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

Databases and Information Systems Commons™

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

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year

Articles 1051 - 1080 of 3441

Full-Text Articles in Databases and Information Systems

Coherence And Identity Learning For Arbitrary-Length Face Video Generation, Shuquan Ye, Chu Han, Jiaying Lin, Guoqiang Han, Shengfeng He Jan 2021

Coherence And Identity Learning For Arbitrary-Length Face Video Generation, Shuquan Ye, Chu Han, Jiaying Lin, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

Face synthesis is an interesting yet challenging task in computer vision. It is even much harder to generate a portrait video than a single image. In this paper, we propose a novel video generation framework for synthesizing arbitrary-length face videos without any face exemplar or landmark. To overcome the synthesis ambiguity of face video, we propose a divide-and-conquer strategy to separately address the video face synthesis problem from two aspects, face identity synthesis and rearrangement. To this end, we design a cascaded network which contains three components, Identity-aware GAN (IA-GAN), Face Coherence Network, and Interpolation Network. IA-GAN is proposed to …

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

Deep Unsupervised Anomaly Detection, Tangqing Li, Zheng Wang, Siying Liu, Wen-Yan Lin Jan 2021

Deep Unsupervised Anomaly Detection, Tangqing Li, Zheng Wang, Siying Liu, Wen-Yan Lin

Research Collection School Of Computing and Information Systems

This paper proposes a novel method to detect anomalies in large datasets under a fully unsupervised setting. The key idea behind our algorithm is to learn the representation underlying normal data. To this end, we leverage the latest clustering technique suitable for handling high dimensional data. This hypothesis provides a reliable starting point for normal data selection. We train an autoencoder from the normal data subset, and iterate between hypothesizing normal candidate subset based on clustering and representation learning. The reconstruction error from the learned autoencoder serves as a scoring function to assess the normality of the data. Experimental results …

Go to article

Facial Emotion Recognition With Noisy Multi-Task Annotations, S. Zhang, Zhiwu Huang, D.P. Paudel, Gool L. Van Jan 2021

Facial Emotion Recognition With Noisy Multi-Task Annotations, S. Zhang, Zhiwu Huang, D.P. Paudel, Gool L. Van

Research Collection School Of Computing and Information Systems

Human emotions can be inferred from facial expressions. However, the annotations of facial expressions are often highly noisy in common emotion coding models, including categorical and dimensional ones. To reduce human labelling effort on multi-task labels, we introduce a new problem of facial emotion recognition with noisy multitask annotations. For this new problem, we suggest a formulation from the point of joint distribution match view, which aims at learning more reliable correlations among raw facial images and multi-task labels, resulting in the reduction of noise influence. In our formulation, we exploit a new method to enable the emotion prediction and …

Go to article

Why My Code Summarization Model Does Not Work: Code Comment Improvement With Category Prediction, Qiuyuan Chen, Xin Xia, Han Hu, David Lo, Shanping Li Jan 2021

Why My Code Summarization Model Does Not Work: Code Comment Improvement With Category Prediction, Qiuyuan Chen, Xin Xia, Han Hu, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

Code summarization aims at generating a code comment given a block of source code and it is normally performed by training machine learning algorithms on existing code block-comment pairs. Code comments in practice have different intentions. For example, some code comments might explain how the methods work, while others explain why some methods are written. Previous works have shown that a relationship exists between a code block and the category of a comment associated with it. In this article, we aim to investigate to which extent we can exploit this relationship to improve code summarization performance. We first classify comments …

Go to article

Context-Aware Retrieval-Based Deep Commit Message Generation, Haoye Wang, Xin Xia, David Lo, Qiang He, Xinyu Wang, John Grundy Jan 2021

Context-Aware Retrieval-Based Deep Commit Message Generation, Haoye Wang, Xin Xia, David Lo, Qiang He, Xinyu Wang, John Grundy

Research Collection School Of Computing and Information Systems

Commit messages recorded in version control systems contain valuable information for software development, maintenance, and comprehension. Unfortunately, developers often commit code with empty or poor quality commit messages. To address this issue, several studies have proposed approaches to generate commit messages from commit diffs. Recent studies make use of neural machine translation algorithms to try and translate git diffs into commit messages and have achieved some promising results. However, these learning-based methods tend to generate high-frequency words but ignore low-frequency ones. In addition, they suffer from exposure bias issues, which leads to a gap between training phase and testing phase. …

Go to article

Sustainability Of Rewards-Based Crowdfunding: A Quasi-Experimental Analysis Of Funding Targets And Backer Satisfaction, Michael Wessel, Rob Gleasure, Robert John Kauffman Jan 2021

Sustainability Of Rewards-Based Crowdfunding: A Quasi-Experimental Analysis Of Funding Targets And Backer Satisfaction, Michael Wessel, Rob Gleasure, Robert John Kauffman

Research Collection School Of Computing and Information Systems

Rewards-based crowdfunding presents an information asymmetry for participants due to the funding mechanism used. Campaign-backers trust creators to complete projects and deliver rewards as outlined prior to the fundraising process, but creators may discover better opportunities as they progress with a project. Despite this, the all-or-nothing (AON) mechanism on crowdfunding platforms incentivizes creators to set meager funding-targets that are easier to achieve but may offer limited slack when creators wish to simultaneously pursue emerging opportunities later in the project. We explore the related issues of how funding targets seem to be selected by the creators, and how dissatisfaction with the …

Go to article

Three Stages Of Consumers’ Multi-Stage Dichotomic Switching Process: Pre-Switch, Switch, And Post-Switch, Jussi Nykanen, Virpi K. Tuunainen, Tuure Tuunanen, Fiona Fui-Hoon Nah Jan 2021

Three Stages Of Consumers’ Multi-Stage Dichotomic Switching Process: Pre-Switch, Switch, And Post-Switch, Jussi Nykanen, Virpi K. Tuunainen, Tuure Tuunanen, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

This research examines why and how consumers switch their mobile phones. We propose a framework that is grounded on decision-making and motivational theories and draws on the findings from a multinational qualitative survey on consumers’ mobile phone switching process. We show that consumers’ pre-switching decisions are affected by push and pull factors, their mobile phone selections are based on utilitarian or hedonic values, and their justifications for switching are based on cognition or affect. Furthermore, we identify two archetypical routes (i.e., cognitive and affective routes) and three conjoint routes that explain the dichotomic switching processes in pre-switch, switch, and post-switch …

Go to article

Chronic Customers Or Increased Awareness? The Dynamics Of Social Media Customer Service, Shujing Sun, Yang Gao, Huaxia Rui Jan 2021

Chronic Customers Or Increased Awareness? The Dynamics Of Social Media Customer Service, Shujing Sun, Yang Gao, Huaxia Rui

Research Collection School Of Computing and Information Systems

Despite that social media has become a promising alternative to traditional call centers, managers hesitate to fully harness its power because they worry that active service intervention may encourage excessive use of the channel by disgruntled customers. This paper sheds light on such a concern by examining the dynamics between brand-level customer complaints and service interventions on social media. Using details of customer-brand interactions of 40 airlines on Twitter, we find that more service interventions indeed cause more customer complaints, accounting for the online customer population and service quality. However, the increased complaints are primarily driven by the awareness enhancement …

Go to article

Adversarial Specification Mining, Hong Jin Kang, David Lo Jan 2021

Adversarial Specification Mining, Hong Jin Kang, David Lo

Research Collection School Of Computing and Information Systems

There have been numerous studies on mining temporal specifications from execution traces. These approaches learn finite-state automata (FSA) from execution traces when running tests. To learn accurate specifications of a software system, many tests are required. Existing approaches generalize from a limited number of traces or use simple test generation strategies. Unfortunately, these strategies may not exercise uncommon usage patterns of a software system. To address this problem, we propose a new approach, adversarial specification mining, and develop a prototype, DICE (Diversity through Counter-Examples). DICE has two components: DICE-Tester and DICE-Miner. After mining Linear Temporal Logic specifications from an input …

Go to article

Do Blockchain And Iot Architecture Create Informedness To Support Provenance Tracking In The Product Lifecycle?, Somnath Mazumdar, Thomas Jensen, Raghava Rao Mukkamala, Robert John Kauffman, Jan Damsgaard Jan 2021

Do Blockchain And Iot Architecture Create Informedness To Support Provenance Tracking In The Product Lifecycle?, Somnath Mazumdar, Thomas Jensen, Raghava Rao Mukkamala, Robert John Kauffman, Jan Damsgaard

Research Collection School Of Computing and Information Systems

Consumers often lack information about the origin and provenance of the products they buy. They may ask: Is a food product truly organic? Or, what is the origin of the gemstone in the ring I purchased? They also may have sustainability concerns about the footprint of a product at the end of its life. Producers and sellers, meanwhile, wish to know how longitudinal tracking of the provenance of products and their components can boost their sales prices and after-market value, and re- veal new business opportunities. We focus on how the product lifecycle (PLC) can be leveraged to track information …

Go to article

Smart Contracts: Will Fintech Be The Catalyst For The Next Global Financial Crisis?, Randall Duran, Paul Griffin Jan 2021

Smart Contracts: Will Fintech Be The Catalyst For The Next Global Financial Crisis?, Randall Duran, Paul Griffin

Research Collection School Of Computing and Information Systems

Purpose: This paper aims to examine the risks associated with smart contracts, a disruptive financial technology (FinTech) innovation, and assesses how in the future they could threaten the integrity of the global financial system. Design/methodology/approach: A qualitative approach is used to identify risk factors related to the use of new financial innovations, by examining how over-the-counter (OTC) derivatives contributed to the Global Financial Crisis (GFC) which occurred during 2007 and 2008. Based on this analysis, the potential for similar concerns with smart contracts are evaluated, drawing on the failure of The DAO on the Ethereum blockchain, which involved the loss …

Go to article

Learning Adl Daily Routines With Spatiotemporal Neural Networks, Shan Gao, Ah-Hwee Tan, Rossi Setchi Jan 2021

Learning Adl Daily Routines With Spatiotemporal Neural Networks, Shan Gao, Ah-Hwee Tan, Rossi Setchi

Research Collection School Of Computing and Information Systems

The activities of daily living (ADLs) refer to the activities performed by individuals on a daily basis and are the indicators of a person’s habits, lifestyle, and wellbeing. Learning an individual’s ADL daily routines has significant value in the healthcare domain. Specifically, ADL recognition and inter-ADL pattern learning problems have been studied extensively in the past couple of decades. However, discovering the patterns performed in a day and clustering them into ADL daily routines has been a relatively unexplored research area. In this paper, a self-organizing neural network model, called the Spatiotemporal ADL Adaptive Resonance Theory (STADLART), is proposed for …

Go to article

Attribute-Aware Pedestrian Detection In A Crowd, Jialiang Zhang, Lixiang Lin, Jianke Zhu, Yang Li, Yun-Chen Chen, Yao Hu, Steven C. H. Hoi Jan 2021

Attribute-Aware Pedestrian Detection In A Crowd, Jialiang Zhang, Lixiang Lin, Jianke Zhu, Yang Li, Yun-Chen Chen, Yao Hu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep learning frameworks from the generic object detectors, pedestrian detection is still a very challenging task due to heavy occlusions, and highly crowded group. Generally, the conventional detectors are unable to differentiate individuals from each other effectively under such a dense environment. To tackle this critical problem, we propose an attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion. Besides the typical semantic features, center position, target's scale, …

Go to article

Jointly Optimizing Sensing Pipelines For Multimodal Mixed Reality Interaction, Ramesh Darshana Rathnayake Kanatta Gamage, Ashen De Silva, Dasun Puwakdandawa, Lakmal Meegahapola, Archan Misra, Indika Perera Dec 2020

Jointly Optimizing Sensing Pipelines For Multimodal Mixed Reality Interaction, Ramesh Darshana Rathnayake Kanatta Gamage, Ashen De Silva, Dasun Puwakdandawa, Lakmal Meegahapola, Archan Misra, Indika Perera

Research Collection School Of Computing and Information Systems

Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate comprehension of such multimodal instructions (MMI), on resource-constrained wearable devices, remains an open challenge, especially as the state-of-the-art comprehension techniques for each individual modality increasingly utilize complex Deep Neural Network models. We demonstrate the possibility of overcoming the core limitation of latency–vs.–accuracy tradeoff by exploiting cross-modal dependencies–i.e., by compensating for the inferior performance of one model with an increased accuracy of more complex model of a different modality. We present a …

Go to article

Co-Embedding Attributed Networks With External Knowledge, Pei-Chi Lo, Ee Peng Lim Dec 2020

Co-Embedding Attributed Networks With External Knowledge, Pei-Chi Lo, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Attributed network embedding aims to learn representations of nodes and their attributes in a low-dimensional space that preserves their semantics. The existing embedding models, however, consider node connectivity and node attributes only while ignoring external knowledge that can enhance node representations for downstream applications. In this paper, we propose a set of new VAE-based embedding models called External Knowledge-Aware Co-Embedding Attributed Network (ECAN) Embeddings to incorporate associations among attributes from relevant external knowledge. Such external knowledge can be extracted from text corpus and knowledge graphs. We use multi-VAE structures to model the attribute associations. To cope with joint encoding of …

Go to article

A Hybrid Approach For Detecting Prerequisite Relations In Multi-Modal Food Recipes, Liangming Pan, Jingjing Chen, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Tat-Seng Chua Dec 2020

A Hybrid Approach For Detecting Prerequisite Relations In Multi-Modal Food Recipes, Liangming Pan, Jingjing Chen, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Modeling the structure of culinary recipes is the core of recipe representation learning. Current approaches mostly focus on extracting the workflow graph from recipes based on text descriptions. Process images, which constitute an important part of cooking recipes, has rarely been investigated in recipe structure modeling. We study this recipe structure problem from a multi-modal learning perspective, by proposing a prerequisite tree to represent recipes with cooking images at a step-level granularity. We propose a simple-yet-effective two-stage framework to automatically construct the prerequisite tree for a recipe by (1) utilizing a trained classifier to detect pairwise prerequisite relations that fuses …

Go to article

Security Analysis Of Permission Re-Delegation Vulnerabilities In Android Apps, Biniam Fisseha Demissie, Mariano Ceccato, Lwin Khin Shar Dec 2020

Security Analysis Of Permission Re-Delegation Vulnerabilities In Android Apps, Biniam Fisseha Demissie, Mariano Ceccato, Lwin Khin Shar

Research Collection School Of Computing and Information Systems

The Android platform facilitates reuse of app functionalities by allowing an app to request an action from another app through inter-process communication mechanism. This feature is one of the reasons for the popularity of Android, but it also poses security risks to the end users because malicious, unprivileged apps could exploit this feature to make privileged apps perform privileged actions on behalf of them. In this paper, we investigate the hybrid use of program analysis, genetic algorithm based test generation, natural language processing, machine learning techniques for precise detection of permission re-delegation vulnerabilities in Android apps. Our approach first groups …

Go to article

Interventional Few-Shot Learning, Zhongqi Yue, Zhang Hanwang, Qianru Sun, Xian-Sheng Hua Dec 2020

Interventional Few-Shot Learning, Zhongqi Yue, Zhang Hanwang, Qianru Sun, Xian-Sheng Hua

Research Collection School Of Computing and Information Systems

We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution …

Go to article

Heterogeneous Univariate Outlier Ensembles In Multidimensional Data, Guansong Pang, Longbing Cao Dec 2020

Heterogeneous Univariate Outlier Ensembles In Multidimensional Data, Guansong Pang, Longbing Cao

Research Collection School Of Computing and Information Systems

In outlier detection, recent major research has shifted from developing univariate methods to multivariate methods due to the rapid growth of multidimensional data. However, one typical issue of this paradigm shift is that many multidimensional data often mainly contains univariate outliers, in which many features are actually irrelevant. In such cases, multivariate methods are ineffective in identifying such outliers due to the potential biases and the curse of dimensionality brought by irrelevant features. Those univariate outliers might be well detected by applying univariate outlier detectors in individually relevant features. However, it is very challenging to choose a right univariate detector …

Go to article

Design Of A Two-Echelon Freight Distribution System In An Urban Area Considering Third-Party Logistics And Loading-Unloading Zones, Vincent F. Yu, Winarno, Shih-Wei Lin, Aldy Gunawan Dec 2020

Design Of A Two-Echelon Freight Distribution System In An Urban Area Considering Third-Party Logistics And Loading-Unloading Zones, Vincent F. Yu, Winarno, Shih-Wei Lin, Aldy Gunawan

Research Collection School Of Computing and Information Systems

This research examines the problem of designing a two-echelon freight distribution system in a dense urban area that considers third-party logistics (TPL) and loading–unloading zones (LUZs). The proposed system takes advantage of outsourcing the last mile deliveries to a TPL provider and utilizing LUZs as temporary intermediate facilities instead of using permanent intermediate facilities to consolidate freight. A mathematical model and a simulated annealing (SA) algorithm are developed to solve the problem. The efficiency and effectiveness of the proposed SA heuristic are verified by testing it on existing benchmark instances. Computational results show that the performance of the proposed SA …

Go to article

Sharper Generalisation Bounds For Pairwise Learning, Yunwen Lei, Antoine Ledent, Marius Kloft Dec 2020

Sharper Generalisation Bounds For Pairwise Learning, Yunwen Lei, Antoine Ledent, Marius Kloft

Research Collection School Of Computing and Information Systems

Pairwise learning refers to learning tasks with loss functions depending on a pair of training examples, which includes ranking and metric learning as specific examples. Recently, there has been an increasing amount of attention on the generalization analysis of pairwise learning to understand its practical behavior. However, the existing stability analysis provides suboptimal high-probability generalization bounds. In this paper, we provide a refined stability analysis by developing generalization bounds which can be √nn-times faster than the existing results, where nn is the sample size. This implies excess risk bounds of the order O(n−1/2) (up to a logarithmic factor) for both …

Go to article

Nearest Centroid: A Bridge Between Statistics And Machine Learning, Manoj Thulasidas Dec 2020

Nearest Centroid: A Bridge Between Statistics And Machine Learning, Manoj Thulasidas

Research Collection School Of Computing and Information Systems

In order to guide our students of machine learning in their statistical thinking, we need conceptually simple and mathematically defensible algorithms. In this paper, we present the Nearest Centroid algorithm (NC) algorithm as a pedagogical tool, combining the key concepts behind two foundational algorithms: K-Means clustering and K Nearest Neighbors (k- NN). In NC, we use the centroid (as defined in the K-Means algorithm) of the observations belonging to each class in our training data set and its distance from a new observation (similar to k-NN) for class prediction. Using this obvious extension, we will illustrate how the concepts of …

Go to article

Secure Answer Book And Automatic Grading, Manoj Thulasidas Dec 2020

Secure Answer Book And Automatic Grading, Manoj Thulasidas

Research Collection School Of Computing and Information Systems

In response to the growing need to perform assessments online, we have developed a secure answer book, as well as a tool for automatically grading it for our course on spread- sheet modeling. We applied these techniques to a cohort of about 160 students who took the course last term. In this paper, we describe the design, implementation and the techniques employed to enhance both the security of the answer book and the ease, accuracy and consistency of grading. In addition, we summarize the experience and takeaways, both from the instructor and the student perspectives. Although the answer book and …

Go to article

Causal Intervention For Weakly-Supervised Semantic Segmentation, Zhang Dong, Hanwang Zhang, Jinhui Tang, Xian-Sheng Hua, Qianru Sun Dec 2020

Causal Intervention For Weakly-Supervised Semantic Segmentation, Zhang Dong, Hanwang Zhang, Jinhui Tang, Xian-Sheng Hua, Qianru Sun

Research Collection School Of Computing and Information Systems

We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels --- the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of "horse'' and "person'' may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and …

Go to article

Debunking Rumors On Twitter With Tree Transformer, Jing Ma, Wei Gao Dec 2020

Debunking Rumors On Twitter With Tree Transformer, Jing Ma, Wei Gao

Research Collection School Of Computing and Information Systems

Rumors are manufactured with no respect for accuracy, but can circulate quickly and widely by "word-of-post" through social media conversations. Conversation tree encodes important information indicative of the credibility of rumor. Existing conversation-based techniques for rumor detection either just strictly follow tree edges or treat all the posts fully-connected during feature learning. In this paper, we propose a novel detection model based on tree transformer to better utilize user interactions in the dialogue where post-level self-attention plays the key role for aggregating the intra-/inter-subtree stances. Experimental results on the TWITTER and PHEME datasets show that the proposed approach consistently improves …

Go to article

A Bert-Based Dual Embedding Model For Chinese Idiom Prediction, Minghuan Tan, Jing Jiang Dec 2020

A Bert-Based Dual Embedding Model For Chinese Idiom Prediction, Minghuan Tan, Jing Jiang

Research Collection School Of Computing and Information Systems

Chinese idioms are special fixed phrases usually derived from ancient stories, whose meanings are oftentimes highly idiomatic and non-compositional. The Chinese idiom prediction task is to select the correct idiom from a set of candidate idioms given a context with a blank. We propose a BERT-based dual embedding model to encode the contextual words as well as to learn dual embeddings of the idioms. Specifically, we first match the embedding of each candidate idiom with the hidden representation corresponding to the blank in the context. We then match the embedding of each candidate idiom with the hidden representations of all …

Go to article

Learning To Dispatch For Job Shop Scheduling Via Deep Reinforcement Learning, Cong Zhang, Wen Song, Zhiguang Cao, Jie Zhang, Puay Siew Tan, Xu Chi Dec 2020

Learning To Dispatch For Job Shop Scheduling Via Deep Reinforcement Learning, Cong Zhang, Wen Song, Zhiguang Cao, Jie Zhang, Puay Siew Tan, Xu Chi

Research Collection School Of Computing and Information Systems

Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP). However, the design of effective PDRs is a tedious task, requiring a myriad of specialized knowledge and often delivering limited performance. In this paper, we propose to automatically learn PDRs via an end-to-end deep reinforcement learning agent. We exploit the disjunctive graph representation of JSSP, and propose a Graph Neural Network based scheme to embed the states encountered during solving. The resulting policy network is size-agnostic, effectively enabling generalization on large-scale instances. Experiments show that the agent can learn high-quality PDRs from scratch with elementary raw …

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

Blockchain-Based Public Auditing And Secure Deduplication With Fair Arbitration, Haoran Yuan, Xiaofeng Chen, Jianfeng Wang, Jiaming Yuan, Hongyang Yan, Willy Susilo Dec 2020

Blockchain-Based Public Auditing And Secure Deduplication With Fair Arbitration, Haoran Yuan, Xiaofeng Chen, Jianfeng Wang, Jiaming Yuan, Hongyang Yan, Willy Susilo

Research Collection School Of Computing and Information Systems

Data auditing enables data owners to verify the integrity of their sensitive data stored at an untrusted cloud without retrieving them. This feature has been widely adopted by commercial cloud storage. However, the existing approaches still have some drawbacks. On the one hand, the existing schemes have a defect of fair arbitration, i.e., existing auditing schemes lack an effective method to punish the malicious cloud service provider (CSP) and compensate users whose data integrity is destroyed. On the other hand, a CSP may store redundant and repetitive data. These redundant data inevitably increase management overhead and computational cost during the …

Go to article

First Prev Next Last