

Go to article

Independent Reinforcement Learning For Weakly Cooperative Multiagent Traffic Control Problem, Chengwei Zhang, Shan Jin, Wanli Xue, Xiaofei Xie, Shengyong Chen, Rong Chen Aug 2021

Independent Reinforcement Learning For Weakly Cooperative Multiagent Traffic Control Problem, Chengwei Zhang, Shan Jin, Wanli Xue, Xiaofei Xie, Shengyong Chen, Rong Chen

Research Collection School Of Computing and Information Systems

The adaptive traffic signal control (ATSC) problem can be modeled as a multiagent cooperative game among urban intersections, where intersections cooperate to counter the city's traffic conditions. Recently, reinforcement learning (RL) has achieved marked successes in managing sequential decision making problems, which motivates us to apply RL in the ATSC problem. One of the largest challenges of this problem is that the observation of intersection is typically partially observable, which limits the learning performance of RL algorithms. Considering the large scale of intersections in an urban traffic environment, we use independent RL to solve ATSC problem in this study. We …

Go to article

An Empirical Study Of Gui Widget Detection For Industrial Mobile Games, Jiaming Ye, Ke Chen, Xiaofei Xie, Lei Ma, Ruochen Huang, Yingfeng Chen, Yinxing Xue, Jianjun Zhao Aug 2021

An Empirical Study Of Gui Widget Detection For Industrial Mobile Games, Jiaming Ye, Ke Chen, Xiaofei Xie, Lei Ma, Ruochen Huang, Yingfeng Chen, Yinxing Xue, Jianjun Zhao

Research Collection School Of Computing and Information Systems

With the widespread adoption of smartphones in our daily life, mobile games experienced increasing demand over the past years. Meanwhile, the quality of mobile games has been continuously drawing more and more attention, which can greatly affect the player experience. For better quality assurance, general-purpose testing has been extensively studied for mobile apps. However, due to the unique characteristic of mobile games, existing mobile testing techniques may not be directly suitable and applicable. To better understand the challenges in mobile game testing, in this paper, we first initiate an early step to conduct an empirical study towards understanding the challenges …

Go to article

Explainable Deep Few-Shot Anomaly Detection With Deviation Networks, Guansong Pang, Choubo Ding, Chunhua Shen, Anton Van Den Hengel Aug 2021

Explainable Deep Few-Shot Anomaly Detection With Deviation Networks, Guansong Pang, Choubo Ding, Chunhua Shen, Anton Van Den Hengel

Research Collection School Of Computing and Information Systems

Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models. To address this problem, we introduce a novel weakly-supervised anomaly detection framework to train detection models without assuming the examples illustrating all possible classes of anomaly.Specifically, the …

Go to article

Deeprepair: Style-Guided Repairing For Deep Neural Networks In The Real-World Operational Environment, Bing Yu, Hua Qi, Guo Qing, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jianjun Zhao Aug 2021

Deeprepair: Style-Guided Repairing For Deep Neural Networks In The Real-World Operational Environment, Bing Yu, Hua Qi, Guo Qing, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Deep neural networks (DNNs) are continuously expanding their application to various domains due to their high performance. Nevertheless, a well-trained DNN after deployment could oftentimes raise errors during practical use in the operational environment due to the mismatching between distributions of the training dataset and the potential unknown noise factors in the operational environment, e.g., weather, blur, noise, etc. Hence, it poses a rather important problem for the DNNs' real-world applications: how to repair the deployed DNNs for correcting the failure samples under the deployed operational environment while not harming their capability of handling normal or clean data with limited …

Go to article

Toward Deep Supervised Anomaly Detection: Reinforcement Learning From Partially Labeled Anomaly Data, Guansong Pang, Anton Van Den Hengel, Chunhua Shen, Longbing Cao Aug 2021

Toward Deep Supervised Anomaly Detection: Reinforcement Learning From Partially Labeled Anomaly Data, Guansong Pang, Anton Van Den Hengel, Chunhua Shen, Longbing Cao

Research Collection School Of Computing and Information Systems

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies. This approach learns the known abnormality by automatically interacting with an anomalybiased simulation environment, while continuously extending the …

Go to article

Optimization Planning For 3d Convnets, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei Jul 2021

Optimization Planning For 3d Convnets, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal "path" to automate the entire training. In this paper, we decompose the path into a series of training …

Go to article

Claim: Curriculum Learning Policy For Influence Maximization In Unknown Social Networks, Dexun Li, Meghna Lowalekar, Pradeep Varakantham Jul 2021

Claim: Curriculum Learning Policy For Influence Maximization In Unknown Social Networks, Dexun Li, Meghna Lowalekar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Influence maximization is the problem of finding a small subset of nodes in a network that can maximize the diffusion of information. Recently, it has also found application in HIV prevention, substance abuse prevention, micro-finance adoption, etc., where the goal is to identify the set of peer leaders in a real-world physical social network who can disseminate information to a large group of people. Unlike online social networks, real-world networks are not completely known, and collecting information about the network is costly as it involves surveying multiple people. In this paper, we focus on this problem of network discovery for …

Go to article

Bias Field Poses A Threat To Dnn-Based X-Ray Recognition, Bingyu Tian, Qing Guo, Felix Juefei-Xu, Wen Le Chan, Yupeng Cheng, Xiaohong Li, Xiaofei Xie, Shengchao Qin Jul 2021

Bias Field Poses A Threat To Dnn-Based X-Ray Recognition, Bingyu Tian, Qing Guo, Felix Juefei-Xu, Wen Le Chan, Yupeng Cheng, Xiaohong Li, Xiaofei Xie, Shengchao Qin

Research Collection School Of Computing and Information Systems

Chest X-ray plays a key role in screening and diagnosis of many lung diseases including the COVID-19. Many works construct deep neural networks (DNNs) for chest X-ray images to realize automated and efficient diagnosis of lung diseases. However, bias field caused by the improper medical image acquisition process widely exists in the chest X-ray images while the robustness of DNNs to the bias field is rarely explored, posing a threat to the X-ray-based automated diagnosis system. In this paper, we study this problem based on the adversarial attack and propose a brand new attack, i.e., adversarial bias field attack where …

Go to article

Multi-View Collaborative Network Embedding, Sezin Kircali Ata, Yuan Fang, Min Wu, Jiaqi Shi, Chee Keong Kwoh, Xiaoli Li Jun 2021

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 …

Go to article

Adaptive Aggregation Networks For Class-Incremental Learning, Yaoyao Liu, Bernt Schiele, Qianru Sun Jun 2021

Adaptive Aggregation Networks For Class-Incremental Learning, Yaoyao Liu, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase. An inherent problem in CIL is the stability-plasticity dilemma between the learning of old and new classes, i.e., high-plasticity models easily forget old classes, but high-stability models are weak to learn new classes. We alleviate this issue by proposing a novel network architecture called Adaptive Aggregation Networks (AANets) in which we explicitly build two types of residual blocks at each residual level (taking ResNet as the baseline architecture): a stable block and a plastic block. We aggregate the output feature maps from these two …

Go to article

Contextual Transformation Networks For Online Continual Learning, Quang Pham, Chenghao Liu, Doyen Sahoo, Steve C. H. Hoi May 2021

Contextual Transformation Networks For Online Continual Learning, Quang Pham, Chenghao Liu, Doyen Sahoo, Steve C. H. Hoi

Research Collection School Of Computing and Information Systems

Continual learning methods with fixed architectures rely on a single network to learn models that can perform well on all tasks. As a result, they often only accommodate common features of those tasks but neglect each task's specific features. On the other hand, dynamic architecture methods can have a separate network for each task, but they are too expensive to train and not scalable in practice, especially in online settings. To address this problem, we propose a novel online continual learning method named ``Contextual Transformation Networks” (CTN) to efficiently model the \emph{task-specific features} while enjoying neglectable complexity overhead compared to …

Go to article

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

Ship-Gan: Generative Modeling Based Maritime Traffic Simulator, Chaithanya Shankaramurthy 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

Learning Network-Based Multi-Modal Mobile User Interface Embeddings, Gary Ang, Ee-Peng Lim Apr 2021

Learning Network-Based Multi-Modal Mobile User Interface Embeddings, Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Rich multi-modal information - text, code, images, categorical and numerical data - co-exist in the user interface (UI) design of mobile applications. UI designs are composed of UI entities supporting different functions which together enable the application. To support effective search and recommendation applications over mobile UIs, we need to be able to learn UI representations that integrate latent semantics. In this paper, we propose a novel unsupervised model - Multi-modal Attention-based Attributed Network Embedding (MAAN) model. MAAN is designed to capture both multi-modal and structural network information. Based on the encoder-decoder framework, MAAN aims to learn UI representations that …

Go to article

Practical Server-Side Wifi-Based Indoor Localization: Addressing Cardinality & Outlier Challenges For Improved Occupancy Estimation, Anuradha Ravi, Archan Misra Apr 2021

Practical Server-Side Wifi-Based Indoor Localization: Addressing Cardinality & Outlier Challenges For Improved Occupancy Estimation, Anuradha Ravi, Archan Misra

Research Collection School Of Computing and Information Systems

Server-side WiFi-based indoor localization offers a compelling approach for passive occupancy estimation (i.e., without requiring active participation by client devices, such as smartphones carried by visitors), but is known to suffer from median error of 6–8 meters. By analyzing the characteristics of an operationally-deployed, WiFi-based passive indoor location system, based on the classical RADAR algorithm, we identify and tackle 2 practical challenges for accurate individual device localization. The first challenge is the low-cardinality issue, whereby only the associated AP generates sufficiently frequent RSSI reports, causing a client to experience large localization error due to the absence of sufficient measurements from …

Go to article

Breaking Neural Reasoning Architectures With Metamorphic Relation-Based Adversarial Examples, Alvin Chan, Lei Ma, Felix Juefei-Xu, Yew-Soon Ong, Xiaofei Xie, Minhui Xue, Yang Liu Apr 2021

Breaking Neural Reasoning Architectures With Metamorphic Relation-Based Adversarial Examples, Alvin Chan, Lei Ma, Felix Juefei-Xu, Yew-Soon Ong, Xiaofei Xie, Minhui Xue, Yang Liu

Research Collection School Of Computing and Information Systems

The ability to read, reason, and infer lies at the heart of neural reasoning architectures. After all, the ability to perform logical reasoning over language remains a coveted goal of Artificial Intelligence. To this end, models such as the Turing-complete differentiable neural computer (DNC) boast of real logical reasoning capabilities, along with the ability to reason beyond simple surface-level matching. In this brief, we propose the first probe into DNC's logical reasoning capabilities with a focus on text-based question answering (QA). More concretely, we propose a conceptually simple but effective adversarial attack based on metamorphic relations. Our proposed adversarial attack …

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

Deepis: Susceptibility Estimation On Social Networks, Wenwen Xia, Yuchen Li, Jun Wu, Shenghong Li Mar 2021

Deepis: Susceptibility Estimation On Social Networks, Wenwen Xia, Yuchen Li, Jun Wu, Shenghong Li

Research Collection School Of Computing and Information Systems

Influence diffusion estimation is a crucial problem in social network analysis. Most prior works mainly focus on predicting the total influence spread, i.e., the expected number of influenced nodes given an initial set of active nodes (aka. seeds). However, accurate estimation of susceptibility, i.e., the probability of being influenced for each individual, is more appealing and valuable in real-world applications. Previous methods generally adopt Monte Carlo simulation or heuristic rules to estimate the influence, resulting in high computational cost or unsatisfactory estimation error when these methods are used to estimate susceptibility. In this work, we propose to leverage graph neural …

Go to article

Neural Architecture Search As Sparse Supernet, Y. Wu, A. Liu, Zhiwu Huang, S. Zhang, Gool L. Van Feb 2021

Neural Architecture Search As Sparse Supernet, Y. Wu, A. Liu, Zhiwu Huang, S. Zhang, Gool L. Van

Research Collection School Of Computing and Information Systems

This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse supernet, we exploit a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework. Extensive experiments on Convolutional Neural Network and Recurrent Neural Network search demonstrate that the proposed method is capable of searching for …

Go to article

Decision-Guided Weighted Automata Extraction From Recurrent Neural Networks, Xiyue Zhang, Xiaoning Du, Xiaofei Xie, Lei Ma, Yang Liu, Meng Sun Feb 2021

Decision-Guided Weighted Automata Extraction From Recurrent Neural Networks, Xiyue Zhang, Xiaoning Du, Xiaofei Xie, Lei Ma, Yang Liu, Meng Sun

Research Collection School Of Computing and Information Systems

Recurrent Neural Networks (RNNs) have demonstrated their effectiveness in learning and processing sequential data (e.g., speech and natural language). However, due to the black-box nature of neural networks, understanding the decision logic of RNNs is quite challenging. Some recent progress has been made to approximate the behavior of an RNN by weighted automata. They provide better interpretability, but still suffer from poor scalability. In this paper, we propose a novel approach to extracting weighted automata with the guidance of a target RNN’s decision and context information. In particular, we identify the patterns of RNN’s step-wise predictive decisions to instruct the …

Go to article

Learning To Pre-Train Graph Neural Networks, Yuanfu Lu, Xunqiang Jiang, Yuan Fang, Chuan Shi Feb 2021

Learning To Pre-Train Graph Neural Networks, Yuanfu Lu, Xunqiang Jiang, Yuan Fang, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph neural networks (GNNs) have become the de facto standard for representation learning on graphs, which derive effective node representations by recursively aggregating information from graph neighborhoods. While GNNs can be trained from scratch, pre-training GNNs to learn transferable knowledge for downstream tasks has recently been demonstrated to improve the state of the art. However, conventional GNN pre-training methods follow a two-step paradigm: 1) pre-training on abundant unlabeled data and 2) fine-tuning on downstream labeled data, between which there exists a significant gap due to the divergence of optimization objectives in the two steps. In this paper, we conduct an …

Go to article

Treecaps: Tree-Based Capsule Networks For Source Code Processing, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang Feb 2021

Treecaps: Tree-Based Capsule Networks For Source Code Processing, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., Abstract Syntax Trees) and/or semantic information (e.g., Dependency Graphs). While graphs may be better at capturing various viewpoints of code semantics than trees, constructing graph inputs from code need static code semantic analysis that may not be accurate and introduces noise during learning. On the other hand, syntax trees are precisely defined according to the language grammar and easier to construct and process than graphs. We propose a new tree-based learning technique, named TreeCaps, by fusing capsule networks with tree-based convolutional neural networks, to …

Go to article

Scalable Verification Of Quantized Neural Networks, Thomas A. Henzinger, Mathias Lechner, Dorde Zikelic Feb 2021

Scalable Verification Of Quantized Neural Networks, Thomas A. Henzinger, Mathias Lechner, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Formal verification of neural networks is an active topic of research, and recent advances have significantly increased the size of the networks that verification tools can handle. However, most methods are designed for verification of an idealized model of the actual network which works over real arithmetic and ignores rounding imprecisions. This idealization is in stark contrast to network quantization, which is a technique that trades numerical precision for computational efficiency and is, therefore, often applied in practice. Neglecting rounding errors of such low-bit quantized neural networks has been shown to lead to wrong conclusions about the network’s correctness. Thus, …

Go to article

Unsupervised Representation Learning By Predicting Random Distances, Hu Wang, Guansong Pang, Chunhua Shen, Congbo Ma Jan 2021

Unsupervised Representation Learning By Predicting Random Distances, Hu Wang, Guansong Pang, Chunhua Shen, Congbo Ma

Research Collection School Of Computing and Information Systems

Deep neural networks have gained great success in a broad range of tasks due to its remarkable capability to learn semantically rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption in unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications to critical domains where obtaining massive labelled data is prohibitively expensive. To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected …

Go to article

Technical Q8a Site Answer Recommendation Via Question Boosting, Zhipeng Gao, Xin Xia, David Lo, John Grundy Jan 2021

Technical Q8a Site Answer Recommendation Via Question Boosting, Zhipeng Gao, Xin Xia, David Lo, John Grundy

Research Collection School Of Computing and Information Systems

Software developers have heavily used online question and answer platforms to seek help to solve their technical problems. However, a major problem with these technical Q&A sites is "answer hungriness" i.e., a large number of questions remain unanswered or unresolved, and users have to wait for a long time or painstakingly go through the provided answers with various levels of quality. To alleviate this time-consuming problem, we propose a novel DeepAns neural network-based approach to identify the most relevant answer among a set of answer candidates. Our approach follows a three-stage process: question boosting, label establishment, and answer recommendation. Given …

Go to article

Theory-Inspired Path-Regularized Differential Network Architecture Search, Pan Zhou, Caiming Xiong, Richard Socher, Steven C. H. Hoi Dec 2020

Theory-Inspired Path-Regularized Differential Network Architecture Search, Pan Zhou, Caiming Xiong, Richard Socher, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g. convolution, skip connection and zero operation, to the network optimization. We prove that the architectures with more skip connections can converge faster than the other candidates, and thus are selected by DARTS. This result, for the first time, theoretically and explicitly …

Go to article

Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam In Deep Learning, Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven C. H. Hoi, Weinan E Dec 2020

Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam In Deep Learning, Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven C. H. Hoi, Weinan E

Research Collection School Of Computing and Information Systems

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing their local convergence behaviors. Specifically, we observe the heavy tails of gradient noise in these algorithms. This motivates us to analyze these algorithms through their Lévy-driven stochastic differential equations (SDEs) because of the similar convergence behaviors of an algorithm and its SDE. Then we establish the escaping time of these SDEs from a local basin. The result shows that (1) the escaping time of both SGD …

Go to article

Watch Out! Motion Is Blurring The Vision Of Your Deep Neural Networks, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, Yang Liu Dec 2020

Watch Out! Motion Is Blurring The Vision Of Your Deep Neural Networks, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, Yang Liu

Research Collection School Of Computing and Information Systems

The state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples with additive random noise-like perturbations. While such examples are hardly found in the physical world, the image blurring effect caused by object motion, on the other hand, commonly occurs in practice, making the study of which greatly important especially for the widely adopted real-time image processing tasks (e.g., object detection, tracking). In this paper, we initiate the first step to comprehensively investigate the potential hazards of blur effect for DNN, caused by object motion. We propose a novel adversarial attack method that can generate visually natural motion-blurred adversarial examples, …

Go to article

First Prev Next Last