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

Computer Sciences Commons™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 2341 - 2370 of 9003

Full-Text Articles in Computer Sciences

Joint Hyperbolic And Euclidean Geometry Contrastive Graph Neural Networks, Xiaoyu Xu, Guansong Pang, Di Wu, Mingsheng Shang Sep 2022

Joint Hyperbolic And Euclidean Geometry Contrastive Graph Neural Networks, Xiaoyu Xu, Guansong Pang, Di Wu, Mingsheng Shang

Research Collection School Of Computing and Information Systems

Graph Neural Networks (GNNs) have demonstrated state-of-the-art performance in a wide variety of analytical tasks. Current GNN approaches focus on learning representations in a Euclidean space, which are effective in capturing non-tree-like structural relations, but they fail to model complex relations in many real-world graphs, such as tree-like hierarchical graph structure. This paper instead proposes to learn representations in both Euclidean and hyperbolic spaces to model these two types of graph geometries. To this end, we introduce a novel approach - Joint hyperbolic and Euclidean geometry contrastive graph neural networks (JointGMC). JointGMC is enforced to learn multiple layer-wise optimal combinations …

Go to article

Eeg-Video Emotion-Based Summarization: Learning With Eeg Auxiliary Signals, Wai-Cheong L. Lew, Di Wang, Kai-Keng Ang, Joo-Hwee Lim, Chai Quek, Ah-Hwee Tan Sep 2022

Eeg-Video Emotion-Based Summarization: Learning With Eeg Auxiliary Signals, Wai-Cheong L. Lew, Di Wang, Kai-Keng Ang, Joo-Hwee Lim, Chai Quek, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Video summarization is the process of selecting a subset of informative keyframes to expedite storytelling with limited loss of information. In this paper, we propose an EEG-Video Emotion-based Summarization (EVES) model based on a multimodal deep reinforcement learning (DRL) architecture that leverages neural signals to learn visual interestingness to produce quantitatively and qualitatively better video summaries. As such, EVES does not learn from the expensive human annotations but the multimodal signals. Furthermore, to ensure the temporal alignment and minimize the modality gap between the visual and EEG modalities, we introduce a Time Synchronization Module (TSM) that uses an attention mechanism …

Go to article

Constrained Multiagent Reinforcement Learning For Large Agent Population, Jiajing Ling, Arambam James Singh, Duc Thien Nguyen, Akshat Kumar Sep 2022

Constrained Multiagent Reinforcement Learning For Large Agent Population, Jiajing Ling, Arambam James Singh, Duc Thien Nguyen, Akshat Kumar

Research Collection School Of Computing and Information Systems

Learning control policies for a large number of agents in a decentralized setting is challenging due to partial observability, uncertainty in the environment, and scalability challenges. While several scalable multiagent RL (MARL) methods have been proposed, relatively few approaches exist for large scale constrained MARL settings. To address this, we first formulate the constrained MARL problem in a collective multiagent setting where interactions among agents are governed by the aggregate count and types of agents, and do not depend on agents’ specific identities. Second, we show that standard Lagrangian relaxation methods, which are popular for single agent RL, do not …

Go to article

Toward Intention Discovery For Early Malice Detection In Bitcoin, Ling Cheng, Feida Zhu, Yong Wang, Huiwen Liu Sep 2022

Toward Intention Discovery For Early Malice Detection In Bitcoin, Ling Cheng, Feida Zhu, Yong Wang, Huiwen Liu

Research Collection School Of Computing and Information Systems

Bitcoin has been subject to illicit activities more often than probably any other financial assets, due to the pseudo-anonymous nature of its transacting entities. An ideal detection model is expected to achieve all the three properties of (I) early detection, (II) good interpretability, and (III) versatility for various illicit activities. However, existing solutions cannot meet all these requirements, as most of them heavily rely on deep learning without satisfying interpretability and are only available for retrospective analysis of a specific illicit type.First, we present asset transfer paths, which aim to describe addresses' early characteristics. Next, with a decision tree based …

Go to article

Automatic Fairness Testing Of Neural Classifiers Through Adversarial Sampling, Peixin Zhang, Jingyi Wang, Jun Sun, Xinyu Wang, Guoliang Dong, Xinggen Wang, Ting Dai, Jinsong Dong Sep 2022

Automatic Fairness Testing Of Neural Classifiers Through Adversarial Sampling, Peixin Zhang, Jingyi Wang, Jun Sun, Xinyu Wang, Guoliang Dong, Xinggen Wang, Ting Dai, Jinsong Dong

Research Collection School Of Computing and Information Systems

Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e., non-discrimination). Unfortunately, discrimination might be intrinsically embedded into the models due to the discrimination in the training data. As a countermeasure, fairness testing systemically identifies discriminatory samples, which can be used to retrain the model and improve the model’s fairness. Existing fairness testing approaches however have two major limitations. Firstly, they only work well on traditional machine learning models and have poor performance (e.g., effectiveness and efficiency) on deep learning …

Go to article

Does Social Media Accelerate Product Recalls? Evidence From The Pharmaceutical Industry, Yang Gao, Wenjing Duan, Huaxia Rui Sep 2022

Does Social Media Accelerate Product Recalls? Evidence From The Pharmaceutical Industry, Yang Gao, Wenjing Duan, Huaxia Rui

Research Collection School Of Computing and Information Systems

Social media has become a vital platform for voicing product-related experiences that may not only reveal product defects but also impose pressure on firms to act more promptly than before. This study scrutinizes the rarely-studied relationship between these voices and the speed of product recalls in the context of the pharmaceutical industry where social media pharmacovigilance is becoming increasingly important for the detection of drug safety signals. Using Federal Drug Administration (FDA) drug enforcement reports and social media data crawled from online forums and Twitter, we investigate whether social media can accelerate the product recall process in the context of …

Go to article

Structured Encryption For Knowledge Graphs, Yujie Xue, Lanxiang Chen, Yu Mi, Lingfang Zeng, Fatemeh Rezaeibagha, Robert H. Deng Aug 2022

Structured Encryption For Knowledge Graphs, Yujie Xue, Lanxiang Chen, Yu Mi, Lingfang Zeng, Fatemeh Rezaeibagha, Robert H. Deng

Research Collection School Of Computing and Information Systems

We investigate the problem of structured encryption (STE) for knowledge graphs (KGs) where the knowledge of data can be efficiently and privately queried. Presently, the application of natural language processing (NLP) for knowledge-based search is gradually emerging. Compared with the traditional search based only on keywords of documents-symmetric searchable encryption (SSE), the knowledge-based search system transforms the latent knowledge contained in documents into a semantic network as a knowledge base, which greatly improves the accuracy and relevance of search results. In order to develop a knowledge-based search, the contents of documents are analyzed and extracted using KG techniques (e.g. multi-relational …

Go to article

Destress: Computation-Optimal And Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization, Boyue Li, Zhize Li, Yuejie Chi Aug 2022

Destress: Computation-Optimal And Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization, Boyue Li, Zhize Li, Yuejie Chi

Research Collection School Of Computing and Information Systems

Emerging applications in multiagent environments such as internet-of-things, networked sensing, autonomous systems, and federated learning, call for decentralized algorithms for finite-sum optimizations that are resource efficient in terms of both computation and communication. In this paper, we consider the prototypical setting where the agents work collaboratively to minimize the sum of local loss functions by only communicating with their neighbors over a predetermined network topology. We develop a new algorithm, called DEcentralized STochastic REcurSive gradient methodS (DESTRESS) for nonconvex finite-sum optimization, which matches the optimal incremental first-order oracle complexity of centralized algorithms for finding first-order stationary points, while maintaining communication …

Go to article

Self-Adaptive Systems: A Systematic Literature Review Across Categories And Domains, Terence Wong, Markus Wagner, Christoph Treude Aug 2022

Self-Adaptive Systems: A Systematic Literature Review Across Categories And Domains, Terence Wong, Markus Wagner, Christoph Treude

Research Collection School Of Computing and Information Systems

Context: Championed by IBM’s vision of autonomic computing paper in 2003, the autonomic computing research field has seen increased research activity over the last 20 years. Several conferences (SEAMS, SASO, ICAC) and workshops (SISSY) have been established and have contributed to the autonomic computing knowledge base in search of a new kind of system — a self-adaptive system (SAS). These systems are characterized by being context-aware and can act on that awareness. The actions carried out could be on the system or on the context (or environment). The underlying goal of a SAS is the sustained achievement of its goals …

Go to article

Neural-Progressive Hedging: Enforcing Constraints In Reinforcement Learning With Stochastic Programming, Supriyo Ghosh, Laura Wynter, Shiau Hong Lim, Duc Thien Nguyen Aug 2022

Neural-Progressive Hedging: Enforcing Constraints In Reinforcement Learning With Stochastic Programming, Supriyo Ghosh, Laura Wynter, Shiau Hong Lim, Duc Thien Nguyen

Research Collection School Of Computing and Information Systems

We propose a framework, called neural-progressive hedging (NP), that leverages stochastic programming during the online phase of executing a reinforcement learning (RL) policy. The goal is to ensure feasibility with respect to constraints and risk-based objectives such as conditional value-at-risk (CVaR) during the execution of the policy, using probabilistic models of the state transitions to guide policy adjustments. The framework is particularly amenable to the class of sequential resource allocation problems since feasibility with respect to typical resource constraints cannot be enforced in a scalable manner. The NP framework provides an alternative that adds modest overhead during the online phase. …

Go to article

Legion: Massively Composing Rankers For Improved Bug Localization At Adobe, Darryl Jarman, Jeffrey Berry, Riley Smith, Ferdian Thung, David Lo Aug 2022

Legion: Massively Composing Rankers For Improved Bug Localization At Adobe, Darryl Jarman, Jeffrey Berry, Riley Smith, Ferdian Thung, David Lo

Research Collection School Of Computing and Information Systems

Studies have estimated that, in industrial settings, developers spend between 30 and 90 percent of their time fixing bugs. As such, tools that assist in identifying the location of bugs provide value by reducing debugging costs. One such tool is BugLocator. This study initially aimed to determine if developers working on the Adobe Analytics product could use BugLocator. The initial results show that BugLocator achieves a similar accuracy on five of seven Adobe Analytics repositories and on open-source projects. However, these results do not meet the minimum applicability requirement deemed necessary by Adobe Analytics developers prior to possible adoption. Thus, …

Go to article

Crosscbr: Cross‑View Contrastive Learning For Bundle Recommendation, Yunshan Ma, Yingzhi He, An Zhang, Xiang Wang, Tat-Seng Chua Aug 2022

Crosscbr: Cross‑View Contrastive Learning For Bundle Recommendation, Yunshan Ma, Yingzhi He, An Zhang, Xiang Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Bundle recommendation aims to recommend a bundle of related items to users, which can satisfy the users' various needs with one-stop convenience. Recent methods usually take advantage of both user-bundle and user-item interactions information to obtain informative representations for users and bundles, corresponding to bundle view and item view, respectively. However, they either use a unified view without differentiation or loosely combine the predictions of two separate views, while the crucial cooperative association between the two views' representations is overlooked.In this work, we propose to model the cooperative association between the two different views through cross-view contrastive learning. By encouraging …

Go to article

Developing Gamification Research In Information Systems, De Liu, Richard Landers, Paul Lowry, Fiona Fui-Hoon Nah, Radhika Santhanam Aug 2022

Developing Gamification Research In Information Systems, De Liu, Richard Landers, Paul Lowry, Fiona Fui-Hoon Nah, Radhika Santhanam

Research Collection School Of Computing and Information Systems

Gamification, an umbrella term for incorporating game design elements into non-game systems to make them more engaging and productive, is of interest to Information System (IS) communities, because it has wide applications, such as, gamification designs for workplace, learning and health apps, social media, online communities, and the gig economy. As a multidisciplinary research domain, gamification integrates elements of technology, human motivation, task design, human-computer-interface design, and algorithms/AI design, and is a fertile ground for IS researchers with a variety of different background. There are many challenges in conducting gamification research, including how to get started in this highly multidisciplinary …

Go to article

Extract Human Mobility Patterns Powered By City Semantic Diagram, Zhangqing Shan, Weiwei Shan, Baihua Zheng Aug 2022

Extract Human Mobility Patterns Powered By City Semantic Diagram, Zhangqing Shan, Weiwei Shan, Baihua Zheng

Research Collection School Of Computing and Information Systems

With widespread deployment of GPS devices, massive spatiotemporal trajectories became more accessible. This booming trend paved the solid data ground for researchers to discover the regularities or patterns of human mobility. However, there are still three challenges in semantic pattern extraction including semantic absence, semantic bias and semantic complexity. In this paper, we invent and apply a novel data structure namely City Semantic Diagram to overcome above three challenges. First, our approach resolves semantic absence by exactly identifying semantic behaviours from raw trajectories. Second, the delicate design of semantic purification helps us to detect semantic complexity from human mobility. Third, …

Go to article

Joint Chance-Constrained Staffing Optimization In Multi-Skill Call Centers, Tien Thanh Dam, Thuy Anh Ta, Tien Mai Aug 2022

Joint Chance-Constrained Staffing Optimization In Multi-Skill Call Centers, Tien Thanh Dam, Thuy Anh Ta, Tien Mai

Research Collection School Of Computing and Information Systems

This paper concerns the staffing optimization problem in multi-skill call centers. The objective is to find a minimal cost staffing solution while meeting a target level for the quality of service (QoS) to customers. We consider a staffing problem in which joint chance constraints are imposed on the QoS of the day. Our joint chance-constrained formulation is more rational capturing the correlation between different call types, as compared to separate chance-constrained versions considered in previous studies. We show that, in general, the probability functions in the joint-chance constraints display S-shaped curves, and the optimal solutions should belong to the concave …

Go to article

Aligning Dual Disentangled User Representations From Ratings And Textual Content, Nhu Thuat Tran, Hady Wirawan Lauw Aug 2022

Aligning Dual Disentangled User Representations From Ratings And Textual Content, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Classical recommendation methods typically render user representation as a single vector in latent space. Oftentimes, a user's interactions with items are influenced by several hidden factors. To better uncover these hidden factors, we seek disentangled representations. Existing disentanglement methods for recommendations are mainly concerned with user-item interactions alone. To further improve not only the effectiveness of recommendations but also the interpretability of the representations, we propose to learn a second set of disentangled user representations from textual content and to align the two sets of representations with one another. The purpose of this coupling is two-fold. For one benefit, we …

Go to article

Resumable Zero-Knowledge For Circuits From Symmetric Key Primitives, Handong Zhang, Puwen Wei, Haiyang Xue, Yi Deng, Jinsong Li, Wei Wang, Guoxiao Liu Aug 2022

Resumable Zero-Knowledge For Circuits From Symmetric Key Primitives, Handong Zhang, Puwen Wei, Haiyang Xue, Yi Deng, Jinsong Li, Wei Wang, Guoxiao Liu

Research Collection School Of Computing and Information Systems

Consider the scenario that the prover and the verifier perform the zero-knowledge (ZK) proof protocol for the same statement multiple times sequentially, where each proof is modeled as a session. We focus on the problem of how to resume a ZK proof efficiently in such scenario. We introduce a new primitive called resumable honest verifier zero-knowledge proof of knowledge (resumable HVZKPoK) and propose a general construction of the resumable HVZKPoK for circuits based on the “MPC-in-the-head" paradigm, where the complexity of the resumed session is less than that of the original ZK proofs. To ensure the knowledge soundness for the …

Go to article

Artificial Intelligence In Financial Technology, Keng Siau, Fiona Fui-Hoon Nah, Brenda L. Eschenbrenner, Langtao Chen Aug 2022

Artificial Intelligence In Financial Technology, Keng Siau, Fiona Fui-Hoon Nah, Brenda L. Eschenbrenner, Langtao Chen

Research Collection School Of Computing and Information Systems

AI applications in health care, communications, and arts have brought about rapid and dramatic advances in these fields. Nevertheless, the rapidly expanding potential of AI in the economy and society has raised a set of challenging issues. The fields of AI and financial technology are not spared. How can artificial intelligence (AI) be utilized in financial technology (fintech)? What will be the impact? What actionable objectives are needed to realize value from AI? This research uses a systematic qualitative research methodology, Value-Focused Thinking, to identify the actionable objectives for deriving value from AI in the fintech industry. The results of …

Go to article

Individually Rational Collaborative Vehicle Routing Through Give-And-Take Exchanges, Tran Phong, Paul Tang, Hoong Chuin Lau Aug 2022

Individually Rational Collaborative Vehicle Routing Through Give-And-Take Exchanges, Tran Phong, Paul Tang, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

In this paper, we are concerned with the automated exchange of orders between logistics companies in a marketplace platform to optimize total revenues. We introduce a novel multi-agent approach to this problem, focusing on the Collaborative Vehicle Routing Problem (CVRP) through the lens of individual rationality. Our proposed algorithm applies the principles of Vehicle Routing Problem (VRP) to pairs of vehicles from different logistics companies, optimizing the overall routes while considering standard VRP constraints plus individual rationality constraints. By facilitating cooperation among competing logistics agents through a Give-and-Take approach, we show that it is possible to reduce travel distance and …

Go to article

Fed-Ltd: Towards Cross-Platform Ride Hailing Via Federated Learning To Dispatch, Yansheng Wang, Yongxin Tong, Zimu Zhou, Ziyao Ren, Yi Xu, Guobin Wu, Weifeng Lv Aug 2022

Fed-Ltd: Towards Cross-Platform Ride Hailing Via Federated Learning To Dispatch, Yansheng Wang, Yongxin Tong, Zimu Zhou, Ziyao Ren, Yi Xu, Guobin Wu, Weifeng Lv

Research Collection School Of Computing and Information Systems

Learning based order dispatching has witnessed tremendous success in ride hailing. However, the success halts within individual ride hailing platforms because sharing raw order dispatching data across platforms may leak user privacy and business secrets. Such data isolation not only impairs user experience but also decreases the potential revenues of the platforms. In this paper, we advocate federated order dispatching for cross-platform ride hailing, where multiple platforms collaboratively make dispatching decisions without sharing their local data. Realizing this concept calls for new federated learning strategies that tackle the unique challenges on effectiveness, privacy and efficiency in the context of order …

Go to article

P-Meta: Towards On-Device Deep Model Adaptation, Zhongnan Qu, Zimu Zhou, Yongxin Tong, Lothar Thiele Aug 2022

P-Meta: Towards On-Device Deep Model Adaptation, Zhongnan Qu, Zimu Zhou, Yongxin Tong, Lothar Thiele

Research Collection School Of Computing and Information Systems

Data collected by IoT devices are often private and have a large diversity across users. Therefore, learning requires pre-training a model with available representative data samples, deploying the pre-trained model on IoT devices, and adapting the deployed model on the device with local data. Such an on-device adaption for deep learning empowered applications demands data and memory efficiency. However, existing gradient-based meta learning schemes fail to support memory-efficient adaptation. To this end, we propose p-Meta, a new meta learning method that enforces structure-wise partial parameter updates while ensuring fast generalization to unseen tasks. Evaluations on few-shot image classification and reinforcement …

Go to article

Mobile Health With Head-Worn Devices: Challenges And Opportunities, Andrea Ferlini, Dong Ma, Lorena Qendro, Cecilia Mascolo Aug 2022

Mobile Health With Head-Worn Devices: Challenges And Opportunities, Andrea Ferlini, Dong Ma, Lorena Qendro, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Monitoring human behavior and health status using mobile devices, a.k.a. Mobile Health, has gained increasing attention from both academia and industry in recent years. It allows imperceptible health tracking from the users and remote health management from the healthcare service providers. Headworn devices, such as earbuds, glasses, and BCIs (Brain Computer Interfaces), exhibit great potential for mobile health due to their advantageous wearing position, the human head, which is motion-resilient and full of human bio-signals. Although initial attempts have been conducted for different healthcare applications with head-worn devices, this fast-growing area is still under-explored and retains great promises. With this …

Go to article

Efficient Resource Allocation With Fairness Constraints In Restless Multi-Armed Bandits, Dexun Li, Pradeep Varakantham Aug 2022

Efficient Resource Allocation With Fairness Constraints In Restless Multi-Armed Bandits, Dexun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Restless Multi-Armed Bandits (RMAB) is an apt model to represent decision-making problems in public health interventions (e.g., tuberculosis, maternal, and child care), anti-poaching planning, sensor monitoring, personalized recommendations and many more. Existing research in RMAB has contributed mechanisms and theoretical results to a wide variety of settings, where the focus is on maximizing expected value. In this paper, we are interested in ensuring that RMAB decision making is also fair to different arms while maximizing expected value. In the context of public health settings, this would ensure that different people and/or communities are fairly represented while making public health intervention …

Go to article

Holistic Combination Of Structural And Textual Code Information For Context Based Api Recommendation, Chi Chen, Xin Peng, Zhengchang Xing, Jun Sun, Xin Wang, Yifan Zhao, Wenyun Zhao Aug 2022

Holistic Combination Of Structural And Textual Code Information For Context Based Api Recommendation, Chi Chen, Xin Peng, Zhengchang Xing, Jun Sun, Xin Wang, Yifan Zhao, Wenyun Zhao

Research Collection School Of Computing and Information Systems

Context based API recommendation is an important way to help developers find the needed APIs effectively and efficiently. For effective API recommendation, we need not only a joint view of both structural and textual code information, but also a holistic view of correlated API usage in control and data flow graph as a whole. Unfortunately, existing API recommendation methods exploit structural or textual code information separately. In this work, we propose a novel API recommendation approach called APIRec-CST (API Recommendation by Combining Structural and Textual code information). APIRec-CST is a deep learning model that combines the API usage with the …

Go to article

Ransomsoc: A More Effective Security Operations Center To Detect And Respond To Ransomware Attacks, Anthony Cheuk Tung Lai, Ping Fan Ke, Kelvin Chan, Siu Ming Yiu, Dongsun Kim, Wai Kin Wong, Shuai Wang, Joseph Muppala, Alan Ho Aug 2022

Ransomsoc: A More Effective Security Operations Center To Detect And Respond To Ransomware Attacks, Anthony Cheuk Tung Lai, Ping Fan Ke, Kelvin Chan, Siu Ming Yiu, Dongsun Kim, Wai Kin Wong, Shuai Wang, Joseph Muppala, Alan Ho

Research Collection School Of Computing and Information Systems

Ransomware remains a major threat for organizations. Despite a lot of research done, existing solutions still have at least two shortcomings. (I) Slow detection time: by the time we realize that the system is under ransomware attack, almost all files have been encrypted. (II) Without a ransomwareaware backup scheme: Most existing systems, in particular those in SMEs (small and medium enterprises), do not have a proper backup system. Even they have it, either it is not a remote-site backup (i.e., files in the backup system may also be encrypted) or it is not designed for ransomware attacks. In this paper, …

Go to article

Interpreting Trajectories From Multiple Views: A Hierarchical Self-Attention Network For Estimating The Time Of Arrival, Zebin Chen, Xiaolin Xiao, Yue-Jiao Gong, Jun Fang, Nan Ma, Hua Chai, Zhiguang Cao Aug 2022

Interpreting Trajectories From Multiple Views: A Hierarchical Self-Attention Network For Estimating The Time Of Arrival, Zebin Chen, Xiaolin Xiao, Yue-Jiao Gong, Jun Fang, Nan Ma, Hua Chai, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Estimating the time of arrival is a crucial task in intelligent transportation systems. Although considerable efforts have been made to solve this problem, most of them decompose a trajectory into several segments and then compute the travel time by integrating the attributes from all segments. The segment view, though being able to depict the local traffic conditions straightforwardly, is insufficient to embody the intrinsic structure of trajectories on the road network. To overcome the limitation, this study proposes multi-view trajectory representation that comprehensively interprets a trajectory from the segment-, link-, and intersection-views. To fulfill the purpose, we design a hierarchical …

Go to article

Finding Meta Winning Ticket To Train Your Maml, Dawei Gao, Yuexiang Xie, Zimu Zhou, Zhen Wang, Yaliang Li, Bolin. Ding Aug 2022

Finding Meta Winning Ticket To Train Your Maml, Dawei Gao, Yuexiang Xie, Zimu Zhou, Zhen Wang, Yaliang Li, Bolin. Ding

Research Collection School Of Computing and Information Systems

The lottery ticket hypothesis (LTH) states that a randomly initialized dense network contains sub-networks that can be trained in isolation to the performance of the dense network. In this paper, to achieve rapid learning with less computational cost, we explore LTH in the context of meta learning. First, we experimentally show that there are sparse sub-networks, known as meta winning tickets, which can be meta-trained to few-shot classification accuracy to the original backbone. The application of LTH in meta learning enables the adaptation of meta-trained networks on various IoT devices with fewer computation. However, the status quo to identify winning …

Go to article

Finding Meta Winning Ticket To Train Your Maml, Dawei Gao, Yuexiang Xie, Zimu Zhou, Zhen Wang, Yaliang Li, Bolin. Ding Aug 2022

Finding Meta Winning Ticket To Train Your Maml, Dawei Gao, Yuexiang Xie, Zimu Zhou, Zhen Wang, Yaliang Li, Bolin. Ding

Research Collection School Of Computing and Information Systems

The lottery ticket hypothesis (LTH) states that a randomly initialized dense network contains sub-networks that can be trained in isolation to the performance of the dense network. In this paper, to achieve rapid learning with less computational cost, we explore LTH in the context of meta learning. First, we experimentally show that there are sparse sub-networks, known as meta winning tickets, which can be meta-trained to few-shot classification accuracy to the original backbone. The application of LTH in meta learning enables the adaptation of meta-trained networks on various IoT devices with fewer computation. However, the status quo to identify winning …

Go to article

Variational Graph Author Topic Modeling, Ce Zhang, Hady Wirawan Lauw Aug 2022

Variational Graph Author Topic Modeling, Ce Zhang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

While Variational Graph Auto-Encoder (VGAE) has presented promising ability to learn representations for documents, most existing VGAE methods do not model a latent topic structure and therefore lack semantic interpretability. Exploring hidden topics within documents and discovering key words associated with each topic allow us to develop a semantic interpretation of the corpus. Moreover, documents are usually associated with authors. For example, news reports have journalists specializing in writing certain type of events, academic papers have authors with expertise in certain research topics, etc. Modeling authorship information could benefit topic modeling, since documents by the same authors tend to reveal …

Go to article

Verifying Neural Networks Against Backdoor Attacks, Long Hong Pham, Jun Sun Aug 2022

Verifying Neural Networks Against Backdoor Attacks, Long Hong Pham, Jun Sun

Research Collection School Of Computing and Information Systems

Neural networks have achieved state-of-the-art performance in solving many problems, including many applications in safety/security-critical systems. Researchers also discovered multiple security issues associated with neural networks. One of them is backdoor attacks, i.e., a neural network may be embedded with a backdoor such that a target output is almost always generated in the presence of a trigger. Existing defense approaches mostly focus on detecting whether a neural network is ‘backdoored’ based on heuristics, e.g., activation patterns. To the best of our knowledge, the only line of work which certifies the absence of backdoor is based on randomized smoothing, which is …

Go to article

First Prev Next Last