Databases and Information Systems Commons^™

Watme: Towards Lossless Watermarking Through Lexical Redundancy, Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability of suitable tokens and significantly degrades the quality of responses. This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. Our finding highlights a significant disparity; knowledge recall and logical reasoning are more adversely affected than language generation. These results suggest a more profound effect of watermarking on LLMs than previously understood. To address these challenges, we introduce Watermarking with …

Prompt Tuning On Graph-Augmented Low-Resource Text Classification, Zhihao Wen, Yuan Fang

Research Collection School Of Computing and Information Systems

Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with no or few labeled samples, presents a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) …

Is Aggregation The Only Choice? Federated Learning Via Layer-Wise Model Recombination, Ming Hu, Zhihao Yue, Xiaofei Xie, Cheng Chen Chen

Research Collection School Of Computing and Information Systems

Although Federated Learning (FL) enables global model training Xiaofei Xie [email protected] Singapore Management University Singapore, Singapore Xian Wei [email protected] East China Normal University Shanghai, China Mingsong Chen∗ [email protected] East China Normal University Shanghai, China • Computing methodologies → Distributed artificial intelligence. across clients without compromising their raw data, due to the unevenly distributed data among clients, existing Federated Averaging (FedAvg)-based methods suffer from the problem of low inference performance. Specifically, different data distributions among clients lead to various optimization directions of local models. Aggregating local models usually results in a low-generalized global model, which performs worse on most of the …

Reachability-Aware Fair Influence Maximization, Wenyue Ma, Maximilian K. Egger, Andreas Pavlogiannis, Yuchen Li, Panagiotis Karras

Research Collection School Of Computing and Information Systems

How can we ensure that an information dissemination campaign reaches every corner of society and also achieves high overall reach? The problem of maximizing the spread of influence over a social network has commonly been considered with an aggregate objective. Less attention has been paid to achieving equality of opportunity, reducing information barriers, and ensuring that everyone in the network has a fair chance to be reached. To that end, the fairness objective aims to maximize the minimum probability of reaching an individual. To address this inapproximable problem, past research has proposed heuristics, which, however, perform less well when the …

Value-Based Subgoal Discovery And Path Planning For Reaching Long-Horizon Goals, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan, Chai Quek

Research Collection School Of Computing and Information Systems

Learning to reach long-horizon goals in spatial traversal tasks is a significant challenge for autonomous agents. Recent subgoal graph-based planning methods address this challenge by decomposing a goal into a sequence of shorter-horizon subgoals. These methods, however, use arbitrary heuristics for sampling or discovering subgoals, which may not conform to the cumulative reward distribution. Moreover, they are prone to learning erroneous connections (edges) between subgoals, especially those lying across obstacles. To address these issues, this article proposes a novel subgoal graph-based planning method called learning subgoal graph using value-based subgoal discovery and automatic pruning (LSGVP). The proposed method uses a …

Causvsr: Causality Inspired Visual Sentiment Recognition, Xinyue Zhang, Zhaoxia Wang, Hailing Wang, Jing Xiang, Chunwei Wu, Guitao Cao

Research Collection School Of Computing and Information Systems

Visual Sentiment Recognition (VSR) is an evolving field that aims to detect emotional tendencieswithin visual content. Despite its growing significance, detecting emotions depicted in visual content,such as images, faces challenges, notably the emergence of misleading or spurious correlationsof the contextual information. In response to these challenges, we propose a causality inspired VSRapproach, called CausVSR. CausVSR is rooted in the fundamental principles of Emotional Causalitytheory, mimicking the human process from receiving emotional stimuli to deriving emotional states.CausVSR takes a deliberate stride toward conquering the VSR challenges. It harnesses the power of astructural causal model, intricately designed to encapsulate the dynamic causal …

Chain-Of-Exemplar: Enhancing Distractor Generation For Multimodal Educational Question Generation, Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Multiple-choice questions (MCQs) are important in enhancing concept learning and student engagement for educational purposes. Despite the multimodal nature of educational content, current methods focus mainly on text-based inputs and often neglect the integration of visual information. In this work, we study the problem of multimodal educational question generation, which aims at generating subject-specific educational questions with plausible yet incorrect distractors based on multimodal educational content. To tackle this problem, we introduce a novel framework, named Chain-of-Exemplar (CoE), which utilizes multimodal large language models (MLLMs) with Chain-of-Thought reasoning to improve the generation of challenging distractors. Furthermore, CoE leverages three-stage contextualized …

On The Multi-Turn Instruction Following For Conversational Web Agents, Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancements, the potential for LLM-powered agents to effectively engage with sequential user instructions in real-world scenarios has not been fully explored. In this work, we introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment, supported by a specially developed dataset named Multi-Turn Mind2Web (MT-Mind2Web). To tackle the limited context length of LLMs and the …

Interpretable Tensor Fusion, Saurabh Varshneya, Antoine Ledent, Philipp Liznerski, Andriy Balinskyy, Purvanshi Mehta, Waleed Mustafa, Marius Kloft

Research Collection School Of Computing and Information Systems

Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method training a neural network to simultaneously learn multiple data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of the data types, thereby disentangling higher-order interactions from the individual effects of each modality. InTense provides interpretability out of the box by assigning relevance scores to modalities and their associations, respectively. The approach is …

Gamification In Erp Systems: A Study On Intrinsic Motivation And User Behavioral Intentions, Esi Adeborna, Fiona Fui-Hoon Nah, Luvai Motiwalla

Research Collection School Of Computing and Information Systems

In the evolving landscape of Enterprise Resource Planning (ERP) systems, integrating gamification shows promise for enhancing user training and education. However, empirical research on gamification's effect on intrinsic motivation in using ERP is limited. Hence, we examined the intrinsic motivational effects of a gamified ERP environment in this research. We created a Gamified Web Application linked to SAP ERP to investigate how gamification affects users' behavioral intention. Leveraging self-determination theory, we examined the influence of perceived competence, autonomy, and relatedness on usage intent. In a controlled experiment with 63 participants, data collected via survey revealed that gamification enhances perceived competence, …

Sequential Decision Learning For Social Good And Fairness, Dexun Li

Dissertations and Theses Collection (Open Access)

Sequential decision learning is one of the key research areas in artificial intelligence. Typically, a sequence of events is observed through a transformation that introduces uncertainty into the observations and based on these observations, the recognition process produces a hypothesis of the underlying events. This learning process is characterized by maximizing the sum of the reward signals. However, many real-life problems are inherently constrained by limited resources. Besides, when the learning algorithms are used to inform decisions involving human beings (e.g., Security and justice, health intervention, etc), they may inherit the potential, pre-existing bias in the dataset and exhibit similar …

A Deep Learning Method To Predict Bacterial Adp-Ribosyltransferase Toxins, Dandan Zheng, Siyu Zhou, Lihong Chen, Guansong Pang, Jian Yang

Research Collection School Of Computing and Information Systems

Motivation: ADP-ribosylation is a critical modification involved in regulating diverse cellular processes, including chromatin structure regulation, RNA transcription, and cell death. Bacterial ADP-ribosyltransferase toxins (bARTTs) serve as potent virulence factors that orchestrate the manipulation of host cell functions to facilitate bacterial pathogenesis. Despite their pivotal role, the bioinformatic identification of novel bARTTs poses a formidable challenge due to limited verified data and the inherent sequence diversity among bARTT members. Results: We proposed a deep learning-based model, ARTNet, specifically engineered to predict bARTTs from bacterial genomes. Initially, we introduced an effective data augmentation method to address the issue of data scarcity …

Generalization Analysis Of Deep Nonlinear Matrix Completion, Antoine Ledent, Rodrigo Alves

Research Collection School Of Computing and Information Systems

We provide generalization bounds for matrix completion with Schatten $p$ quasi-norm constraints, which is equivalent to deep matrix factorization with Frobenius constraints. In the uniform sampling regime, the sample complexity scales like $\widetilde{O}\left( rn\right)$ where $n$ is the size of the matrix and $r$ is a constraint of the same order as the ground truth rank in the isotropic case. In the distribution-free setting, the bounds scale as $\widetilde{O}\left(r^{1-\frac{p}{2}}n^{1+\frac{p}{2}}\right)$, which reduces to the familiar $\sqrt{r}n^{\frac{3}{2}}$ for $p=1$. Furthermore, we provide an analogue of the weighted trace norm for this setting which brings the sample complexity down to $\widetilde{O}(nr)$ in all …

A Bottom-Up Multi-Disciplinary Approach For Sustainability Education: Un-Sdg 13.3, Benjamin Gan, Thomas Menkhoff, Eng Lieh Ouh, Kevin Cheong

Research Collection School Of Computing and Information Systems

Teaching both information systems and business undergraduates to break the current inertia in sustainability action requires innovative teaching & learning approaches as well as inter-disciplinary knowledge inputs. This study presents a bottom-up T&L approach delivered by a group of educators from different disciplines aimed at addressing UN-SDG Goal 13 ‘Climate Action’ with a novel approach. Integrating a problem-centric community project assignment into existing courses, our students worked on different disciplinary elements such as persuasive technologies and awareness campaigns to help to address local sustainability initiatives by community partners. We collected data to measure how students’ motivation, engagement, teamwork, and community …

Decentralized Consensus And Governance For Collaborative Intelligence, Huiwen Liu

Dissertations and Theses Collection (Open Access)

The data economy today is becoming increasingly collaborative in nature. Take business intelligence, for example. To unleash the full potential of big data, it is essential to integrate multi-source data depicting entities from a multi-faceted and multi-modal perspective, which, not surprisingly, is not achievable by any company alone. In collaborative intelligence, there are two core issues, namely "trust" and "incentive". The core mechanisms to solve these two problems are consensus and tokenization separately.

To solve the trust problem more effectively, we propose a systematic consensus evaluation framework to investigate whether existing consensus algorithms can do so. After a lot of …

Towards Human-Centered Proactive Conversational Agents, Yang Deng, Lizi Liao, Zhonghua Zheng, Grace Hui Yang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recent research on proactive conversational agents (PCAs) mainly focuses on improving the system's capabilities in anticipating and planning action sequences to accomplish tasks and achieve goals before users articulate their requests. This perspectives paper highlights the importance of moving towards building human-centered PCAs that emphasize human needs and expectations, and that considers ethical and social implications of these agents, rather than solely focusing on technological capabilities. The distinction between a proactive and a reactive system lies in the proactive system's initiative-taking nature. Without thoughtful design, proactive systems risk being perceived as intrusive by human users. We address the issue by …

Exploring The Market Impact Of Web3 Identity Imitation In Ethereum Name Service, Ping Fan Ke, Yi Meng Lau

Research Collection School Of Computing and Information Systems

Digital identities are paramount in today’s digital landscape. However, in the Web3 ecosystem, the absence of a central governing body leaves digital identities, such as domain names, vulnerable to cybersquatting and identity imitation. This study examines the market impact of identity imitation in the Web3 ecosystem. By scrutinizing trading activities within Web3 domain names from Ethereum Name Service (ENS) and its imitator, "Ether Name Service," we found that the presence of a newly imitating domain name increases the subsequent resale value of the authentic domain name. Additionally, we find a positive correlation between the resale value of the imitating domain …

Towards Automated Slide Augmentation To Discover Credible And Relevant Links, Dilan Dinushka Senarath Arachchige, Christopher M. Poskitt, Kwan Chin (Xu Guangjin) Koh, Heng Ngee Mok, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning from concise educational materials, such as lecture notes and presentation slides, often prompts students to seek additional resources. Newcomers to a subject may struggle to find the best keywords or lack confidence in the credibility of the supplementary materials they discover. To address these problems, we introduce Slide++, an automated tool that identifies keywords from lecture slides, and uses them to search for relevant links, videos, and Q&As. This interactive website integrates the original slides with recommended resources, and further allows instructors to 'pin' the most important ones. To evaluate the effectiveness of the tool, we trialled the system …

Diffusion Models For Generative Outfit Recommendation, Yiyan Xu, Wenjie Wang, Fuli Feng, Yunshan Ma, Jizhi Zhang, Xiangnan He

Research Collection School Of Computing and Information Systems

Outfit Recommendation (OR) in the fashion domain has evolved through two stages: Pre-defined Outfit Recommendation and Personalized Outfit Composition. However, both stages are constrained by existing fashion products, limiting their effectiveness in addressing users' diverse fashion needs. Recently, the advent of AI-generated content provides the opportunity for OR to transcend these limitations, showcasing the potential for personalized outfit generation and recommendation.To this end, we introduce a novel task called Generative Outfit Recommendation (GOR), aiming to generate a set of fashion images and compose them into a visually compatible outfit tailored to specific users. The key objectives of GOR lie in …

Unveiling The Dynamics Of Crisis Events: Sentiment And Emotion Analysis Via Multi-Task Learning With Attention Mechanism And Subject-Based Intent Prediction, Phyo Yi Win Myint, Siaw Ling Lo, Yuhao Zhang

Research Collection School Of Computing and Information Systems

In the age of rapid internet expansion, social media platforms like Twitter have become crucial for sharing information, expressing emotions, and revealing intentions during crisis situations. They offer crisis responders a means to assess public sentiment, attitudes, intentions, and emotional shifts by monitoring crisis-related tweets. To enhance sentiment and emotion classification, we adopt a transformer-based multi-task learning (MTL) approach with attention mechanism, enabling simultaneous handling of both tasks, and capitalizing on task interdependencies. Incorporating attention mechanism allows the model to concentrate on important words that strongly convey sentiment and emotion. We compare three baseline models, and our findings show that …

Broadening The View: Demonstration-Augmented Prompt Learning For Conversational Recommendation, Quang Huy Dao, Yang Deng, Dung D. Le, Lizi Liao

Research Collection School Of Computing and Information Systems

Conversational Recommender Systems (CRSs) leverage natural language dialogues to provide tailored recommendations. Traditional methods in this field primarily focus on extracting user preferences from isolated dialogues. It often yields responses with a limited perspective, confined to the scope of individual conversations. Recognizing the potential in collective dialogue examples, our research proposes an expanded approach for CRS models, utilizing selective analogues from dialogue histories and responses to enrich both generation and recommendation processes. This introduces significant research challenges, including: (1) How to secure high-quality collections of recommendation dialogue exemplars? (2) How to effectively leverage these exemplars to enhance CRS models?To tackle …

Large Language Model Powered Agents For Information Retrieval, An Zhang, Yang Deng, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The vital goal of information retrieval today extends beyond merely connecting users with relevant information they search for. It also aims to enrich the diversity, personalization, and interactivity of that connection, ensuring the information retrieval process is as seamless, beneficial, and supportive as possible in the global digital era. Current information retrieval systems often encounter challenges like a constrained understanding of queries, static and inflexible responses, limited personalization, and restricted interactivity. With the advent of large language models (LLMs), there's a transformative paradigm shift as we integrate LLM-powered agents into these systems. These agents bring forth crucial human capabilities like …

Comparative Analysis Of Hate Speech Detection: Traditional Vs. Deep Learning Approaches, Haibo Pen, Nicole Anne Huiying Teo, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Detecting hate speech on social media poses a significant challenge, especially in distinguishing it from offensive language, as learning-based models often struggle due to nuanced differences between them, which leads to frequent misclassifications of hate speech instances, with most research focusing on refining hate speech detection methods. Thus, this paper seeks to know if traditional learning-based methods should still be used, considering the perceived advantages of deep learning in this domain. This is done by investigating advancements in hate speech detection. It involves the utilization of deep learning-based models for detailed hate speech detection tasks and compares the results with …

Performance Analysis Of Llama 2 Among Other Llms, Donghao Huang, Zhenda Hu, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Llama 2, an open-source large language model developed by Meta, offers a versatile and high-performance solution for natural language processing, boasting a broad scale, competitive dialogue capabilities, and open accessibility for research and development, thus driving innovation in AI applications. Despite these advancements, there remains a limited understanding of the underlying principles and performance of Llama 2 compared with other LLMs. To address this gap, this paper presents a comprehensive evaluation of Llama 2, focusing on its application in in-context learning — an AI design pattern that harnesses pre-trained LLMs for processing confidential and sensitive data. Through a rigorous comparative …

Jigsaw: Edge-Based Streaming Perception Over Spatially Overlapped Multi-Camera Deployments, Ila Gokarn, Yigong Hu, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

We present JIGSAW, a novel system that performs edge-based streaming perception over multiple video streams, while additionally factoring in the redundancy offered by the spatial overlap often exhibited in urban, multi-camera deployments. To assure high streaming throughput, JIGSAW extracts and spatially multiplexes multiple regions-of-interest from different camera frames into a smaller canvas frame. Moreover, to ensure that perception stays abreast of evolving object kinematics, JIGSAW includes a utility-based weighted scheduler to preferentially prioritize and even skip object-specific tiles extracted from an incoming stream of camera frames. Using the CityflowV2 traffic surveillance dataset, we show that JIGSAW can simultaneously process 25 …

Fedstem-Adl: A Federated Spatial-Temporal Episodic Memory Model For Adl Prediction, Doudou Wu, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Learning of Activities of Daily Living (ADLs) provides insights into an individual’s habits, lifestyle, and well-being. However, it is crucial to address data privacy concerns in practical situations when learning the ADL routines of individuals. In this paper, we introduce FedSTEM-ADL, a federated spatial-temporal episodic memory model to address this privacy issue. FedSTEM-ADL utilizes a federation of Spatial-Temporal Episodic Memory for ADLs (STEM-ADL) for federated learning, wherein multiple local STEM-ADL models from individual users are combined into a global model while preserving the privacy of the original data. Specifically, each local model is designed to learn the spatio-temporal ADL routines …

Is There A Space In Landslide Susceptibility Modelling: A Case Study Of Valtellina Valley, Northern Italy, Min Naing Khant, Mei Yi Victoria Grace Ann, Tin Seong Kam

Research Collection School Of Computing and Information Systems

Landslides pose significant and ever-threatening risks to human life and infrastructure worldwide. Landslide susceptibility modelling is an emerging field of research seeking to determine contributing factors of these events. Yet, previous studies rarely explored the spatial variation of different landslide factors. Hence, this study aims to demonstrate the potential contribution of spatial nonstationarity in landslide susceptibility modelling using Global Logistic Regression (GLR) and Geographically Weighted Logistic Regression (GWLR). The second objective of this study is to demonstrate the important role of data preparation, data sampling, variable sensing, and variable selections in landslide susceptibility modelling. Using Valtellina Valley in Northern Italy …

The Information Content Of Financial Statement Fraud Risk: An Ensemble Learning Approach, Wei Duan, Nan Hu, Fujing Xue

Research Collection School Of Computing and Information Systems

This study aims to assess the financial statement fraud risk ex ante and empirically explore its information content to help improve decision-making and daily operations. We propose an ex-ante fraud risk index by adopting an ensemble learning approach and a theoretically grounded framework. Our ensemble learning model systematically examines the fraud process and deals effectively with the unique challenges in the financial fraud setting, which yields superior prediction performance. More importantly, we empirically examine the information content of our estimated ex-ante fraud risk from the perspective of operational efficiency. Our empirical results find that the estimated ex-ante fraud risk is …

An Exploratory Study Of Conventional Machine Learning And Large Language Models For Sentiment Analysis, Cui Zou, Jingyuan Cai, Langtao Chen, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Sentiment analysis is the use of natural language processing to identify affective states and determine people’s opinions in various analytical applications such as customer reviews and social media analyses. Large language models (LLMs) such as GPT-4o demonstrate impressive performance in text generation tasks. Despite numerous studies in the extant literature, few have compared the performance of conventional machine learning models with LLMs for sentiment analysis. This study aims to fill this gap by conducting an evaluation of these models using a balanced dataset of 2,000 IMDb movie reviews. Our study shows that GPT-4o achieves the highest performance, while GPT-3.5 and …

A Computational Aesthetic Design Science Study On Online Video Based On Triple-Dimensional Multimodal Analysis, Zhangguang Kang, Fiona Fui-Hoon Nah, Keng Siau

Research Collection School Of Computing and Information Systems

Computational video aesthetic prediction refers to using models that automatically evaluate the features of videos to produce their aesthetic scores. Current video aesthetic prediction models are designed based on bimodal frameworks. To address their limitations, we developed the Triple-Dimensional Multimodal Temporal Video Aesthetic neural network (TMTVA-net) model. The Long Short-Term Memory (LSTM) forms the conceptual foundation for the design framework. In the multimodal transformer layer, we employed two distinct transformers: the multimodal transformer and the feature transformer, enabling the acquisition of modality-specific patterns and representational features uniquely adapted to each modality. The fusion layer has also been redesigned to compute …