Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (9338)
- Social and Behavioral Sciences (9166)
- Computer Sciences (9030)
- Business (6904)
- International and Area Studies (3679)
-
- Asian Studies (3587)
- Databases and Information Systems (3562)
- Economics (2446)
- Law (2305)
- Software Engineering (2215)
- Artificial Intelligence and Robotics (1906)
- Finance and Financial Management (1290)
- Public Affairs, Public Policy and Public Administration (1143)
- Information Security (1108)
- Sociology (1108)
- Engineering (1100)
- Psychology (1081)
- Organizational Behavior and Theory (1064)
- Numerical Analysis and Scientific Computing (1059)
- Graphics and Human Computer Interfaces (952)
- Accounting (916)
- Education (900)
- Econometrics (824)
- Technology and Innovation (817)
- Communication (811)
- Strategic Management Policy (732)
- Arts and Humanities (689)
- Corporate Finance (665)
- Political Science (665)
- Higher Education (598)
- Keyword
-
- Singapore (1056)
- China (354)
- Singapore Management University (275)
- Innovation (206)
- COVID-19 (177)
-
- Machine learning (175)
- Artificial intelligence (144)
- Social media (137)
- Deep learning (135)
- Sustainability (130)
- Higher education (129)
- Corporate governance (117)
- Culture (113)
- Asia (110)
- Technology (109)
- Trust (97)
- Pandemic (92)
- Creativity (85)
- Performance (84)
- Leadership (83)
- Well-being (82)
- Education (81)
- Climate change (77)
- Data mining (77)
- Privacy (74)
- Reinforcement learning (74)
- Collaboration (72)
- India (71)
- Marketing (71)
- Southeast Asia (70)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (8692)
- Research Collection Lee Kong Chian School Of Business (3273)
- Research Collection School of Social Sciences (2262)
- Research Collection Yong Pung How School Of Law (2076)
- Research Collection School Of Economics (1760)
-
- Dissertations and Theses Collection (Open Access) (891)
- Research Collection School Of Accountancy (815)
- Perspectives@SMU (663)
- Research Collection College of Integrative Studies (534)
- Knowledge@SMU (403)
- Asian Management Insights (317)
- SMU Press Releases and News (243)
- Research Collection Library (221)
- Social Space (210)
- Research Collection Institute of Service Excellence (2007-2024) (85)
- Sim Kee Boon Institute for Financial Economics (62)
- Oral History Collection (50)
- Singapore Law Journal (Lexicon) (50)
- Digital Narratives of Asia (46)
- Dissertations and Theses Collection (45)
- Research@SMU: Connecting the Dots (45)
- Research Collection BNP Paribas Hedge Fund Centre (37)
- ROSA Research Briefs (31)
- Report to Stakeholders (25)
- Lien Centre for Social Innovation: Research (22)
- Research Collection Lee Kong Chian School of Business (22)
- CCX Research (20)
- Friends of the Museum Collection (20)
- SMU Corporate Reports (19)
- Student Publications (18)
- Publication Type
- File Type
Articles 1561 - 1590 of 23193
Full-Text Articles in Entire DC Network
Institutional Cross-Ownership Of Peer Firms And Revelatory Price Efficiency, Young Jun Cho, Holly I. Yang, Yue Zhao
Institutional Cross-Ownership Of Peer Firms And Revelatory Price Efficiency, Young Jun Cho, Holly I. Yang, Yue Zhao
Research Collection School Of Accountancy
We argue that cross-ownership increases the amount of private information in stock price, enhancing the ability of stock price to provide feedback to managers. Consistent with this argument, we find greater cross-ownership heightens a firm’s investment-q sensitivity. This effect is stronger for firms with a lower propensity for voluntary disclosure and for firms whose managers hold less private information. Furthermore, we find that cross-ownership is negatively associated with the sensitivity of a firm’s investment to its peers’ stock prices. Additionally, cross-ownership has a stronger impact on the investment-q sensitivity when measured among investors who trade more actively the …
Undergraduate Accounting Capstone: Enhancing Integration, Reflective Learning, And Workplace Transition For Future Professionals, Duan Ning, Magdeleine Lew, Clarence Goh, Poh Sun Seow, Gary Pan
Undergraduate Accounting Capstone: Enhancing Integration, Reflective Learning, And Workplace Transition For Future Professionals, Duan Ning, Magdeleine Lew, Clarence Goh, Poh Sun Seow, Gary Pan
Research Collection School Of Accountancy
This study examines whether a university capstone course focused on accounting data and analytics equips undergraduate accounting students with the relevant professional and technological skills for future work. There is concern that the traditional accounting curriculum, which often emphasizes theoretical knowledge and technical skills, may not sufficiently prepare students for the complex, data-driven environment in the workplace. Therefore, our study is important because professional and technological skills are essential skills that students need to thrive in complex, data-driven environments, and our study provides insights into whether a capstone course can equip students with these skills. To examine these issues, we …
Decarbonising Digital Infrastructure And Urban Sustainability In The Case Of Data Centres, Felicia H. M. Liu, Karen P. Y. Lai, Bertrand Seah, Winston T. L. Chow
Decarbonising Digital Infrastructure And Urban Sustainability In The Case Of Data Centres, Felicia H. M. Liu, Karen P. Y. Lai, Bertrand Seah, Winston T. L. Chow
Research Collection College of Integrative Studies
This paper critically assesses the complex interplay between urban transitions of digitisation and sustainability. Building on a mixed-method research design, we unpack the challenges of decarbonising digital infrastructure while attending to urban sustainability goals in a land- and water-scarce country facing significant physical climate risks. We identify transferrable lessons on the economic, technological, and environmental synergies and trade-offs behind data centre development and argue that stewarding the global data centre sector towards sustainability requires an ecosystem-wide approach. We identify implementation gaps across five key dimensions: technological innovation, policy and regulation, finance, infrastructure, and people. We find that the progress and …
Characterising Reproducibility Debt In Scientific Software: A Systematic Literature Review, Zara Hassan, Christoph Treude, Michael Norrish, Graham Williams, Alex Potanin
Characterising Reproducibility Debt In Scientific Software: A Systematic Literature Review, Zara Hassan, Christoph Treude, Michael Norrish, Graham Williams, Alex Potanin
Research Collection School Of Computing and Information Systems
Context: In scientific software, the inability to reproduce results is often due to technical issues and challenges in recreating the full computational workflow from the original analysis. We conceptualise this problem as Reproducibility Debt (RpD). Much research has been performed to propose solutions to tackle these issues across various computational science disciplines. It is essential to identify and accumulate existing knowledge on reproducibility issues and state-of-the-art solutions so as to provide researchers and practitioners with information that enables further research activities and RpD management in practice. Objective: In the context of scientific software, we aim to characterise RpD by providing …
Trait Mindfulness Is Associated With Enhanced Daily Affectivity And Cognition Independent Of Daily Stressors Exposure: Insights From Large-Scale Daily Diary Studies In The Us And Singapore, Yi Jing Chua, Andree Hartanto, Nadyanna M. Majeed
Trait Mindfulness Is Associated With Enhanced Daily Affectivity And Cognition Independent Of Daily Stressors Exposure: Insights From Large-Scale Daily Diary Studies In The Us And Singapore, Yi Jing Chua, Andree Hartanto, Nadyanna M. Majeed
Research Collection School of Social Sciences
Trait mindfulness has been linked to various adaptive outcomes, including attenuated affective and cognitive responses to laboratory-induced stress. However, the role of trait mindfulness as a resilience factor against daily stressors exposures is less established. Across 2 studies, multilevel analysis was used to examine the relationships between trait mindfulness and daily affect and cognition, as well as affective and cognitive reactivity to and recovery from everyday stressor exposure. Trait mindfulness was significantly associated with higher daily positive affect in both studies, lower negative affect and cognitive failure, and lower cognitive reactivity to daily stressor exposure in Study 2. However, trait …
Registered Replication Report: Study 3 From Trafimow And Hughes (2012), Sean C. Rife, Et Al
Registered Replication Report: Study 3 From Trafimow And Hughes (2012), Sean C. Rife, Et Al
Research Collection School of Social Sciences
Terror-management theory (TMT) proposes that when people are made aware of their own death, they are more likely to endorse cultural values. TMT is a staple of social psychology, featured prominently in textbooks and the subject of much research. The implications associated with TMT are significant because its advocates claim it can partially explain cultural conflicts, intergroup antagonisms, and even war. However, considerable ambiguity regarding effect size exists, and no preregistered replication of death-thought-accessibility findings exists. Moreover, there is debate regarding the role of time delay between the manipulation of mortality salience and assessment of key measures. We present results …
Ageing In Place: The Key To Receiving A Superaged Society, Paulin Tay Straughan, Yi Wen (Chen Yiwen) Tan, Qi Ting, Zidane Tiew, Zeyu Zheng, Rachel Wen Yi Ngu, Wei Tin Hiah
Ageing In Place: The Key To Receiving A Superaged Society, Paulin Tay Straughan, Yi Wen (Chen Yiwen) Tan, Qi Ting, Zidane Tiew, Zeyu Zheng, Rachel Wen Yi Ngu, Wei Tin Hiah
Research Collection School of Social Sciences
Ageing in place is the ability to remain in one’s community, where living conditions foster a sense of attachment that enhances holistic well-being. To facilitate this, both the built and social environments within which the home is nested must be conducive to successful ageing. This paper deconstructs the merits of ageing in place, specifically how attachment to the lived environment contributes to holistic well-being. We analysed data from 6020 participants in the Singapore Life Panel® using path models, where we examined three dimensions of ageing in place: place identity, continuity, and social inclusion. Five path analyses show that two dimensions …
What Is A Digital Twin Anyway? Deriving The Definition For The Built Environment From Over 15,000 Scientific Publications, Abdelrahman Mahmoud, Edgardo Macatulad, Binyu Lei, Matias Quintana, Clayton Miller, Filip Biljecki
What Is A Digital Twin Anyway? Deriving The Definition For The Built Environment From Over 15,000 Scientific Publications, Abdelrahman Mahmoud, Edgardo Macatulad, Binyu Lei, Matias Quintana, Clayton Miller, Filip Biljecki
Research Collection College of Integrative Studies
The concept of Digital Twins (DT) has attracted significant attention across various domains, particularly within the built environment. However, there is a sheer volume of definitions and the terminological consensus remains out of reach. The lack of a universally accepted definition leads to ambiguities in their conceptualization and implementation, and may cause miscommunication for both researchers and practitioners.We employed Natural Language Processing (NLP) techniques to systematically extract and analyze definitions of DTs from a corpus of more than 15,000 full-text articles spanning diverse disciplines. The study compares these findings with insights from an expert survey that included 52 experts. The …
The Insurgent Smart City: How A Social Movement Created An Alternative Imaginary Of The Smart City, Andrew Stokols
The Insurgent Smart City: How A Social Movement Created An Alternative Imaginary Of The Smart City, Andrew Stokols
Research Collection College of Integrative Studies
Urban scholars have critiqued smart cities for their association with neoliberal governance, narrow focus on quantifiable aspects of urban systems, and failure to incorporate citizens’ needs or aspirations. The “smart city” remains a contested concept and as such is subject to reappropriation. Here, I analyze the case of an urban social movement, the 2019–2020 Hong Kong Anti-ELAB protests, as an alternative, “insurgent smart city.” Following from an earlier network analysis of Telegram channels used during the protests, I show how the communications system underpinning much of the protest action simultaneously enabled coordination while also remaining open to grassroots decision-making and …
On The Probability Of Necessity And Sufficiency Of Explaining Graph Neural Networks: A Lower Bound Optimization Approach, Ruichu Cai, Yuxuan Zhu, Xuexin Chen, Yuan Fang, Min Wu, Jie Qiao, Zhifeng Hao
On The Probability Of Necessity And Sufficiency Of Explaining Graph Neural Networks: A Lower Bound Optimization Approach, Ruichu Cai, Yuxuan Zhu, Xuexin Chen, Yuan Fang, Min Wu, Jie Qiao, Zhifeng Hao
Research Collection School Of Computing and Information Systems
The explainability of Graph Neural Networks (GNNs) is critical to various GNN applications, yet it remains a significant challenge. A convincing explanation should be both necessary and sufficient simultaneously. However, existing GNN explaining approaches focus on only one of the two aspects, necessity or sufficiency, or a heuristic trade-off between the two. Theoretically, the Probability of Necessity and Sufficiency (PNS) holds the potential to identify the most necessary and sufficient explanation since it can mathematically quantify the necessity and sufficiency of an explanation. Nevertheless, the difficulty of obtaining PNS due to non-monotonicity and the challenge of counterfactual estimation limit its …
Chatcrs: Incorporating External Knowledge And Goal Guidance For Llm-Based Conversational Recommender Systems, Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li
Chatcrs: Incorporating External Knowledge And Goal Guidance For Llm-Based Conversational Recommender Systems, Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li
Research Collection School Of Computing and Information Systems
This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1) generating grounded responses with recommendation-oriented knowledge, or 2) proactively leading the conversations through different dialogue goals. In this work, we first analyze those limitations through a comprehensive evaluation, showing the necessity of external knowledge and goal guidance which contribute significantly to the recommendation accuracy and language quality. In light of this finding, we propose a novel ChatCRS framework to decompose the complex CRS task into …
Rethinking Neural Multi-Objective Combinatorial Optimization Via Neat Weight Embedding, Jinbiao Chen, Zhiguang Cao, Jiahai Wang, Yaoxin Wu, Hanzhang Qin, Zizhen Zhang, Yue-Jiao Gong
Rethinking Neural Multi-Objective Combinatorial Optimization Via Neat Weight Embedding, Jinbiao Chen, Zhiguang Cao, Jiahai Wang, Yaoxin Wu, Hanzhang Qin, Zizhen Zhang, Yue-Jiao Gong
Research Collection School Of Computing and Information Systems
Recent decomposition-based neural multi-objective combinatorial optimization (MOCO) methods struggle to achieve desirable performance. Even equipped with complex learning techniques, they often suffer from significant optimality gaps in weight-specific subproblems. To address this challenge, we propose a neat weight embedding method to learn weight-specific representations, which captures weight-instance interaction for the subproblems and was overlooked by most current methods. We demonstrate the potentials of our method in two instantiations. First, we introduce a succinct addition model to learn weight-specific node embeddings, which surpassed most existing neural methods. Second, we design an enhanced conditional attention model to simultaneously learn the weight embedding …
Learning-Guided Bi-Objective Evolutionary Optimization For Green Municipal Waste Collection Vehicle Routing, Shubing Liao, Yixin Xu, Yunyun Niu, Zhiguang Cao
Learning-Guided Bi-Objective Evolutionary Optimization For Green Municipal Waste Collection Vehicle Routing, Shubing Liao, Yixin Xu, Yunyun Niu, Zhiguang Cao
Research Collection School Of Computing and Information Systems
Waste management has emerged as a critical issue in modern society, where vehicles are scheduled to visit multiple locations for waste collection and transport. This study focuses on a key problem in waste management: route optimization of waste collection vehicles, and formulate it as a bi-objective vehicle routing problem with stochastic demand (VRPSD), aiming to minimizing both total costs and carbon emissions. Although previous studies have significantly advanced our understanding of solving similar problems, the lack of real-world data and limited problem-solving capabilities still restrict the practical applicability of existing methods. To bridge this research gap, this study designed a …
Agentstudio: A Toolkit For Building General Virtual Agents, Longtao Zheng, Zhiyuan Huang, Zhenghai Xue, Xinrun Wang, Bo An, Shuicheng Yan
Agentstudio: A Toolkit For Building General Virtual Agents, Longtao Zheng, Zhiyuan Huang, Zhenghai Xue, Xinrun Wang, Bo An, Shuicheng Yan
Research Collection School Of Computing and Information Systems
General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments. However, existing environments are often domain-specific and require complex setups, which limits agent development and evaluation in real-world settings. As a result, current evaluations lack in-depth analyses that decompose fundamental agent capabilities. We introduce AgentStudio, a trinity of environments, tools, and benchmarks to address these issues. AgentStudio provides a lightweight, interactive environment with highly generic observation and action spaces, e.g., video observations and GUI/API actions. It integrates tools for creating online benchmark tasks, annotating GUI elements, and labeling actions in videos. Based …
Estimation And Inference In A Possibly Multicointegrated System With A Fixed Number Of Instruments, Yixiao Sun, Peter C. B. Phillips, Igor L. Kheifets
Estimation And Inference In A Possibly Multicointegrated System With A Fixed Number Of Instruments, Yixiao Sun, Peter C. B. Phillips, Igor L. Kheifets
Research Collection School Of Economics
This paper shows that the mixed normal asymptotic limit of the trend IV estimator with a fixed number of deterministic instruments (fTIV) holds in both singular (multicointegrated) and nonsingular cointegration systems, thereby relaxing the exogeneity condition in (Phillips and Kheifets, 2024, Theorem 1(ii)). The mixed normality of the limiting distribution of fTIV allows for asymptotically pivotal F and t tests about the cointegration parameters and for simple efficiency comparisons of the estimators for different numbers K of instruments, as well as comparisons with the trend IV estimator when K→∞ with the sample size.
Statistical Inference For Noisy Matrix Completion Incorporating Auxiliary Information, Shujie Ma, Po-Yao Niu, Yichong Zhang, Yinchu Zhu
Statistical Inference For Noisy Matrix Completion Incorporating Auxiliary Information, Shujie Ma, Po-Yao Niu, Yichong Zhang, Yinchu Zhu
Research Collection School Of Economics
This article investigates statistical inference for noisy matrix completion in a semi-supervised model when auxiliary covariates are available. The model consists of two parts. One part is a low-rank matrix induced by unobserved latent factors; the other part models the effects of the observed covariates through a coefficient matrix which is composed of high-dimensional column vectors. We model the observational pattern of the responses through a logistic regression of the covariates, and allow its probability to go to zero as the sample size increases. We apply an iterative least squares (LS) estimation approach in our considered context. The iterative LS …
From A Learning To A Smart Nation: The Rise Of The Digitalization Megatrend And Singapore's Development, Siu Loon Hoe
From A Learning To A Smart Nation: The Rise Of The Digitalization Megatrend And Singapore's Development, Siu Loon Hoe
Research Collection School Of Computing and Information Systems
Purpose: The purpose of this article is to discuss the “learning nation” concept and examine the characteristics and implications of using the “learning” premodifier in this nation-building program. Design/methodology/approach: This article reviews how the “learning” aspect is inter-related to a series of national information and communication technology masterplans and includes a comparative analysis of the related premodifier “smart” as Singapore sets forth its ambition to become a “smart nation” as part of the digitalization megatrend. A print media indicator and Google Trends form part of the methodology to ascertain the rise of digital technology over a certain period. The former …
Enmob: Unveil The Behavior With Multi-Flow Analysis Of Encrypted App Traffic, Mengmeng Ge, Ruitao Feng, Likun Liu, Xiangzhan Yu, Sachidananda Vinay, Xiaofei Xie, Yang Liu
Enmob: Unveil The Behavior With Multi-Flow Analysis Of Encrypted App Traffic, Mengmeng Ge, Ruitao Feng, Likun Liu, Xiangzhan Yu, Sachidananda Vinay, Xiaofei Xie, Yang Liu
Research Collection School Of Computing and Information Systems
In the contemporary digital landscape, mobile applications have become the predominant conduit for internet connectivity and daily tasks. Simultaneously, the advent of application encryption technology has safeguarded users’ privacy. However, this encryption, while fortifying privacy, introduces challenges to security by hindering the effective management of network applications within encrypted data streams. Conventional detection methods for encrypted application traffic, relying heavily on statistical metrics like payload, packet size, and distribution, are constrained to single traffic flows, often yielding results of limited specificity. To address this limitation, our paper introduces an innovative approach that elucidates the multi-flow nature of application behavior traffic …
Verification Of Bit-Flip Attacks Against Quantized Neural Networks, Yedi Zhang, Lei Huang, Pengfei Gao, Fu Song, Jun Sun, Jin Song Dong
Verification Of Bit-Flip Attacks Against Quantized Neural Networks, Yedi Zhang, Lei Huang, Pengfei Gao, Fu Song, Jun Sun, Jin Song Dong
Research Collection School Of Computing and Information Systems
In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage memory system to induce harmful behavior), has emerged as a relevant area of research. Existing studies suggest that quantization may serve as a viable defense against such attacks. Recognizing the documented susceptibility of real-valued neural networks to such attacks and the comparative robustness of quantized neural networks (QNNs), in this work, we introduce BFAVerifier, the first verification framework designed to formally verify the absence of bit-flip attacks against …
The Lao Penal Code: A Comparative Discourse, Wing Cheong Chan, Wing Cheong Chan, Phanthasak Mingnakhone, Perrine Simon, Stanley Yeo
The Lao Penal Code: A Comparative Discourse, Wing Cheong Chan, Wing Cheong Chan, Phanthasak Mingnakhone, Perrine Simon, Stanley Yeo
Research Collection Yong Pung How School Of Law
This book comprises a commentary on the criminal law of Laos dealing with the general principles of criminal responsibility, and describing the main offences against the person and property under the Lao Penal Code 2017.
Verifying Timed Properties Of Programs In Iot Nodes Using Parametric Time Petri Nets, Étienne André, Jean-Luc Béchennec, Sudipta Chattopadhyay, Sebastien Faucou, Didier Lime, Dylan Marinho, Olivier H. Roux, Jun Sun
Verifying Timed Properties Of Programs In Iot Nodes Using Parametric Time Petri Nets, Étienne André, Jean-Luc Béchennec, Sudipta Chattopadhyay, Sebastien Faucou, Didier Lime, Dylan Marinho, Olivier H. Roux, Jun Sun
Research Collection School Of Computing and Information Systems
The analysis of timed properties of programs is a complex task, as it is highly dependent on both the software and the hardware. In this work, we propose a framework for modeling with timed formal models the execution of programs, taking into account the micro-architecture of the machine on which it executes. We model both the program, at the instruction set architecture level, and the hardware, including the processor micro-architecture, using time Petri nets. Our implementation uses the ARM Cortex-M instruction set architecture and a hardware architecture representative of microcontrollers used in IoT nodes. The whole translation is fully automated …
Democratic Training Against Universal Adversarial Perturbations, Bing Sun, Jun Sun, Wei Zhao
Democratic Training Against Universal Adversarial Perturbations, Bing Sun, Jun Sun, Wei Zhao
Research Collection School Of Computing and Information Systems
Despite their advances and success, real-world deep neural networks are known to be vulnerable to adversarial attacks. Universal adversarial perturbation, an inputagnostic attack, poses a serious threat for them to be deployed in security-sensitive systems. In this case, a single universal adversarial perturbation deceives the model on a range of clean inputs without requiring input-specific optimization, which makes it particularly threatening. In this work, we observe that universal adversarial perturbations usually lead to abnormal entropy spectrum in hidden layers, which suggests that the prediction is dominated by a small number of “feature” in such cases (rather than democratically by many …
Ada-Gen: Iterative And Incremental Generation Of Full-Stack Apps For Learning Agile/Devops Software Development Practices, Nguyen Binh Duong Ta
Ada-Gen: Iterative And Incremental Generation Of Full-Stack Apps For Learning Agile/Devops Software Development Practices, Nguyen Binh Duong Ta
Research Collection School Of Computing and Information Systems
To learn Agile/DevOps practices effectively, students need to apply them in an actual software development project. This is challenging if students are mostly from non-computing backgrounds and they do not have time in the curriculum to learn programming and related tools. Therefore, it is important to help students who do not possess programming foundations to develop fully functional software during the process of learning Agile/DevOps concepts. We noted that existing low-code/no-code app development platforms have not been designed to teach Agile/DevOps practices. On the other hand, recent AI-based tools for code generation such as GitHub Copilot have been built mainly …
On Unraveling Student Resilience And Academic Performance In Higher Education, Aldy Gunawan, Ee-Peng Lim, Audrey Tedja Widjaja, William Tov, James Foo, Lieven Lode E. Demeester
On Unraveling Student Resilience And Academic Performance In Higher Education, Aldy Gunawan, Ee-Peng Lim, Audrey Tedja Widjaja, William Tov, James Foo, Lieven Lode E. Demeester
Research Collection School Of Computing and Information Systems
The transition period from pre-tertiary to higher education levels is critical. We explore the role of resilience by conducting a survey to investigate students’ resilience and the relationship with overall academic performance, learning experience, and well-being. This effort is part of an initiative to develop strategies for better student engagement in the academic program, enhance their resilience, and prepare them for a competitive job market. We conclude that (i) high-resilience students are associated with better life satisfaction and are likely to perform well academically, (ii) a favorable learning environment supports students to study and perform well in the university, and …
Towards Understanding Why Fixmatch Generalizes Better Than Supervised Learning, Jingyang Li, Jiachun Pan, Vincent Tan, Kim-Chuan Toh, Pan Zhou
Towards Understanding Why Fixmatch Generalizes Better Than Supervised Learning, Jingyang Li, Jiachun Pan, Vincent Tan, Kim-Chuan Toh, Pan Zhou
Research Collection School Of Computing and Information Systems
Semi-supervised learning (SSL), exemplified by FixMatch (Sohn et al., 2020), has shown significant generalization advantages over supervised learning (SL), particularly in the context of deep neural networks (DNNs). However, it is still unclear, from a theoretical standpoint, why FixMatch-like SSL algorithms generalize better than SL on DNNs. In this work, we present the first theoretical justification for the enhanced test accuracy observed in FixMatch-like SSL applied to DNNs by taking convolutional neural networks (CNNs) on classification tasks as an example. Our theoretical analysis reveals that the semantic feature learning processes in FixMatch and SL are rather different. In particular, FixMatch …
Capo: Cooperative Plan Optimization For Efficient Embodied Multi-Agent Cooperation, Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees Snoek, Jan-Jakob Sonke, Efstratios Gavves
Capo: Cooperative Plan Optimization For Efficient Embodied Multi-Agent Cooperation, Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees Snoek, Jan-Jakob Sonke, Efstratios Gavves
Research Collection School Of Computing and Information Systems
In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without long-term strategic and cooperative planning, leading to redundant steps, failures, and even serious repercussions in complex tasks like search-and-rescue missions where discussion and cooperative plan are crucial. To solve this issue, we propose Cooperative Plan Optimization (CaPo) to enhance the cooperation efficiency of LLM-based embodied agents. Inspired by human cooperation schemes, CaPo improves cooperation efficiency with two phases: 1) meta-plan generation, and 2) progress-adaptive meta-plan and …
Configx: Modular Configuration For Evolutionary Algorithms Via Multitask Reinforcement Learning, Hongshu Guo, Zeyuan Ma, Jiacheng Chen, Yining Ma, Zhiguang Cao, Xinglin Zhang, Yue-Jiao Gong
Configx: Modular Configuration For Evolutionary Algorithms Via Multitask Reinforcement Learning, Hongshu Guo, Zeyuan Ma, Jiacheng Chen, Yining Ma, Zhiguang Cao, Xinglin Zhang, Yue-Jiao Gong
Research Collection School Of Computing and Information Systems
Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enhancing their performance and adaptability across various BBO instances. However, they are often tailored to a specific EA, which limits their generalizability and necessitates retraining or redesigns for different EAs and optimization problems. To address this limitation, we introduce ConfigX, a new paradigm of the MetaBBO framework that is capable of learning a universal configuration agent (model) for boosting diverse EAs. To achieve so, our ConfigX first leverages a novel modularization system that enables the flexible combination of …
Neural Multi-Objective Combinatorial Optimization Via Graph-Image Multimodal Fusion, Jinbiao Chen, Jiahai Wang, Zhiguang Cao, Yaoxin Wu
Neural Multi-Objective Combinatorial Optimization Via Graph-Image Multimodal Fusion, Jinbiao Chen, Jiahai Wang, Zhiguang Cao, Yaoxin Wu
Research Collection School Of Computing and Information Systems
Existing neural multi-objective combinatorial optimization (MOCO) methods still exhibit an optimality gap since they fail to fully exploit the intrinsic features of problem instances. A significant factor contributing to this shortfall is their reliance solely on graph-modal information. To overcome this, we propose a novel graph-image multimodal fusion (GIMF) framework that enhances neural MOCO methods by integrating graph and image information of the problem instances. Our GIMF framework comprises three key components: (1) a constructed coordinate image to better represent the spatial structure of the problem instance, (2) a problem-size adaptive resolution strategy during the image construction process to improve …
Llm-Enhanced Multiple Instance Learning For Joint Rumor And Stance Detection With Social Context Information, Ruichao Yang, Jing Ma, Wei Gao, Hongzhan Lin
Llm-Enhanced Multiple Instance Learning For Joint Rumor And Stance Detection With Social Context Information, Ruichao Yang, Jing Ma, Wei Gao, Hongzhan Lin
Research Collection School Of Computing and Information Systems
The proliferation of misinformation, such as rumors on social media, has drawn significant attention, prompting various expressions of stance among users. Although rumor detection and stance detection are distinct tasks, they can complement each other. Rumors can be identified by cross-referencing stances in related posts, and stances are influenced by the nature of the rumor. However, existing stance detection methods often require post-level stance annotations, which are costly to obtain. We propose a novel LLM-enhanced Multiple Instance Learning (MIL) approach to jointly predict post stance and claim class labels, supervised solely by claim labels, using an undirected microblog propagation model. …
Sita: Structurally Imperceptible And Transferable Adversarial Attacks For Stylized Image Generation, Jingdan Kang, Haoxin Yang, Yan Cai, Huaidong Zhang, Xuemiao Xu, Yong Du, Shengfeng He
Sita: Structurally Imperceptible And Transferable Adversarial Attacks For Stylized Image Generation, Jingdan Kang, Haoxin Yang, Yan Cai, Huaidong Zhang, Xuemiao Xu, Yong Du, Shengfeng He
Research Collection School Of Computing and Information Systems
Image generation technology has brought significant advancements across various fields but has also raised concerns about data misuse and potential rights infringements, particularly with respect to creating visual artworks. Current methods aimed at safeguarding artworks often employ adversarial attacks. However, these methods face challenges such as poor transferability, high computational costs, and the introduction of noticeable noise, which compromises the aesthetic quality of the original artwork. To address these limitations, we propose a Structurally Imperceptible and Transferable Adversarial (SITA) attacks. SITA leverages a CLIP-based destylization loss, which decouples and disrupts the robust style representation of the image. This disruption hinders …