Computer Sciences Commons^™

Prompt To Be Consistent Is Better Than Self-Consistent? Few-Shot And Zero-Shot Fact Verification With Pre-Trained Language Models, Fengzhu Zeng, Wei Gao

Research Collection School Of Computing and Information Systems

Few-shot or zero-shot fact verification only relies on a few or no labeled training examples. In this paper, we propose a novel method called ProToCo, to Prompt pre-trained language models (PLMs) To be Consistent, for improving the factuality assessment capability of PLMs in the few-shot and zero-shot settings. Given a claim-evidence pair, ProToCo generates multiple variants of the claim with different relations and frames a simple consistency mechanism as constraints for making compatible predictions across these variants. We update PLMs by using parameter-efficient fine-tuning (PEFT), leading to more accurate predictions in few-shot and zero-shot fact verification tasks. Our experiments on …

Analyzing Taxi Drivers’ Decision-Making And Recommending Strategies For Enhanced Performance: A Data-Driven Approach, Mengyu Ji

Dissertations and Theses Collection (Open Access)

This thesis focuses on analyzing the decision-making process of taxi drivers and providing data-driven strategies to enhance their performance. By examin- ing comprehensive historical data encompassing passenger demand patterns, drivers’ spatial dynamics, and fare structures, valuable insights are gained into drivers’ choices regarding optimal routes, timing, and areas with high demand. Integrating real-time information sources, such as GPS data and passenger updates, allows drivers to adapt their strategies dynamically to changing traffic conditions and emerging demand patterns. Predictive analytics models, includ- ing ARIMA, XGBoost, and Linear Regression, are utilized to forecast demand flow at key locations, enabling proactive decision-making and …

Balanced Blended Space: Foundational Human–Ai Dialogues In A Symmetry-Based Mediation Framework, David Smith

Publications and Research

This working paper documents the early development of the Balanced Blended Space (BBS) framework through a series of iterative interactions between a cognitive agent (human researcher) and a computational agent (AI system) conducted in 2023. The work is motivated by the need for a universal theoretical model capable of describing the integration of physical, virtual, and conceptual spaces, particularly in response to increasing fragmentation across contemporary communication systems.

BBS is proposed as a symmetry-based mediation framework in which relationships between domains—such as physical and virtual space, cognition and computation, and multiple sensory modalities—are treated as structurally equivalent and mappable. Central …

Surveillance And The Future Of Work: Exploring Employees’ Attitudes Toward Monitoring In A Post-Covid Workplace, Jessica Vitak, Michael Zimmer

Computer Science Faculty Research and Publications

The future of work increasingly focuses on the collection and analysis of worker data to monitor communication, ensure productivity, reduce security threats, and assist in decision-making. The COVID-19 pandemic increased employer reliance on these technologies; however, the blurring of home and work boundaries meant these monitoring tools might also surveil private spaces. To explore workers’ attitudes toward increased monitoring practices, we present findings from a factorial vignette survey of 645 U.S. adults who worked from home during the early months of the pandemic. Using the theory of privacy as contextual integrity to guide the survey design and analysis, we unpack …

Security Of Text To Image Conversions, Zobaida Alssadi

Theses and Dissertations

The use of images and icons to represent news or narratives has grown in popularity. Still, one critical problem is that they are not equivalent to language, making them vulnerable to adversary attacks. This study examines the impact of image-poisoning attacks based on polysemantic words and of image attacks based on cultural differences when converting text to images. Such attacks can lead to the loss of important information and create confusion and incorrect interpretations of the intended meaning, misinforming the general public. The study specifically focuses on possible effects in a news and story context. This study highlights the significance …

Reinforcement Learning For Sequential Decision Making With Constraints, Jiajing Ling

Dissertations and Theses Collection (Open Access)

Reinforcement learning is a widely used approach to tackle problems in sequential decision making where an agent learns from rewards or penalties. However, in decision-making problems that involve safety or limited resources, the agent's exploration is often limited by constraints. To model such problems, constrained Markov decision processes and constrained decentralized partially observable Markov decision processes have been proposed for single-agent and multi-agent settings, respectively. A significant challenge in solving constrained Dec-POMDP is determining the contribution of each agent to the primary objective and constraint violations. To address this issue, we propose a fictitious play-based method that uses Lagrangian Relaxation …

A Hierarchical Optimization Approach For Dynamic Pickup And Delivery Problem With Lifo Constraints, Jianhui Du, Zhiqin Zhang, Xu Wang, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We consider a dynamic pickup and delivery problem (DPDP) where loading and unloading operations must follow a last in first out (LIFO) sequence. A fleet of vehicles will pick up orders in pickup points and deliver them to destinations. The objective is to minimize the total over-time (that is the amount of time that exceeds the committed delivery time) and total travel distance. Given the dynamics of orders and vehicles, this paper proposes a hierarchical optimization approach based on multiple intuitive yet often-neglected strategies, namely what we term as the urgent strategy, hitchhike strategy and packing-bags strategy. These multiple strategies …

Safe Mdp Planning By Learning Temporal Patterns Of Undesirable Trajectories And Averting Negative Side Effects, Siow Meng Low, Akshat Kumar, Scott Sanner

Research Collection School Of Computing and Information Systems

In safe MDP planning, a cost function based on the current state and action is often used to specify safety aspects. In real world, often the state representation used may lack sufficient fidelity to specify such safety constraints. Operating based on an incomplete model can often produce unintended negative side effects (NSEs). To address these challenges, first, we associate safety signals with state-action trajectories (rather than just immediate state-action). This makes our safety model highly general. We also assume categorical safety labels are given for different trajectories, rather than a numerical cost function, which is harder to specify by the …

Learning Deep Time-Index Models For Time Series Forecasting, Jiale Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

Research Collection School Of Computing and Information Systems

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historicalvalue models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep timeindex models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a …

Understanding The Role Of External Pull Requests In The Npm Ecosystem, Vittunyuta Maeprasart, Supatsara Wattanakriengkrai, Raula Gaikovina Kula, Christoph Treude, Kenichi Matsumoto

Research Collection School Of Computing and Information Systems

The risk to using third-party libraries in a software application is that much needed maintenance is solely carried out by library maintainers. These libraries may rely on a core team of maintainers (who might be a single maintainer that is unpaid and overworked) to serve a massive client user-base. On the other hand, being open source has the benefit of receiving contributions (in the form of External PRs) to help fix bugs and add new features. In this paper, we investigate the role by which External PRs (contributions from outside the core team of maintainers) contribute to a library. Through …

A Comprehensive Study On Quality Assurance Tools For Java, Han Liu, Sen Chen, Ruitao Feng, Chengwei Liu, Kaixuan Li, Zhengzi Xu, Liming Nie, Yang Liu, Yixiang Chen

Research Collection School Of Computing and Information Systems

Quality assurance (QA) tools are receiving more and more attention and are widely used by developers. Given the wide range of solutions for QA technology, it is still a question of evaluating QA tools. Most existing research is limited in the following ways: (i) They compare tools without considering scanning rules analysis. (ii) They disagree on the effectiveness of tools due to the study methodology and benchmark dataset. (iii) They do not separately analyze the role of the warnings. (iv) There is no large-scale study on the analysis of time performance. To address these problems, in the paper, we systematically …

Impact Of Difficult Negatives On Twitter Crisis Detection, Yuhao Zhang, Siaw Ling Lo, Phyo Yi Win Myint

Research Collection School Of Computing and Information Systems

Twitter has become an alternative information source during a crisis. However, the short, noisy nature of tweets hinders information extraction. While models trained with standard Twitter crisis datasets accomplished decent performance, it remained a challenge to generalize to unseen crisis events. Thus, we proposed adding “difficult” negative examples during training to improve model generalization for Twitter crisis detection. Although adding random noise is a common practice, the impact of difficult negatives, i.e., negative data semantically similar to true examples, was never examined in NLP. Most of existing research focuses on the classification task, without considering the primary information need of …

Imitation Improvement Learning For Large-Scale Capacitated Vehicle Routing Problems, The Viet Bui, Tien Mai

Research Collection School Of Computing and Information Systems

Recent works using deep reinforcement learning (RL) to solve routing problems such as the capacitated vehicle routing problem (CVRP) have focused on improvement learning-based methods, which involve improving a given solution until it becomes near-optimal. Although adequate solutions can be achieved for small problem instances, their efficiency degrades for large-scale ones. In this work, we propose a newimprovement learning-based framework based on imitation learning where classical heuristics serve as experts to encourage the policy model to mimic and produce similar or better solutions. Moreover, to improve scalability, we propose Clockwise Clustering, a novel augmented framework for decomposing large-scale CVRP into …

Machine-Learning Approach To Automated Doubt Identification On Stack Overflow Comments To Guide Programming Learners, Tianhao Chen, Eng Lieh Ouh, Kar Way Tan, Siaw Ling Lo

Research Collection School Of Computing and Information Systems

Stack Overflow is a popular Q&A platform for developers to find solutions to programming problems. However, due to the varying quality of user-generated answers, there is a need for ways to help users find high-quality answers. While Stack Overflow's community-based approach can be effective, important technical aspects of the answer need to be captured, and users’ comments might contain doubts regarding these aspects. In this paper, we showed the feasibility of using a machine learning model to identify doubts and conducted data analysis. We found that highly reputed users tend to raise more doubts; most answers have doubt in the …

Augmenting Low-Resource Text Classification With Graph-Grounded Pre-Training And Prompting, Zhihao Wen, Yuan Fang

Research Collection School Of Computing and Information Systems

ext 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 few or no labeled samples, poses 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) …

Do-Good: Towards Distribution Shift Evaluation For Pre-Trained Visual Document Understanding Models, Jiabang He, Yi Hu, Lei Wang, Xing Xu, Ning Liu, Hui Liu

Research Collection School Of Computing and Information Systems

Numerous pre-training techniques for visual document understanding (VDU) have recently shown substantial improvements in performance across a wide range of document tasks. However, these pre-trained VDU models cannot guarantee continued success when the distribution of test data differs from the distribution of training data. In this paper, to investigate how robust existing pre-trained VDU models are to various distribution shifts, we first develop an out-of-distribution (OOD) benchmark termed Do-GOOD for the fine-Grained analysis on Document image-related tasks specifically. The Do-GOOD benchmark defines the underlying mechanisms that result in different distribution shifts and contains 9 OOD datasets covering 3 VDU related …

Silent Compiler Bug De-Duplication Via Three-Dimensional Analysis, Chen Yang, Junjie Chen, Xingyu Fan, Jiajun Jiang, Jun Sun

Research Collection School Of Computing and Information Systems

Compiler testing is an important task for assuring the quality of compilers, but investigating test failures is very time-consuming. This is because many test failures are caused by the same compiler bug (known as bug duplication problem). In particular, this problem becomes much more challenging on silent compiler bugs (also called wrong code bugs), since these bugs can provide little information (unlike crash bugs that can produce error messages) for bug de-duplication. In this work, we propose a novel technique (called D3) to solve the duplication problem on silent compiler bugs. Its key insight is to characterize the silent bugs …

Large-Scale Correlation Analysis Of Automated Metrics For Topic Models, Jia Peng Lim, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Automated coherence metrics constitute an important and popular way to evaluate topic models. Previous works present a mixed picture of their presumed correlation with human judgement. In this paper, we conduct a large-scale correlation analysis of coherence metrics. We propose a novel sampling approach to mine topics for the purpose of metric evaluation, and conduct the analysis via three large corpora showing that certain automated coherence metrics are correlated. Moreover, we extend the analysis to measure topical differences between corpora. Lastly, we examine the reliability of human judgement by conducting an extensive user study, which is designed as an amalgamation …

Cone: An Efficient Coarse-To-Fine Alignment Framework For Long Video Temporal Grounding, Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, Wing-Kwong Chan, Chong-Wah Ngo, Mike Z. Shou, Nan. Duan

Research Collection School Of Computing and Information Systems

This paper tackles an emerging and challenging problem of long video temporal grounding (VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, which brings new challenges in higher inference computation cost and weaker multi-modal alignment. To address these challenges, we propose CONE, an efficient COarse-to-fiNE alignment framework. CONE is a plug-and-play framework on top of existing VTG models to handle long videos through a sliding window mechanism. Specifically, CONE (1) introduces a query-guided window selection strategy to speed up inference, and (2) proposes a …

Transfer-Once-For-All: Ai Model Optimization For Edge, Achintya Kundu, Laura Wynter, Rhui Dih Lee, Luis Angel Bathen

Research Collection School Of Computing and Information Systems

Weight-sharing neural architecture search aims to optimize a configurable neural network model (supernet) for a variety of deployment scenarios across many devices with different resource constraints. Existing approaches use evolutionary search to extract models of different sizes from a supernet trained on a very large data set, and then fine-tune the extracted models on the typically small, real-world data set of interest. The computational cost of training thus grows linearly with the number of different model deployment scenarios. Hence, we propose Transfer-Once-For-All (TOFA) for supernet-style training on small data sets with constant computational training cost over any number of edge …

Strategy‑Aware Bundle Recommender System, Yinwei Wei, Xiaohao Liu, Yunshan Ma, Xiang Wang, Liqiang Nie, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

A bundle is a group of items that provides improved services to users and increased profits for sellers. However, locating the desired bundles that match the users' tastes still challenges us, due to the sparsity issue. Despite the remarkable performance of existing approaches, we argue that they seldom consider the bundling strategy (i.e., how the items within a bundle are associated with each other) in the bundle recommendation, resulting in the suboptimal user and bundle representations for their interaction prediction. Therefore, we propose to model the strategy-aware user and bundle representations for the bundle recommendation.Towards this end, we develop a …

Recognizing Hand Gestures Using Solar Cells, Dong Ma, Guohao Lan, Mahbub Hassan, Wen Hu, B. Mushfika Upama, Ashraf Uddin, Youseef, Moustafa

Research Collection School Of Computing and Information Systems

We design a system, SolarGest, which can recognize hand gestures near a solar-powered device by analyzing the patterns of the photocurrent. SolarGest is based on the observation that each gesture interferes with incident light rays on the solar panel in a unique way, leaving its discernible signature in harvested photocurrent. Using solar energy harvesting laws, we develop a model to optimize design and usage of SolarGest. To further improve the robustness of SolarGest under non-deterministic operating conditions, we combine dynamic time warping with Z-score transformation in a signal processing pipeline to pre-process each gesture waveform before it is analyzed for …

Generative Ai And Chatgpt: Applications, Challenges, And Ai-Human Collaboration, Fiona Nah, Ruilin Zheng, Jingyuan Cai, Keng Siau, Langtao Chen

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) has elicited much attention across disciplines and industries (Hyder et al., Citation2019). AI has been defined as “a system’s ability to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation” (Kaplan & Haenlein, Citation2019, p. 15). AI has gone through several development stages and AI winters. In the first two decades (i.e., 1950s and 1960s), AI demonstrated success which included programs such as General Problem Solver (Newell et al., Citation1959) and ELIZA (Weizenbaum, Citation1966). However, limitations in processing capacity and reduced spending on …

Binalign: Alignment Padding Based Compiler Provenance Recovery, Maliha Ismail, Yan Lin, Donggyun Han, Debin Gao

Research Collection School Of Computing and Information Systems

Compiler provenance is significant in investigating the source-level indicators of binary code, like development-environment, source compiler, and optimization settings. Not only does compiler provenance analysis have important security applications in malware and vulnerability analysis, but it is also very challenging to extract useful artifacts from binary when high-level language constructs are missing. Previous works applied machine-learning techniques to predict the source compiler of binaries. However, most of the work is done on the binaries compiled on Linux operating system. We highlight the importance and need to explore Windows compilers and the complicated binaries compiled on the latest versions of these …

Diaasq: A Benchmark Of Conversational Aspect-Based Sentiment Quadruple Analysis, Bobo Li, Hao Fei, Fei Li, Yuhan Wu, Jinsong Zhang, Shengqiong Wu, Jingye Li, Yijiang Liu, Lizi Liao, Tat-Seng Chua, Donghong Ji

Research Collection School Of Computing and Information Systems

The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limited to the scenario of a single text piece, leaving the study in dialogue contexts unexplored. To bridge the gap between fine-grained sentiment analysis and conversational opinion mining, in this work, we introduce a novel task of conversational aspect-based sentiment quadruple analysis, namely DiaASQ, aiming to detect the quadruple of target-aspect-opinion-sentiment in a dialogue. We manually construct a large-scale high-quality DiaASQ dataset in both Chinese and English languages. We deliberately develop a neural model to benchmark …

A Unified Multi-Task Learning Framework For Multi-Goal Conversational Recommender Systems, Yang Deng, Wenxuan Zhang, Weiwen Xu, Wenqiang Lei, Tat-Seng Chua, Wai Lam

Research Collection School Of Computing and Information Systems

Question generation (QG) aims to automatically generate fluent and relevant questions, where the two most mainstream directions are generating questions from unstructured contextual texts (CQG), such as news articles, and generating questions from structured factoid texts (FQG), such as knowledge graphs or tables. Existing methods for these two tasks mainly face challenges of limited internal structural information as well as scarce background information, while these two tasks can benefit each other for alleviating these issues. For example, when meeting the entity mention “United Kingdom” in CQG, it can be inferred that it is a country in European continent based on …

Learning To Ask Clarification Questions With Spatial Reasoning, Yang Deng, Shuaiyi Li, Wai Lam

Research Collection School Of Computing and Information Systems

Asking clarifying questions has become a key element of various conversational systems, allowing for an effective resolution of ambiguity and uncertainty through natural language questions. Despite the extensive applications of spatial information grounded dialogues, it remains an understudied area on learning to ask clarification questions with the capability of spatial reasoning. In this work, we propose a novel method, named SpatialCQ, for this problem. Specifically, we first align the representation space between textual and spatial information by encoding spatial states with textual descriptions. Then a multi-relational graph is constructed to capture the spatial relations and enable spatial reasoning with relational …

Marketing In Metaverse: Sales-Avatar Visual Features On Customer Trust, Yuxin Liu, Keng Siau

Research Collection School Of Computing and Information Systems

The metaverse wave is sweeping across the world. Virtual shopping promises a bright future and has the potential to provide customers with an immersive and realistic shopping experience anytime and anywhere. Salesavatars are critical in customer trust development in virtual shopping in the metaverse by directly interacting with customers. Considering the virtual characteristics of the metaverse and the anonymity of salesavatars, this research investigates the effect of salesavatars' genders and ages on customers' trust in the metaverse through the lens of first impression formation. Two dimensions of facial first impression, perceived facial trustworthiness and perceived facial dominance, will be studied …

Conference Report On 2022 Ieee Symposium Series On Computational Intelligence (Ieee Ssci 2022), Ah-Hwee Tan, Dipti Srinivasan, Chunyan Miao

Research Collection School Of Computing and Information Systems

On behalf of the organizing committee, we are delighted to deliver this conference report for the 2022 IEEE Symposium Series on Computational Intelligence (SSCI 2022), which was held in Singapore from 4th to 7th December 2022. IEEE SSCI is an established flagship annual international series of symposia on computational intelligence (CI) sponsored by the IEEE Computational Intelligence Society (CIS) to promote and stimulate discussions on the latest theory, algorithms, applications, and emerging topics on computational intelligence. After two years of virtual conferences due to the global pandemic, IEEE SSCI returned as an in-person meeting with online elements in 2022.

Mitigating Adversarial Attacks On Data-Driven Invariant Checkers For Cyber-Physical Systems, Rajib Ranjan Maiti, Cheah Huei Yoong, Venkata Reddy Palleti, Arlindo Silva, Christopher M. Poskitt

Research Collection School Of Computing and Information Systems

The use of invariants in developing security mechanisms has become an attractive research area because of their potential to both prevent attacks and detect attacks in Cyber-Physical Systems (CPS). In general, an invariant is a property that is expressed using design parameters along with Boolean operators and which always holds in normal operation of a system, in particular, a CPS. Invariants can be derived by analysing operational data of various design parameters in a running CPS, or by analysing the system's requirements/design documents, with both of the approaches demonstrating significant potential to detect and prevent cyber-attacks on a CPS. While …