Digital Commons Network^™

Generative Semi-Supervised Graph Anomaly Detection, Hezhe Qiao, Qingsong Wen, Xiaoli Li, Ee-Peng Lim, Guansong Pang

Research Collection School Of Computing and Information Systems

This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the extensively explored unsupervised setting with a fully unlabeled graph. We reveal that having access to the normal nodes, even just a small percentage of normal nodes, helps enhance the detection performance of existing unsupervised GAD methods when they are adapted to the semi-supervised setting. However, their utilization of these normal nodes is limited. In this paper we propose a novel Generative GAD approach (namely GGAD) for the semi-supervised scenario to better exploit the …

Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games, The Viet Bui, Tien Mai, Hong Thanh Nguyen

Research Collection School Of Computing and Information Systems

Training agents in multi-agent games presents significant challenges due to their intricate nature. These challenges are exacerbated by dynamics influenced not only by the environment but also by strategies of opponents. Existing methods often struggle with slow convergence and instability. To address these challenges, we harness the potential of imitation learning (IL) to comprehend and anticipate actions of the opponents, aiming to mitigate uncertainties with respect to the game dynamics. Our key contributions include: (i) a new multi-agent IL model for predicting next moves of the opponents --- our model works with hidden actions of opponents and local observations; (ii) …

Sampdetox : Black-Box Backdoor Defense Via Perturbation-Based Sample Detoxification, Yanxin Yang, Chentao Jia, Dengke Yan, Ming Hu, Tianlin Li, Xiaofei Xie, Xian Wei, Mingsong Chen

Research Collection School Of Computing and Information Systems

The advancement of Machine Learning has enabled the widespread deployment of Machine Learning as a Service (MLaaS) applications. However, the untrustworthy nature of third-party ML services poses backdoor threats. Existing defenses in MLaaS are limited by their reliance on training samples or white-box model analysis, highlighting the need for a black-box backdoor purification method. In our paper, we attempt to use diffusion models for purification by introducing noise in a forward diffusion process to destroy backdoors and recover clean samples through a reverse generative process. However, since a higher noise also destroys the semantics of the original samples, it still …

Collaboration! Towards Robust Neural Methods For Routing Problems, Jianan Zhou, Yaoxin Wu, Zhiguang Cao, Wen Song, Jie Zhang, Zhiqi Shen

Research Collection School Of Computing and Information Systems

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues – their performance significantly deteriorates on clean instances with crafted perturbations. To enhance robustness, we propose an ensemble-based Collaborative Neural Framework (CNF) w.r.t. the defense of neural VRP methods, which is crucial yet underexplored in the literature. Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances. A neural router is designed to adeptly distribute training instances among models, enhancing …

Flexfl: Heterogeneous Federated Learning Via Apoz-Guided Flexible Pruning In Uncertain Scenarios, Zekai Chen, Chentao Jia, Ming Hu, Xiaofei Xie, Anran Li, Mingsong Chen

Research Collection School Of Computing and Information Systems

Along with the increasing popularity of Deep Learning (DL) techniques, more and more Artificial Intelligence of Things (AIoT) systems are adopting federated learning (FL) to enable privacy-aware collaborative learning among AIoT devices. However, due to the inherent data and device heterogeneity issues, existing FL-based AIoT systems suffer from the model selection problem. Although various heterogeneous FL methods have been investigated to enable collaborative training among heterogeneous models, there is still a lack of i) wise heterogeneous model generation methods for devices, ii) consideration of uncertain factors, and iii) performance guarantee for large models, thus strongly limiting the overall FL performance. …

Inverse Factorized Soft Q-Learning For Cooperative Multi-Agent Imitation Learning, The Viet Bui, Tien Mai, Thanh Nguyen

Research Collection School Of Computing and Information Systems

This paper concerns imitation learning (IL) in cooperative multi-agent systems.The learning problem under consideration poses several challenges, characterized by high-dimensional state and action spaces and intricate inter-agent dependencies. In a single-agent setting, IL was shown to be done efficiently via an inverse soft-Q learning process. However, extending this framework to a multi-agent context introduces the need to simultaneously learn both local value functions to capture local observations and individual actions, and a joint value function for exploiting centralized learning.In this work, we introduce a new multi-agent IL algorithm designed to address these challenges. Our approach enables thecentralized learning by leveraging …

A Community-Driven Framework To Evaluate Factors Influencing Nft Buyers, Yi Meng Lau, Ping Fan Ke

Research Collection School Of Computing and Information Systems

This study examines the pivotal role of community-driven social dynamics in shaping non-fungible tokens (NFT) buyers’ purchasing intentions and the increasing social significance of digital assets. Building on prior research in online word-of-mouth, we propose a comprehensive framework that integrates technological, personal, social, economic, and political factors influencing NFT purchases. The framework emphasizes the importance of service providers, personalization, perceived value, and associated risks, while also providing insights into how online word-of-mouth and community dynamics impact these aspects. As a preliminary exploration, this research lays the foundation for future empirical studies to validate the framework and assess its applicability across …

Towards General Conceptual Model Editing Via Adversarial Representation Engineering, Yihao Zhang, Zeming Wei, Jun Sun, Meng Sun

Research Collection School Of Computing and Information Systems

Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their behaviors through the lens of inner representation. However, developing practical and efficient methods for applying these representations for general and flexible model editing remains challenging. In this work, we explore how to leverage insights from representation engineering to guide the editing of LLMs by deploying a representation sensor as an editing oracle. We first identify the importance of a robust and reliable sensor during editing, then propose an …

Ali-Agent: Assessing Llms’ Alignment With Human Values Via Agent-Based Evaluation, Jingnan Zheng, Han Wang, Tai D. Nguyen, An Zhang, Jun Sun, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, current evaluation benchmarks predominantly employ expertdesigned contextual scenarios to assess how well LLMs align with human values. However, the labor-intensive nature of these benchmarks limits their test scope, hindering their ability to generalize to the extensive variety of open-world use cases and identify rare but crucial long-tail risks. Additionally, these static tests fail to adapt to the rapid evolution of LLMs, making it hard to evaluate timely alignment issues. To address these challenges, …

Question-Attentive Review-Level Explanation For Neural Rating Regression, Trung Hoang Le, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Recommendation explanations help to improve their acceptance by end users. Explanations come in many different forms. One that is of interest here is presenting an existing review of the recommended item as the explanation. The challenge is in selecting a suitable review, which is customarily addressed by assessing the relative importance or “attention” of each review to the recommendation objective. Our focus is improving review-level explanation by leveraging additional information in the form of questions and answers (QA). The proposed framework employs QA in an attention mechanism that aligns reviews to various QAs of an item and assesses their contribution …

Replay-And-Forget-Free Graph Class-Incremental Learning: A Task Profiling And Prompting Approach, Chaoxi Niu, Guansong Pang, Ling Chen, Bing Liu

Research Collection School Of Computing and Information Systems

Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but needs to deal with graph tasks (e.g., node classification in a graph). The key characteristic of CIL lies in the absence of task identifiers (IDs) during inference, which causes a significant challenge in separating classes from different tasks (i.e., inter-task class separation). Being able to accurately predict the task IDs can help address this issue, but it is a challenging problem. In this paper, we show theoretically that accurate task ID …

Long-Tailed Out-Of-Distribution Detection Via Normalized Outlier Distribution Adaptation, Wenjun Miao, Guansong Pang, Jin Zheng, Xiao Bai

Research Collection School Of Computing and Information Systems

Onekeychallenge in Out-of-Distribution (OOD) detection is the absence of groundtruth OOD samples during training. One principled approach to address this issue is to use samples from external datasets as outliers (i.e., pseudo OOD samples) to train OOD detectors. However, we find empirically that the outlier samples often present a distribution shift compared to the true OOD samples, especially in LongTailed Recognition (LTR) scenarios, where ID classes are heavily imbalanced, i.e., the true OOD samples exhibit very different probability distribution to the head and tailed ID classes from the outliers. In this work, we propose a novel approach, namely normalized outlier …

Generative Artificial Intelligence In Business Higher Education: A Focus Group Study, Xuenan Huo, Keng Siau

Research Collection School Of Computing and Information Systems

This research investigates the opportunities and challenges of integrating generative artificial intelligence (GenAI) into business higher education, drawing insights from an asynchronous focus group research study with doctoral students who serve dual roles as both learners and educators. Key opportunities identified through thematic analysis include knowledge acquisition, intelligent co-ideation, supportive augmentation, and personalized learning. Challenges identified include AI trustworthiness, cognitive dependency, human value, policy and instruction, assessment integrity, and identity management. This study clarifies GenAI’s specific role in business education and provides practical insights for effectively integrating GenAI to enhance learning outcomes and address emerging challenges. An analysis theory on …

Meta-Entrepreneurship: An Analysis Theory On Integrating Generative Ai, Agentic Ai, And Metaverse For Entrepreneurship, Yingying Zhang, Keng Siau

Research Collection School Of Computing and Information Systems

Metaverse entrepreneurship has emerged as an innovative topic alongside the development of generative AI, agentic AI and metaverse. This study conceptualizes meta-entrepreneurship as a novel form of entrepreneurial activity that enables value creation within virtual and physical realms and proposes an analytical theoretical framework based on a systematic literature review, observations, and focus group study. Our framework is structured around three layers (infrastructure, content, and experience) and two domains (metaverse-based operational domain and AI-based production domain), aims to conceptualize “what is meta-entrepreneurship” and identify new possibilities. The research highlights the multifaceted impact of meta-entrepreneurship on individuals, corporations, industries, societies, and …

Safety Through Feedback In Constrained Rl, Shashank Reddy Chirra, Pradeep Varakantham, Praveen Paruchuri

Research Collection School Of Computing and Information Systems

In safety-critical RL settings, the inclusion of an additional cost function is often favoured over the arduous task of modifying the reward function to ensure the agent's safe behaviour. However, designing or evaluating such a cost function can be prohibitively expensive. For instance, in the domain of self-driving, designing a cost function that encompasses all unsafe behaviours (e.g., aggressive lane changes, risky overtakes) is inherently complex, it must also consider all the actors present in the scene making it expensive to evaluate. In such scenarios, the cost function can be learned from feedback collected offline in between training rounds. This …

Converting Vocal Performances Into Sheet Music Leveraging Large Language Models, Jinjing Jiang, Nicole Teo, Haibo Pen, Seng-Beng Ho, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Advanced natural language processing (NLP) models are increasingly applied in music composition and performance, particularly for generating vocal melodies and simulating singing voices. While NLP techniques have been effective in analyzing vocal performance data to assess quality and style, the automatic transcription of vocal performances into sheet music remains a significant challenge. Manual transcription tools often fall short due to the intricate dynamics of vocal expression. This study tackles the automation of vocal performance transcription into sheet music using innovative techniques, including large language models (LLMs). We propose a method to translate vocal audio input into display-ready sheet music effectively. …

Unsupervised Modality Adaptation With Text-To-Image Diffusion Models For Semantic Segmentation, Ruihao Xia, Yu Liang, Peng-Tao Jiang, Hao Zhang, Bo Li, Yang Tang, Pan Zhou

Research Collection School Of Computing and Information Systems

Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation hinders their performance and restricts their application in real-world multimodal scenarios. To address this issue, we propose Modality Adaptation with text-toimage Diffusion Models (MADM) for semantic segmentation task which utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model’s cross-modality capabilities. Specifically, MADM comprises two key complementary components to tackle major challenges. First, due to the large modality gap, using one modal data to generate …

Lova3 : Learning To Visual Question Answering, Asking And Assessment, Henry Hengyuan Zhao, Pan Zhou, Difei Gao, Bai Shou, Mike Zheng Shou

Research Collection School Of Computing and Information Systems

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. Current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. Inspired by the human learning mechanism, we introduce LOVA3 , an innovative framework named “Learning tO Visual question Answering, Asking and Assessment,” designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming …

4-Bit Shampoo For Memory-Efficient Network Training, Sike Wang, Pan Zhou, Jia Li, Hua Huang

Research Collection School Of Computing and Information Systems

Second-order optimizers, maintaining a matrix termed a preconditioner, are superior to first-order optimizers in both theory and practice. The states forming the preconditioner and its inverse root restrict the maximum size of models trained by second-order optimizers. To address this, compressing 32-bit optimizer states to lower bitwidths has shown promise in reducing memory usage. However, current approaches only pertain to first-order optimizers. In this paper, we propose the first 4-bit second-order optimizers, exemplified by 4-bit Shampoo, maintaining performance similar to that of 32-bit ones. We show that quantizing the eigenvector matrix of the preconditioner in 4-bit Shampoo is remarkably better …

Unified Generative And Discriminative Training For Multi-Modal Large Language Models, Wei Chow, Juncheng Li, Kaihang Pan, Qifan Yu, Hao Fei, Zhiqi Ge, Shuai Yang, Siliang Teng, Hanwang Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle various complex tasks, yet issues such as hallucinations and weak object discrimination persist. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval, yet struggles with complex scenarios requiring fine-grained semantic differentiation. This paper addresses these challenges by proposing a unified approach that integrates the strengths of both paradigms. Considering interleaved image-text sequences as the general format of input samples, we introduce a structure-induced training strategy that imposes semantic relationships between input …

Research On The Influence Of Complementary Assets On Innovation Performance Of New R&D Institutions, Yong Li

Dissertations and Theses Collection (Open Access)

Since the development of new R&D institutions in China in the 1990s, they have received advocacy and support from both national and local governments. After more than 20 years of exploration and development, new R&D institutions have gradually developed characteristics such as diversified investment sources, flexible organizational structures, market-oriented operations, and multi-functional coordination. These institutions have increasingly played an active role in promoting scientific and technological innovation and regional economic development. In the research on the development and evolution, modes and mechanisms, and performance and evaluation of new R&D institutions, numerous results have been generated, promoting the construction and development …

The Effect Of Private Placement On Investment Efficiency: Empirical Evidence From The New Refinancing Regulations, Zhiyong Han

Dissertations and Theses Collection (Open Access)

Compared with public offerings, private placements are more attractive to investors due to a lower threshold, a simpler procedure, and a higher success rate of issuance. These advantages make private placements the preferred choice for listed companies seeking to issue additional shares in many capital markets. With the increased prevalence of private placements as a refinancing method, how to effectively leverage raised funds and improve investment efficiency has emerged as a topic under discussion within the academic community. However, whether private placements can affect investment efficiency remains controversial. Moreover, previous studies lack systematic empirical evidence, and endogeneity issues hinder an …

Interactive Known-Item Search In Large Video Corpora, Zhixin Ma

Dissertations and Theses Collection (Open Access)

The surge in video volume makes it challenging to locate a specific target with a single query using automatic video retrieval systems. The interactive video retrieval offers a solution by enabling users to iteratively refine a search. Nevertheless, existing systems often present users with an overwhelming number of similar videos, which can lead to mental fatigue while inspecting results and increase difficulty in providing feedback. This dissertation studies known-item video search and addresses four key challenges. First and foremost, as the link between users and the system, the interaction must be both efficient and effective. To ensure effectiveness, the user’s …

Unravel The University-Enterprise Research Collaboration: Evidence From Multiple Cases, Lihua Luo

Dissertations and Theses Collection (Open Access)

This study elucidates the pivotal determinants of industry-university research collaboration within the chemical industry and delineates its operational modalities, which can offer valuable insights for pertinent theoretical research and practical applications. By employing grounded theory, an in-depth qualitative analysis of several collaborative cases between chemical enterprises and higher education institutions was conducted, which culminated in the construction of a theoretical model for industry–university research collaboration. The findings reveal that the government plays a significant intermediary role in industry–university partnerships by facilitating the smooth progression and commercialization of collaborative endeavors through policy support, financial subsidies, and performance evaluation.

Moreover, the complementarity …

The Double-Edged Effect Of Ceo Maximizing Values And Corporate Litigation Risk, Qing Xu

Dissertations and Theses Collection (Open Access)

Based on the higher-order theoretical perspective, this study explores the nonlinear influence mechanism of CEO value maximization tendency on corporate litigation risk and its boundary conditions. Based on the survey data of 225 CEOs in the Chinese context, it is found that CEO value maximization has a significant U-shaped relationship with corporate litigation risk, which indicates that moderate value pursuit can reduce litigation risk, but excessive pursuit will increase the possibility of risk, verifying the “dual governance effect”. Environmental uncertainty, redundant resources and CEO tenure moderated the U-shaped relationship between CEO value maximization and corporate litigation risk.

The theoretical contribution …

Political Embeddedness And Organizational Resilience: Empirical Investigation And Theorisation Of Institutional Translation Mechanisms In Chinese Private Enterprises, Shuai Shao

Dissertations and Theses Collection (Open Access)

China is governed by the Communist Party of China (CPC), which embodies the nation's core values, mission, and ideological framework. The CPC organization embeddedness represents a distinctive governance arrangement, reflecting the state's Political Integration Imperatives. In the context of significant external shocks such as Covid-19, how does this political embeddedness influence private enterprises' organizational resilience - specifically their capacity to withstand disruptions and their ability to recover? What are the underlying mechanisms driving these effects?

This study employs a mixed-methods approach to investigate how CPC organization embeddedness shapes organizational resilience within China's unique institutional context, and the mechanisms through which …

The Case For Stronger Scrutiny Of The Deductibility Of Crypto Losses, Vincent Ooi

Research Collection Yong Pung How School Of Law

My paper, The Case for Stronger Scrutiny of the Deductibility of Crypto Losses, which was recently published by The Journal of Tax Administration, discusses the issue of crypto losses and risks to the tax base. It submits that tax authorities and national legislatures should step up their scrutiny of the deductibility of crypto losses and proposes some ways in which this can be done in practice.

Exploring Students' Computer-Supported Collaborative Argumentation With Socio-Scientific Issues, Wenli Chen, Yiting Han, Jesmine Tan, Aileen Siew Cheng Chai, Qianru Lyu, Lyna

Research Collection Lee Kong Chian School Of Business

Background: This study examined the effect of computer-supported collaborative argumentation (CSCA) on secondary school students' understanding of socio-scientific issues (SSI). Engaging students in collaborative argumentation is known to help with deepening their understanding of SSI. Methods: In this study, a mixed-method design is used to investigate 84 students' collaborative argumentation processes and outcomes. The statistical analysis, epistemic network analysis and qualitative uptake analysis results showed that CSCA was effective in supporting secondary school students' evidence-based argumentation skills on SSI. Findings and Conclusion: Several cases were presented to show how students engaged in CSCA to explore meaningful learning opportunities and how …

Flexible Vs. Dedicated Technology Choice In The Presence Of Multiproduct Subscription Programs, Liling Lu, Onur Boyabatli, Sarah Yini Gao

Research Collection Lee Kong Chian School Of Business

Recently, automotive manufacturers have started offering multi-car subscription programs that give customers access to a menu of car models with possibility of switching between the models. The maintenance and depreciation costs during the program are borne by the manufacturers before the cars are sold in the pre-owned market. This paper studies how offering such a subscription program shapes the firm’s flexible versus dedicated technology choice and capacity investment decisions. We consider a two-product firm that makes these decisions under uncertain demand in a single subscription period. The firm faces two types of demand based on which product is requested at …

An Integrative, Systematic Review Of The Situational Judgment Test Literature, Sven Kepes, Sheila K. Keener, Filip Lievens, Michael A. Mcdaniel

Research Collection Lee Kong Chian School Of Business

Situational judgment tests (SJTs) are popular assessment approaches that present scenarios describing situations that one may experience in a job. Due to its long history and cross-disciplinary nature, today’s SJT literature is quite fragmented. In this integrative review, we start by systematically taking stock and synthesizing the SJT literature from the different scientific disciplines via bibliometric techniques on 524 unique documents. We identify six literature clusters (i.e., SJTs in the medical sciences, SJTs in personnel selection, methodological issues and SJTs for specific constructs, SJTs to assess emotional intelligence and related constructs, technological advances in SJTs, SJTs for teacher assessment and …