Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (8556)
- Computer Sciences (8539)
- Databases and Information Systems (3453)
- Software Engineering (2164)
- Artificial Intelligence and Robotics (1697)
-
- Information Security (1071)
- Numerical Analysis and Scientific Computing (1025)
- Graphics and Human Computer Interfaces (933)
- Engineering (888)
- Social and Behavioral Sciences (681)
- Business (642)
- Theory and Algorithms (493)
- Computer Engineering (451)
- Operations Research, Systems Engineering and Industrial Engineering (410)
- Programming Languages and Compilers (379)
- OS and Networks (324)
- Communication (297)
- Social Media (240)
- Public Affairs, Public Policy and Public Administration (217)
- Transportation (195)
- Medicine and Health Sciences (181)
- Education (170)
- Management Information Systems (167)
- Data Storage Systems (162)
- E-Commerce (148)
- International and Area Studies (111)
- Asian Studies (110)
- Health Information Technology (110)
- Digital Communications and Networking (104)
- Technology and Innovation (104)
- Keyword
-
- Deep learning (123)
- Machine learning (122)
- Social media (74)
- Artificial intelligence (72)
- Reinforcement learning (69)
-
- Privacy (65)
- Data mining (64)
- Cloud computing (58)
- Deep Learning (56)
- Empirical study (54)
- Optimization (54)
- Security (54)
- Visualization (51)
- Task analysis (50)
- Online learning (49)
- Software engineering (49)
- Training (49)
- Neural networks (48)
- Singapore (48)
- Anomaly detection (47)
- Feature extraction (46)
- Twitter (46)
- Large Language Models (45)
- Blockchain (44)
- Collaboration (44)
- Semantics (43)
- Access control (41)
- Algorithms (40)
- Android (39)
- Natural language processing (39)
- Publication Year
- File Type
Articles 2551 - 2580 of 8597
Full-Text Articles in Entire DC Network
A Fine-Grained Attribute Based Data Retrieval With Proxy Re-Encryption Scheme For Data Outsourcing Systems, Hanshu Hong, Ximeng Liu, Zhixin Sun
A Fine-Grained Attribute Based Data Retrieval With Proxy Re-Encryption Scheme For Data Outsourcing Systems, Hanshu Hong, Ximeng Liu, Zhixin Sun
Research Collection School Of Computing and Information Systems
Attribute based encryption is suitable for data protection in data outsourcing systems such as cloud computing. However, the leveraging of encryption technique may retrain some routine operations over the encrypted data, particularly in the field of data retrieval. This paper presents an attribute based date retrieval with proxy re-encryption (ABDR-PRE) to provide both fine-grained access control and retrieval over the ciphertexts. The proposed scheme achieves fine-grained data access management by adopting KP-ABE mechanism, a delegator can generate the re-encryption key and search indexes for the ciphertexts to be shared over the target delegatee’s attributes. Throughout the process of data sharing, …
Hierarchical Control Of Multi-Agent Reinforcement Learning Team In Real-Time Strategy (Rts) Games, Weigui Jair Zhou, Budhitama Subagdja, Ah-Hwee Tan, Darren Wee Sze Ong
Hierarchical Control Of Multi-Agent Reinforcement Learning Team In Real-Time Strategy (Rts) Games, Weigui Jair Zhou, Budhitama Subagdja, Ah-Hwee Tan, Darren Wee Sze Ong
Research Collection School Of Computing and Information Systems
Coordinated control of multi-agent teams is an important task in many real-time strategy (RTS) games. In most prior work, micromanagement is the commonly used strategy whereby individual agents operate independently and make their own combat decisions. On the other extreme, some employ a macromanagement strategy whereby all agents are controlled by a single decision model. In this paper, we propose a hierarchical command and control architecture, consisting of a single high-level and multiple low-level reinforcement learning agents operating in a dynamic environment. This hierarchical model enables the low-level unit agents to make individual decisions while taking commands from the high-level …
Graph Learning Assisted Multi-Objective Integer Programming, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Abhishek Gupta, Mingyan Simon Lin
Graph Learning Assisted Multi-Objective Integer Programming, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Abhishek Gupta, Mingyan Simon Lin
Research Collection School Of Computing and Information Systems
Objective-space decomposition algorithms (ODAs) are widely studied for solvingmulti-objective integer programs. However, they often encounter difficulties inhandling scalarized problems, which could cause infeasibility or repetitive nondominatedpoints and thus induce redundant runtime. To mitigate the issue, we presenta graph neural network (GNN) based method to learn the reduction rule in the ODA.We formulate the algorithmic procedure of generic ODAs as a Markov decisionprocess, and parameterize the policy (reduction rule) with a novel two-stage GNNto fuse information from variables, constraints and especially objectives for betterstate representation. We train our model with imitation learning and deploy it ona state-of-the-art ODA. Results show that …
Concise Mercurial Subvector Commitments: Definitions And Constructions, Yannan Li, Willy Susilo, Guomin Yang, Tran Viet Xuan Phuong, Yong Yu, Dongxi Liu
Concise Mercurial Subvector Commitments: Definitions And Constructions, Yannan Li, Willy Susilo, Guomin Yang, Tran Viet Xuan Phuong, Yong Yu, Dongxi Liu
Research Collection School Of Computing and Information Systems
Vector commitment and its variants have attracted a lot of attention recently as they have been exposed to a wide range of applications in blockchain. Two special extensions of vector commitments, namely subvector commitments and mercurial commitments, have been proposed with attractive features that are desirable in many applications. Nevertheless, to the best of our knowledge, a single construction satisfying all those attractive features is still missing. In this work, we analyze those important properties and propose a new primitive called mercurial subvector commitments, which are efficiently updatable, mercurial hiding, position binding, and aggregatable. We formalize the system model and …
Broadcast Authenticated Encryption With Keyword Search, Xueqiao Liu, Kai He, Guomin Yang, Willy Susilo, Joseph Tonien, Qiong Huang
Broadcast Authenticated Encryption With Keyword Search, Xueqiao Liu, Kai He, Guomin Yang, Willy Susilo, Joseph Tonien, Qiong Huang
Research Collection School Of Computing and Information Systems
The emergence of public-key encryption with keyword search (PEKS) has provided an elegant approach to enable keyword search over encrypted content. Due to its high computational complexity proportional to the number of intended receivers, the trivial way of deploying PEKS for data sharing with multiple receivers is impractical, which motivates the development of a new PEKS framework for broadcast mode. However, existing works suffer from either the vulnerability to keyword guessing attacks (KGA) or high computation and communication complexity. In this work, a new primitive for keyword search in broadcast mode, named broadcast authenticated encryption with keyword search (BAEKS), is …
Microservices Orchestration Vs. Choreography: A Decision Framework, Alan @ Ali Madjelisi Megargel, Christopher M. Poskitt, Shankararaman, Venky
Microservices Orchestration Vs. Choreography: A Decision Framework, Alan @ Ali Madjelisi Megargel, Christopher M. Poskitt, Shankararaman, Venky
Research Collection School Of Computing and Information Systems
Microservices-based applications consist of loosely coupled, independently deployable services that encapsulate units of functionality. To implement larger application processes, these microservices must communicate and collaborate. Typically, this follows one of two patterns: (1) choreography, in which communication is done via asynchronous message-passing; or (2) orchestration, in which a controller is used to synchronously manage the process flow. Choosing the right pattern requires the resolution of some trade-offs concerning coupling, chattiness, visibility, and design. To address this problem, we propose a decision framework for microservices collaboration patterns that helps solution architects to crystallize their goals, compare the key factors, and then …
Degree Doesn't Matter: Identifying The Drivers Of Interaction In Software Development Ecosystem, Amrita Bhattacharjee, Subhajit Datta, Subhashis Majumder
Degree Doesn't Matter: Identifying The Drivers Of Interaction In Software Development Ecosystem, Amrita Bhattacharjee, Subhajit Datta, Subhashis Majumder
Research Collection School Of Computing and Information Systems
Large scale software development ecosystems represent one of the most complex human enterprises. In such settings, developers are embedded in a web of shared concerns, responsibilities, and objectives at individual and collective levels. A deep understanding of the factors that influence developers to connect with one another is crucial in appreciating the challenges of such ecosystems as well as formulating strategies to overcome those challenges. We use real world data from multiple software development ecosystems to construct developer interaction networks and examine the mechanisms of such network formation using statistical models to identify developer attributes that have maximal influence on …
Channel Integration Services In Online Healthcare Communities, Anqi Zhao, Qian Tang
Channel Integration Services In Online Healthcare Communities, Anqi Zhao, Qian Tang
Research Collection School Of Computing and Information Systems
In online healthcare communities, channel integration services have become the bridge between online and offline channels, enabling patients to easily migrate across channels. Different from pure online services, online-to-offline (On2Off) and offline-to-online (Off2On) channel integration services involve both channels. This study examines the interrelationships between pure online services and channel integration services. Using a panel dataset composed of data from an online healthcare community, we find that pure online services decrease patients’ demand for On2Off integration services but increase their use of Off2On integration services. Our findings suggest that providing healthcare services online can reduce online patients’ needs to visit …
Solving The Vehicle Routing Problem With Simultaneous Pickup And Delivery And Occasional Drivers By Simulated Annealing, Vincent F. Yu, Grace Aloina, Panca Jodiawan, Aldy Gunawan, Tsung-Chi Huang
Solving The Vehicle Routing Problem With Simultaneous Pickup And Delivery And Occasional Drivers By Simulated Annealing, Vincent F. Yu, Grace Aloina, Panca Jodiawan, Aldy Gunawan, Tsung-Chi Huang
Research Collection School Of Computing and Information Systems
This research studies the vehicle routing problem with simultaneous pickup and delivery with an occasional driver (VRPSPDOD). VRPSPDOD is a new variant of the vehicle routing problems with simultaneous pickup and delivery (VRPSPD). Different from VRPSPD, in VRPSPDOD, occasional drivers are employed to work with regular vehicles to service customers’ pickup and delivery requests in order to minimize the total cost. We formulate a mixed integer linear programming model for VRPSPD and propose a heuristic algorithm based on simulated annealing (SA) to solve the problem. The results of comprehensive numerical experiments show that the proposed SA performs well in terms …
Statistical Moderation: A Case Study In Grading On A Curve, Manoj Thulasidas
Statistical Moderation: A Case Study In Grading On A Curve, Manoj Thulasidas
Research Collection School Of Computing and Information Systems
There is a negative perception about “grading on a curve,” because of the feeling that the cohort strength may skew the final grades one way or another. However, given the difficulties in ensuring absolute uniformity in assessment across the years, especially when taught and assessed by different instructors under different settings, grading on a curve may be a necessary evil. Once we accept this type of statistical moderation as the last line of defense in standardizing the final scores so that student cohorts from different terms or sections or schools may be compared, we have to implement it well. In …
Context-Aware Graph Convolutional Network For Dynamic Origin-Destination Prediction, Juan Nathaniel, Baihua Zheng
Context-Aware Graph Convolutional Network For Dynamic Origin-Destination Prediction, Juan Nathaniel, Baihua Zheng
Research Collection School Of Computing and Information Systems
A robust Origin-Destination (OD) prediction is key to urban mobility. A good forecasting model can reduce operational risks and improve service availability, among many other upsides. Here, we examine the use of Graph Convolutional Net-work (GCN) and its hybrid Markov-Chain (GCN-MC) variant to perform a context-aware OD prediction based on a large-scale public transportation dataset in Singapore. Compared with the baseline Markov-Chain algorithm and GCN, the proposed hybrid GCN-MC model improves the prediction accuracy by 37% and 12% respectively. Lastly, the addition of temporal and historical contextual information further improves the performance of the proposed hybrid model by 4 –12%.
Hrpdf: A Software-Based Heterogeneous Redundant Proactive Defense Framework For Programmable Logic Controller, Ke Liu, Jing-Yi Wang, Qiang Wei, Zhen-Yong Zhang, Jun Sun, Rong-Kuan Ma, Rui-Long Deng
Hrpdf: A Software-Based Heterogeneous Redundant Proactive Defense Framework For Programmable Logic Controller, Ke Liu, Jing-Yi Wang, Qiang Wei, Zhen-Yong Zhang, Jun Sun, Rong-Kuan Ma, Rui-Long Deng
Research Collection School Of Computing and Information Systems
Programmable logic controllers (PLCs) play a critical role in many industrial control systems, yet face increasingly serious cyber threats. In this paper, we propose a novel PLC-compatible software-based defense mechanism, called Heterogeneous Redundant Proactive Defense Framework (HRPDF). We propose a heterogeneous PLC architecture in HRPDF, including multiple heterogeneous, equivalent, and synchronous runtimes, which can thwart multiple types of attacks against PLC without the need of external devices. To ensure the availability of PLC, we also design an inter-process communication algorithm that minimizes the overhead of HRPDF. We implement a prototype system of HRPDF and test it in a real-world PLC …
Linear Algebra For Computer Science, M. Thulasidas
Linear Algebra For Computer Science, M. Thulasidas
Research Collection School Of Computing and Information Systems
This textbook introduces the essential concepts and practice of Linear Algebra to the undergraduate student of computer science. The focus of this book is on the elegance and beauty of the numerical techniques and algorithms originating from Linear Algebra. As a practical handbook for computer and data scientists, LA4CS restricts itself mostly to real fields and tractable discourses, rather than deep and theoretical mathematics.
Strategic Behavior And Market Inefficiency In Blockchain-Based Auctions, Ping Fan Ke, Jianqing Chen, Zhiling Guo
Strategic Behavior And Market Inefficiency In Blockchain-Based Auctions, Ping Fan Ke, Jianqing Chen, Zhiling Guo
Research Collection School Of Computing and Information Systems
Blockchain-based auctions play a key role in decentralized finance, such as liquidation of collaterals in crypto-lending. In this research, we show that a Blockchain-based auction is subject to the threat to availability because of the characteristics of the Blockchain platform, which could lead to auction inefficiency or even market failure. Specifically, an adversary could occupy all of the transaction capacity of an auction by sending transactions with sufficiently high transaction fees, and then win the item in an auction with a nearly zero bid price as there are no competitors available. We discuss how to prevent this kind of strategic …
Decentralized Deterministic Multi-Agent Reinforcement Learning, Antoine Grosnit, Desmond Cai, Laura Wynter
Decentralized Deterministic Multi-Agent Reinforcement Learning, Antoine Grosnit, Desmond Cai, Laura Wynter
Research Collection School Of Computing and Information Systems
Recent work in multi-agent reinforcement learning (MARL) by [Zhang, ICML12018] provided the first decentralized actor-critic algorithm to offer convergence guarantees. In that work, policies are stochastic and are defined on finite action spaces. We extend those results to develop a provably-convergent decentralized actor-critic algorithm for learning deterministic policies on continuous action spaces. Deterministic policies are important in many real-world settings. To handle the lack of exploration inherent in deterministic policies we provide results for the off-policy setting as well as the on-policy setting. We provide the main ingredients needed for this problem: the expression of a local deterministic policy gradient, …
Robust Bipoly-Matching For Multi-Granular Entities, Ween Jiann Lee, Maksim Tkachenko, Hady W. Lauw
Robust Bipoly-Matching For Multi-Granular Entities, Ween Jiann Lee, Maksim Tkachenko, Hady W. Lauw
Research Collection School Of Computing and Information Systems
Entity matching across two data sources is a prevalent need in many domains, including e-commerce. Of interest is the scenario where entities have varying granularity, e.g., a coarse product category may match multiple finer categories. Previous work in one-to-many matching generally presumes the `one' necessarily comes from a designated source and the `many' from the other source. In contrast, we propose a novel formulation that allows concurrent one-to-many bidirectional matching in any direction. Beyond flexibility, we also seek matching that is more robust to noisy similarity values arising from diverse entity descriptions, by introducing receptivity and reclusivity notions. In addition …
On Analysing Student Resilience In Higher Education Programs Using A Data-Driven Approach, Audrey Tedja Widjaja, Ee Peng Lim, Aldy Gunawan
On Analysing Student Resilience In Higher Education Programs Using A Data-Driven Approach, Audrey Tedja Widjaja, Ee Peng Lim, Aldy Gunawan
Research Collection School Of Computing and Information Systems
Analysing student resilience is important as research has shown that resilience is related to students’ academic performance and their persistence through academic setbacks. While questionnaires can be conducted to assess student resilience directly, they suffer from human recall errors and deliberate suppression of true responses. In this paper, we propose ACREA, ACademic REsilience Analytics framework which adopts a datadriven approach to analyse student resilient behavior with the use of student-course data. ACREA defines academic setbacks experienced by students and measures how well students overcome such setbacks using a quasi-experimental design. By applying ACREA on a real world student-course dataset, we …
The Power Of Renegotiation And Monitoring In Software Outsourcing: Substitutes Or Complements?, He Huang, Minhui Hu, Robert J. Kauffman, Hongyan Xu
The Power Of Renegotiation And Monitoring In Software Outsourcing: Substitutes Or Complements?, He Huang, Minhui Hu, Robert J. Kauffman, Hongyan Xu
Research Collection School Of Computing and Information Systems
Monitoring and contract renegotiation are two common solutions for addressing information asymmetry and uncertainty between a client and a vendor of software outsourcing services. Monitoring is mostly applied in time-and-materials contracts, as a basis for inspecting and reimbursing the vendor’s efforts in system development. Renegotiation, by contrast, is deployed in fixed-price and time-and-materials contracts to mitigate the loss of surplus from uncertainty after system development. We investigate the interaction between monitoring and renegotiation and examine the corresponding contract choice problem. We find that the client benefits from renegotiation based on two effects: an uncertainty-resolution effect and a post-development incentive effect, …
Vireo @ Trecvid 2021 Ad-Hoc Video Search, Jiaxin Wu, Phuong Anh Nguyen, Chong-Wah Ngo
Vireo @ Trecvid 2021 Ad-Hoc Video Search, Jiaxin Wu, Phuong Anh Nguyen, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
In this paper, we summarize our submitted runs and results for Ad-hoc Video Search (AVS) task at TRECVid 2020
Video Snapshot: Single Image Motion Expansion Via Invertible Motion Embedding, Qianshu Zhu, Chu Han, Guoqiang Han, Tien-Tsin Wong, Shengfeng He
Video Snapshot: Single Image Motion Expansion Via Invertible Motion Embedding, Qianshu Zhu, Chu Han, Guoqiang Han, Tien-Tsin Wong, Shengfeng He
Research Collection School Of Computing and Information Systems
Unlike images, finding the desired video content in a large pool of videos is not easy due to the time cost of loading and watching. Most video streaming and sharing services provide the video preview function for a better browsing experience. In this paper, we aim to generate a video preview from a single image. To this end, we propose two cascaded networks, the motion embedding network and the motion expansion network. The motion embedding network aims to embed the spatio-temporal information into an embedded image, called video snapshot. On the other end, the motion expansion network is proposed to …
Learning Large Neighborhood Search Policy For Integer Programming, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang
Learning Large Neighborhood Search Policy For Integer Programming, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang
Research Collection School Of Computing and Information Systems
We propose a deep reinforcement learning (RL) method to learn large neighborhood search (LNS) policy for integer programming (IP). The RL policy is trained as the destroy operator to select a subset of variables at each step, which is reoptimized by an IP solver as the repair operator. However, the combinatorial number of variable subsets prevents direct application of typical RL algorithms. To tackle this challenge, we represent all subsets by factorizing them into binary decisions on each variable. We then design a neural network to learn policies for each variable in parallel, trained by a customized actor-critic algorithm. We …
Neurolkh: Combining Deep Learning Model With Lin-Kernighan-Helsgaun Heuristic For Solving The Traveling Salesman Problem, Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang
Neurolkh: Combining Deep Learning Model With Lin-Kernighan-Helsgaun Heuristic For Solving The Traveling Salesman Problem, Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang
Research Collection School Of Computing and Information Systems
We present NeuroLKH, a novel algorithm that combines deep learning with the strong traditional heuristic Lin-Kernighan-Helsgaun (LKH) for solving Traveling Salesman Problem. Specifically, we train a Sparse Graph Network (SGN) with supervised learning for edge scores and unsupervised learning for node penalties, both of which are critical for improving the performance of LKH. Based on the output of SGN, NeuroLKH creates the edge candidate set and transforms edge distances to guide the searching process of LKH. Extensive experiments firmly demonstrate that, by training one model on a wide range of problem sizes, NeuroLKH significantly outperforms LKH and generalizes well to …
Learning To Iteratively Solve Routing Problems With Dual-Aspect Collaborative Transformer, Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, Jing Tang
Learning To Iteratively Solve Routing Problems With Dual-Aspect Collaborative Transformer, Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, Jing Tang
Research Collection School Of Computing and Information Systems
Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, it is less effective in learning improvement models for VRP because its positional encoding (PE) method is not suitable in representing VRP solutions. This paper presents a novel Dual-Aspect Collaborative Transformer (DACT) to learn embeddings for the node and positional features separately, instead of fusing them together as done in existing ones, so as to avoid potential noises and incompatible correlations. Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to allow Transformer to effectively capture the circularity and symmetry …
Canita: Faster Rates For Distributed Convex Optimization With Communication Compression, Zhize Li, Peter Richtarik
Canita: Faster Rates For Distributed Convex Optimization With Communication Compression, Zhize Li, Peter Richtarik
Research Collection School Of Computing and Information Systems
Due to the high communication cost in distributed and federated learning, methods relying on compressed communication are becoming increasingly popular. Besides, the best theoretically and practically performing gradient-type methods invariably rely on some form of acceleration/momentum to reduce the number of communications (faster convergence), e.g., Nesterov's accelerated gradient descent (Nesterov, 1983, 2004) and Adam (Kingma and Ba, 2014). In order to combine the benefits of communication compression and convergence acceleration, we propose a \emph{compressed and accelerated} gradient method based on ANITA (Li, 2021) for distributed optimization, which we call CANITA. Our CANITA achieves the \emph{first accelerated rate} $O\bigg(\sqrt{\Big(1+\sqrt{\frac{\omega^3}{n}}\Big)\frac{L}{\epsilon}} + \omega\big(\frac{1}{\epsilon}\big)^{\frac{1}{3}}\bigg)$, …
Towards Understanding Why Lookahead Generalizes Better Than Sgd And Beyond, Pan Zhou, Hanshu Yan, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan
Towards Understanding Why Lookahead Generalizes Better Than Sgd And Beyond, Pan Zhou, Hanshu Yan, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan
Research Collection School Of Computing and Information Systems
To train networks, lookahead algorithm [1] updates its fast weights k times via an inner-loop optimizer before updating its slow weights once by using the latest fast weights. Any optimizer, e.g. SGD, can serve as the inner-loop optimizer, and the derived lookahead generally enjoys remarkable test performance improvement over the vanilla optimizer. But theoretical understandings on the test performance improvement of lookahead remain absent yet. To solve this issue, we theoretically justify the advantages of lookahead in terms of the excess risk error which measures the test performance. Specifically, we prove that lookahead using SGD as its inner-loop optimizer can …
A Theory-Driven Self-Labeling Refinement Method For Contrastive Representation Learning, Pan Zhou, Caiming Xiong, Xiao-Tong Yuan
A Theory-Driven Self-Labeling Refinement Method For Contrastive Representation Learning, Pan Zhou, Caiming Xiong, Xiao-Tong Yuan
Research Collection School Of Computing and Information Systems
For an image query, unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic similarity between a query and its positives and negatives, and impairs performance, since some negatives are semantically similar to the query or even share the same semantic class as the query. In this work, we first prove that for contrastive learning, inaccurate label assignment heavily impairs its generalization for semantic instance discrimination, while accurate labels benefit its generalization. Inspired by this theory, we propose a novel …
Infinite Time Horizon Safety Of Bayesian Neural Networks, Mathias Lechner, Dorde Zikelic, Krishnendu Chatterjee, Thomas A. Henzinger
Infinite Time Horizon Safety Of Bayesian Neural Networks, Mathias Lechner, Dorde Zikelic, Krishnendu Chatterjee, Thomas A. Henzinger
Research Collection School Of Computing and Information Systems
Bayesian neural networks (BNNs) place distributions over the weights of a neural network to model uncertainty in the data and the network’s prediction. We consider the problem of verifying safety when running a Bayesian neural network policy in a feedback loop with infinite time horizon systems. Compared to the existing sampling-based approaches, which are inapplicable to the infinite time horizon setting, we train a separate deterministic neural network that serves as an infinite time horizon safety certificate. In particular, we show that the certificate network guarantees the safety of the system over a subset of the BNN weight posterior’s support. …
Rmix: Learning Risk-Sensitive Policies For Cooperative Reinforcement Learning Agents, Wei Qiu, Xinrun Wang, Runsheng Yu, Xu He, Rundong Wang, Bo An, Svetlana Obraztsova, Zinovi Rabinovich
Rmix: Learning Risk-Sensitive Policies For Cooperative Reinforcement Learning Agents, Wei Qiu, Xinrun Wang, Runsheng Yu, Xu He, Rundong Wang, Bo An, Svetlana Obraztsova, Zinovi Rabinovich
Research Collection School Of Computing and Information Systems
Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value is not sufficient even with CTDE due to the randomness of rewards and the uncertainty in environments, which causes the failure of these methods to train coordinating agents in complex environments. To address these issues, we propose RMIX, a novel cooperative MARL method with the Conditional Value at Risk (CVaR) measure over the learned distributions of individuals' Q values. Specifically, we first learn the return distributions of individuals to analytically calculate CVaR …
Data Fusion For Trust Evaluation, Zheng Yan, Qinghua Zheng, Laurence T. Yang, Robert H. Deng
Data Fusion For Trust Evaluation, Zheng Yan, Qinghua Zheng, Laurence T. Yang, Robert H. Deng
Research Collection School Of Computing and Information Systems
Trust evaluation is a process to quantify trust by analyzing the data related to the factors that affect trust. It has been widely applied in many fields to facilitate decision making, system entity collaboration and security establishment. For example, in social networking, trust evaluation helps users make a social decision, reduce the risk of social interactions, and ensure the quality of a social networking environment. In digital communications, trust evaluation can be applied to detect malicious nodes, filter unwanted traffic and improve communication security. In e-commerce and cloud services, trust evaluation helps users selecting an appropriate product or service from …
Integration Of Information Technology Certifications Into Undergraduate Computing Curriculum, Eng Lieh Ouh, Kyong Jin Shim
Integration Of Information Technology Certifications Into Undergraduate Computing Curriculum, Eng Lieh Ouh, Kyong Jin Shim
Research Collection School Of Computing and Information Systems
This innovative practice full paper describes our experiences of integrating information technology certifications into an undergraduate computing curriculum. As the technology landscape evolves, a common challenge for educators in computing programs is designing an industry-relevant curriculum. Over the years, industry practitioners have taken technology certifications to validate themselves against a base level of technical knowledge currently in demand in industry. Information technology (IT) certifications can also offer paths for academic computing programs to stay relevant to industry needs. However, identifying relevant IT certifications and integrating it into an academic curriculum requires a careful design approach as substantial efforts are needed …