Computer Sciences Commons^™

Marrying Top-K With Skyline Queries: Operators With Relaxed Preference Input And Controllable Output Size, Kyriakos Mouratidis, Keming Li, Bo Tang

Research Collection School Of Computing and Information Systems

The two most common paradigms to identify records of preference in a multi-objective setting rely either on dominance (e.g., the skyline operator) or on a utility function defined over the records' attributes (typically, using a top-k query). Despite their proliferation, each of them has its own palpable drawbacks. Motivated by these drawbacks, we identify three hard requirements for practical decision support, namely, personalization, controllable output size, and flexibility in preference specification. With these requirements as a guide, we combine elements from both paradigms and propose two new operators, ORD and ORU. We perform a qualitative study to demonstrate how they …

Lara : A Light And Anti-Overfitting Retraining Approach For Unsupervised Time Series Anomaly Detection, Feiyi Chen, Zhen Qin, Mengchu Zhou, Yingying Zhang, Shuiguang Deng, Lunting Fan, Guansong Pang, Qingsong Wen

Research Collection School Of Computing and Information Systems

Most of current anomaly detection models assume that the normal pattern remains the same all the time. However, the normal patterns of web services can change dramatically and frequently over time. The model trained on old-distribution data becomes outdated and ineffective after such changes. Retraining the whole model whenever the pattern is changed is computationally expensive. Further, at the beginning of normal pattern changes, there is not enough observation data from the new distribution. Retraining a large neural network model with limited data is vulnerable to overfitting. Thus, we propose a Light Anti-overfitting Retraining Approach (LARA) based on deep variational …

Bi-Objective Dynamic Tugboat Scheduling With Speed Optimization Under Stochastic And Time-Varying Service Demands, Xiaoyang Wei, Hoong Chuin Lau, Zhe Xiao, Xiuju Fu, Xiaocai Zhang, Zheng Qin

Research Collection School Of Computing and Information Systems

With the growing emphasis on green shipping to reduce the environmental impact of maritime transportation, optimizing fuel consumption with maintaining high service quality has become critical in port operations. Ports are essential nodes in global supply chains, where tugboats play a pivotal role in the safe and efficient maneuvering of ships within constrained environments. However, existing literature lacks approaches that address tugboat scheduling under realistic operational conditions. To fill the research gap, this is the first work to propose the bi-objective dynamic tugboat scheduling problem that optimizes speed under stochastic and time-varying demands, aiming to minimize fuel consumption and manage …

Fuzzing Drones For Anomaly Detection: A Systematic Literature Review, Vikas Kumar Malviya, Wei Minn, Lwin Khin Shar, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Drones, also referred to as Unmanned Aerial Vehicles (UAVs), are becoming popular today due to their uses in different fields and recent technological advancements which provide easy control of UAVs via mobile apps. However, UAVs may contain vulnerabilities or software bugs that cause serious safety and security concerns. For example, the communication protocol used by the UAV may contain authentication and authorization vulnerabilities, which may be exploited by attackers to gain remote access over the UAV. Drones must therefore undergo extensive testing before being released or deployed to identify and fix any software bugs or security vulnerabilities. Fuzzing is one …

Measuring Model Alignment For Code Clone Detection Using Causal Interpretation, Shamsa Abid, Xuemeng Cai, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Deep Neural Network-based models have demonstrated high accuracy for semantic code clone detection. However, the lack of generalization poses a threat to the trustworthiness and reliability of these models. Furthermore, the black-box nature of these models makes interpreting the model’s decisions very challenging. Currently, there is only a limited understanding of the semantic code clone detection behavior of existing models. There is a lack of transparency in understanding how a model identifies semantic code clones and the exact code components influencing its prediction. In this paper, we introduce the use of a causal interpretation framework based on the Neyman-Rubin causal …

Impact Of Achievement-Oriented Gamification In Erp Systems: Examining Subjective And Objective User Outcomes, E. Adeborna, Fiona Fui-Hoon Nah, L. Motiwalla

Research Collection School Of Computing and Information Systems

This research explores the effect of gamification using achievement-oriented affordances in Enterprise Resource Planning (ERP) systems on subjective (behavioral intention) and objective (performance) outcomes. Drawing on the cognitive-affectiveconative (CAC) framework, a research model was developed to explain behavioral intention and tested in a pilot experiment with 63 participants. These participants completed a post-study questionnaire for assessing the impact of gamification on users’ behavioral intention that is mediated by CAC constructs: focused immersion, enjoyment, and selfrewarding experience. Preliminary results show that gamification enhances enjoyment and self-rewarding experience, which in turn positively influence and fully mediate behavioral intention. Objective performance outcomes were …

Interactive Video Search With Multi-Modal Llm Video Captioning, Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Cross-modal representation learning is essential for interactive text-to-video search tasks. However, the representation learning is limited by the size and quality of video-caption pairs. To improve the search accuracy, we propose to enlarge the size of available video-caption pairs by leveraging multi-model LLM on video captioning. Specifically, we use LLM to generate video captions for a large video collection (i.e., WebVid dataset) and use the generated video-caption pairs to pre-train a text-to-video search model. Additionally, we use LLM to generate fine-grained captions for test video collections to enable text-to-caption retrieval. Furthermore, we build a semantic overview of the retrieved rank …

Neuron Semantic-Guided Test Generation For Deep Neural Networks Fuzzing, Li Huang, Weifeng Sun, Meng Yan, Zhongxin Liu, Yan Lei, David Lo

Research Collection School Of Computing and Information Systems

In recent years, significant progress has been made in testing methods for deep neural networks (DNNs) to ensure their correctness and robustness. Coverage-guided criteria, such as neuron-wise, layer-wise, and path-/trace-wise, have been proposed for DNN fuzzing. However, existing coverage-based criteria encounter performance bottlenecks for several reasons: Testing Adequacy: Partial neural coverage criteria have been observed to achieve full coverage using only a small number of test inputs. In this case, increasing the number of test inputs does not consistently improve the quality of models. Interpretability: The current coverage criteria lack interpretability. Consequently, testers are unable to identify and understand which …

Interpreting Topic Models In Byte-Pair Encoding Space, Jia Peng Lim, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Byte-pair encoding (BPE) is pivotal for processing text into chunksize tokens, particularly in Large Language Model (LLM). From a topic modeling perspective, as these chunksize tokens might be mere parts of valid words, evaluating and interpreting these tokens for coherence is challenging. Most, if not all, of coherence evaluation measures are incompatible as they benchmark using valid words. We propose to interpret the recovery of valid words from these tokens as a ranking problem and present a model-agnostic and training-free recovery approach from the topic-token distribution onto a selected vocabulary space, following which we could apply existing evaluation measures. Results …

Weakly-Supervised Semantic Segmentation With Image-Level Labels: From Traditional Models To Foundation Models, Zhaozheng Chen, Qianru Sun

Research Collection School Of Computing and Information Systems

The rapid development of deep learning has driven significant progress in image semantic segmentation—a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e., masks of objects), which are expensive, time consuming, and labor intensive. Weakly supervised semantic segmentation (WSSS) is an effective solution to avoid such labeling. It utilizes only partial or incomplete annotations and provides a cost-effective alternative to fully supervised semantic segmentation. In this article, our focus is on the WSSS with image-level labels, which is the most challenging form of WSSS. Our work has two parts. First, we conduct …

Dims: Distributed Index For Similarity Search In Metric Spaces, Yifan Zhu, Chengyang Luo, Tang Qian, Lu Chen, Yunjun Gao, Baihua Zheng

Research Collection School Of Computing and Information Systems

Similarity search finds objects that are similar to a given query object based on a similarity metric. As the amount and variety of data continue to grow, similarity search in metric spaces has gained significant attention. Metric spaces can accommodate any type of data and support flexible distanc e metrics, making similarity search in metric spaces beneficial for many real-world applications, such as multimedia retrieval, personalized recommendation, trajectory analytics, data mining, decision planning, and distributed servers. However, existing studies mostly focus on indexing metric spaces on a single machine, which faces efficiency and scalability limitations with increasing data volume and …

Robust Learning With Probabilistic Relaxation Using Hypothesis-Test-Based Sampling, Zilin Wang

Dissertations and Theses Collection (Open Access)

In recent years, deep learning has been a vital tool in various tasks. The performance of a neural network is usually evaluated by empirical risk minimization. However, robustness issues have gained great concern which can be fatal in safety-critical applications. Adversarial training can mitigate the issue by minimizing the loss of worst-case perturbations of data. It is effective in improving the robustness of the model, but it is too conservative, and the plain performance of the model can be unsatisfying. Probabilistic Robust Learning (PRL) empirically balances the average- and worst-case performance while the robustness of the model is not provable …

Adan: Adaptive Nesterov Momentum Algorithm For Faster Optimizing Deep Models, Xingyu Xie, Pan Zhou, Huan Li, Zhouchen Lin, Shuicheng Yan

Research Collection School Of Computing and Information Systems

In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model training speed across deep networks, we propose the ADAptive Nesterov momentum algorithm, Adan for short. Adan first reformulates the vanilla Nesterov acceleration to develop a new Nesterov momentum estimation (NME) method, which avoids the extra overhead of computing gradient at the extrapolation point. Then Adan adopts NME to estimate the gradient's first- and second-order moments in adaptive gradient algorithms for convergence acceleration. Besides, we prove that …

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 …

Gotcha ! This Model Uses My Code ! Evaluating Membership Leakage Risks In Code Models, Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsum Kim, Donggyun Han, David Lo

Research Collection School Of Computing and Information Systems

Leveraging large-scale datasets from open-source projects and advances in large language models, recent progress has led to sophisticated code models for key software engineering tasks, such as program repair and code completion. These models are trained on data from various sources, including public open-source projects like GitHub and private, confidential code from companies, raising significant privacy concerns. This paper investigates a crucial but unexplored question: What is the risk of membership information leakage in code models? Membership leakage refers to the vulnerability where an attacker can infer whether a specific data point was part of the training dataset. We present …

Towards Privacy-Aware Iot Communications: Delegable, Revocable, And Efficient, Pengfei Wu, Jianfei Sun, Guomin Yang, Robert H. Deng

Research Collection School Of Computing and Information Systems

The Internet of Things (IoT) is widely recognized for its potential to enhance efficiency and productivity across various industries. However, its increasing prevalence has also made it a more attractive target for cybercriminals. While many advanced cryptographic solutions have been developed to secure IoT, some practical security and privacy issues such as self-sovereign delegation, flexible revocation, and lightweight access remain inadequately addressed in existing solutions. In this paper, we propose PLIC, a Privacy-aware Lightweight IoT Communication scheme, which not only enables any authorized user to flexibly delegate their lightweight access privileges to other delegatees, such that they can also access …

Reinforcement Learning Based Online Request Scheduling Framework For Workload-Adaptive Edge Deep Learning Inference, Xinrui Tan, Hongjia Li, Xiaofei Xie, Lu Guo, Nirwan Ansari, Xueqing Huang, Liming Wang, Zhen Xu, Yang Liu

Research Collection School Of Computing and Information Systems

The recent advances of deep learning in various mobile and Internet-of-Things applications, coupled with the emergence of edge computing, have led to a strong trend of performing deep learning inference on the edge servers located physically close to the end devices. This trend presents the challenge of how to meet the quality-of-service requirements of inference tasks at the resource-constrained network edge, especially under variable or even bursty inference workloads. Solutions to this challenge have not yet been reported in the related literature. In the present paper, we tackle this challenge by means of workload-adaptive inference request scheduling: in different workload …

Mvgamba : Unify 3d Content Generation As State Space Sequence Modeling, Xuanyu Yi, Zike Wu, Qiuhong Shen, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representation for improved visual quality and rendering efficiency. However, we observe that existing Gaussian reconstruction models often suffer from multi-view inconsistency and blurred textures. We attribute this to the compromise of multi-view information propagation in favor of adopting powerful yet computationally intensive architectures (e.g., Transformers). To address this issue, we introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor based on the RNN-like State …

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 …

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, …

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 …

Correlation And Causation Analysis For Cross-Sectional And Panel Data, Barry Nuqoba

Dissertations and Theses Collection (Open Access)

This dissertation investigates how data, algorithms, and expert knowledge can be harnessed to better understand human behavior and enhance well-being. It emphasizes the critical importance of interdisciplinary collaboration to bridge knowledge gaps and foster insights that support preventive care, causal theory advancement, and policy development.

The first study, part of the SHINESeniors project, shed light on the potential usefulness of passive, unobtrusive sensors for detecting nocturia and poor sleep quality, symptoms commonly observed in chronic diseases, thereby enabling live-alone older adults to age in place. Utilizing machine learning techniques on sensor-derived features, the study can identify nocturia and poor sleep …

Causality Analysis For Neural Network Security, Bing Sun

Dissertations and Theses Collection (Open Access)

While neural networks are demonstrating excellent performance in a wide range of applications, there has been a growing concern on their reliability and dependability.Similar to traditional decision-making programs, neural networks inevitably have defects that need to be identified and mitigated at times. Neural networks are usually inherently black-boxes and do not provide explanations on how and why decisions are made. As a result, these defects are more ``hidden" and more challenging to eliminate. It is thus crucial to develop systematic approaches to identify and mitigate defects in a neural network in a rigorous way.

In this dissertation, we focus on …

Towards Robust, Secure, And Privacy-Aware Large Language Models Of Code, Zhou Yang

Dissertations and Theses Collection (Open Access)

The field of software engineering has witnessed a surge in large language models specifically tailored to understand and process code, which we call large language models for code (LLM4Code). The increasing popularity of LLM4Code is inseparable from three key factors: the availability of extensive datasets compiled from diverse data sources, the advancements in deep learning algorithms and computational power that facilitate the training of these powerful models, and the active engagement and collaboration within the research community fostering innovation and the rapid exchange of ideas and methodologies. As evidenced by a series of studies, LLM4Code has been experiencing rapid development …

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 …

Learning De-Biased Representations For Remote-Sensing Imagery, Zichen Tian, Zhaozheng Chen, Qianru Sun

Research Collection School Of Computing and Information Systems

Remote sensing (RS) imagery, requiring specialized satellites to collect and being difficult to annotate, suffers from data scarcity and class imbalance in certain spectrums. Due to data scarcity, training any large-scale RS models from scratch is unrealistic, and the alternative is to transfer pre-trained models by fine-tuning or a more data-efficient method LoRA. Due to class imbalance, transferred models exhibit strong bias, where features of the major class dominate over those of the minor class. In this paper, we propose debLoRA---a generic training approach that works with any LoRA variants to yield debiased features. It is an unsupervised learning approach …

Divlog: Log Parsing With Prompt Enhanced In-Context Learning, Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, Pinjia He

Research Collection School Of Computing and Information Systems

Log parsing, which involves log template extraction from semistructured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing supervised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose DivLog, an effective log parsing …

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 …

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 …

Learning To Handle Complex Constraints For Vehicle Routing Problems, Jieyi Bi, Yining Ma, Jianan Zhou, Wen Song, Zhiguang Cao, Yaoxin Wu, Jie Zhang

Research Collection School Of Computing and Information Systems

Vehicle Routing Problems (VRPs) can model many real-world scenarios and often involve complex constraints. While recent neural methods excel in constructing solutions based on feasibility masking, they struggle with handling complex constraints, especially when obtaining the masking itself is NP-hard. In this paper, we propose a novel Proactive Infeasibility Prevention (PIP) framework to advance the capabilities of neural methods towards more complex VRPs. Our PIP integrates the Lagrangian multiplier as a basis to enhance constraint awareness and introduces preventative infeasibility masking to proactively steer the solution construction process. Moreover, we present PIP-D, which employs an auxiliary decoder and two adaptive …