Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Computer Sciences (6871)
- Databases and Information Systems (2866)
- Software Engineering (1846)
- Artificial Intelligence and Robotics (983)
- Numerical Analysis and Scientific Computing (931)
-
- Information Security (895)
- Engineering (770)
- Graphics and Human Computer Interfaces (661)
- Social and Behavioral Sciences (585)
- Business (529)
- Theory and Algorithms (438)
- Computer Engineering (394)
- Operations Research, Systems Engineering and Industrial Engineering (358)
- Programming Languages and Compilers (286)
- OS and Networks (282)
- Communication (272)
- Social Media (220)
- Public Affairs, Public Policy and Public Administration (174)
- Data Storage Systems (157)
- Transportation (156)
- Medicine and Health Sciences (145)
- Management Information Systems (141)
- Education (126)
- E-Commerce (114)
- International and Area Studies (95)
- Asian Studies (94)
- Technology and Innovation (84)
- Health Information Technology (83)
- Finance and Financial Management (77)
- Keyword
-
- Deep learning (103)
- Machine learning (86)
- Social media (65)
- Data mining (56)
- Artificial intelligence (55)
-
- Cloud computing (55)
- Reinforcement learning (51)
- Optimization (49)
- Twitter (46)
- Visualization (46)
- Online learning (45)
- Privacy (45)
- Deep Learning (44)
- Empirical study (44)
- Security (44)
- Software engineering (44)
- Task analysis (44)
- Neural networks (43)
- Feature extraction (41)
- Singapore (40)
- Access control (39)
- Semantics (39)
- Algorithms (38)
- Blockchain (36)
- Classification (36)
- Anomaly detection (34)
- Clustering (34)
- Collaboration (34)
- Android (33)
- Software (32)
- Publication Year
- File Type
Articles 61 - 90 of 6884
Full-Text Articles in Physical Sciences and Mathematics
Microkarta: Visualising Microservice Architectures, Oscar Manglaras, Alex Farkas, Peter Fule, Christoph Treude, Markus Wagner
Microkarta: Visualising Microservice Architectures, Oscar Manglaras, Alex Farkas, Peter Fule, Christoph Treude, Markus Wagner
Research Collection School Of Computing and Information Systems
Conceptualising and debugging a microservice architecture can be a challenge for developers due to the complex topology of inter-service communication, which may only apparent when viewing the architecture as a whole. In this paper, we present MicroKarta, a dashboard containing three types of network diagram that visualise complex microservice architectures, and that are designed to address problems faced by developers of these architectures. Initial feedback from industry developers has been positive. This dashboard can be used by developers to explore and debug microservice architectures, and can be used to compare the effectiveness of different types of network visualisation for assisting …
Toward Effective Secure Code Reviews: An Empirical Study Of Security-Related Coding Weaknesses, Wachiraphan Charoenwet, Patanamon Thongtanunam, Thuan Pham, Christoph Treude
Toward Effective Secure Code Reviews: An Empirical Study Of Security-Related Coding Weaknesses, Wachiraphan Charoenwet, Patanamon Thongtanunam, Thuan Pham, Christoph Treude
Research Collection School Of Computing and Information Systems
Identifying security issues early is encouraged to reduce the latent negative impacts on software systems. Code review is a widely-used method that allows developers to manually inspect modified code, catching security issues during a software development cycle. However, existing code review studies often focus on known vulnerabilities, neglecting coding weaknesses, which can introduce real-world security issues that are more visible through code review. The practices of code reviews in identifying such coding weaknesses are not yet fully investigated. To better understand this, we conducted an empirical case study in two large open-source projects, OpenSSL and PHP. Based on 135,560 code …
Partial Solution Based Constraint Solving Cache In Symbolic Execution, Ziqi Shuai, Zhenbang Chen, Kelin Ma, Kunlin Liu, Yufeng Zhang, Jun Sun, Ji Wang
Partial Solution Based Constraint Solving Cache In Symbolic Execution, Ziqi Shuai, Zhenbang Chen, Kelin Ma, Kunlin Liu, Yufeng Zhang, Jun Sun, Ji Wang
Research Collection School Of Computing and Information Systems
Constraint solving is one of the main challenges for symbolic execution. Caching is an effective mechanism to reduce the number of the solver invocations in symbolic execution and is adopted by many mainstream symbolic execution engines. However, caching can not perform well on all programs. How to improve caching’s effectiveness is challenging in general. In this work, we propose a partial solution-based caching method for improving caching’s effectiveness. Our key idea is to utilize the partial solutions inside the constraint solving to generate more cache entries. A partial solution may satisfy other constraints of symbolic execution. Hence, our partial solution-based …
Esem: To Harden Process Synchronization For Servers, Zhanbo Wang, Jiaxin Zhan, Xuhua Ding, Fengwei Zhang, Ning Hu
Esem: To Harden Process Synchronization For Servers, Zhanbo Wang, Jiaxin Zhan, Xuhua Ding, Fengwei Zhang, Ning Hu
Research Collection School Of Computing and Information Systems
Process synchronization primitives lubricate server computing involving a group of processes as they ensure those processes to properly coordinate their executions for a common purpose such as provisioning a web service. A malfunctioned synchronization due to attacks causes friction among processes and leads to unexpected, and often hard-to-detect, application transaction errors. Unfortunately, synchronization primitives are not naturally protected by existing hardware-assisted isolation techniques e.g., SGX, because their process-oriented isolation conflicts with the primitive's demand for cross-process operations.This paper introduces the Enclave-Semaphore service (ESem) which shelters application semaphores and their operations against kernel-privileged attacks. ESem encapsulates all semaphores in the platform …
Mvmoe: Multi-Task Vehicle Routing Solver With Mixture-Of-Experts, Jianan Zhou, Zhiguang Cao, Yaoxin Wu, Wen Song, Yining Ma, Jie Zhang, Chi Xu
Mvmoe: Multi-Task Vehicle Routing Solver With Mixture-Of-Experts, Jianan Zhou, Zhiguang Cao, Yaoxin Wu, Wen Song, Yining Ma, Jie Zhang, Chi Xu
Research Collection School Of Computing and Information Systems
Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously. Specifically, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in computation. We further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational complexity. Experimentally, our method significantly promotes …
Learning Topological Representations With Bidirectional Graph Attention Network For Solving Job Shop Scheduling Problem, Cong Zhang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jing Sun
Learning Topological Representations With Bidirectional Graph Attention Network For Solving Job Shop Scheduling Problem, Cong Zhang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jing Sun
Research Collection School Of Computing and Information Systems
Existing learning-based methods for solving job shop scheduling problems (JSSP) usually use off-the-shelf GNN models tailored to undirected graphs and neglect the rich and meaningful topological structures of disjunctive graphs (DGs). This paper proposes the topology-aware bidirectional graph attention network (TBGAT), a novel GNN architecture based on the attention mechanism, to embed the DG for solving JSSP in a local search framework. Specifically, TBGAT embeds the DG from a forward and a backward view, respectively, where the messages are propagated by following the different topologies of the views and aggregated via graph attention. Then, we propose a novel operator based …
Adaptive Stabilization Based On Machine Learning For Column Generation, Yunzhuang Shen, Yuan Sun, Xiaodong Li, Zhiguang Cao, Eberhard Andrew, Guangquan Zhang
Adaptive Stabilization Based On Machine Learning For Column Generation, Yunzhuang Shen, Yuan Sun, Xiaodong Li, Zhiguang Cao, Eberhard Andrew, Guangquan Zhang
Research Collection School Of Computing and Information Systems
Column generation (CG) is a well-established method for solving large-scale linear programs. It involves iteratively optimizing a subproblem containing a subset of columns and using its dual solution to generate new columns with negative reduced costs. This process continues until the dual values converge to the optimal dual solution to the original problem. A natural phenomenon in CG is the heavy oscillation of the dual values during iterations, which can lead to a substantial slowdown in the convergence rate. Stabilization techniques are devised to accelerate the convergence of dual values by using information beyond the state of the current subproblem. …
Refining Chatgpt-Generated Code: Characterizing And Mitigating Code Quality Issues, Yue Liu, Thanh Le-Cong, Ratnadira Widyasari, David Lo
Refining Chatgpt-Generated Code: Characterizing And Mitigating Code Quality Issues, Yue Liu, Thanh Le-Cong, Ratnadira Widyasari, David Lo
Research Collection School Of Computing and Information Systems
Since its introduction in November 2022, ChatGPT has rapidly gained popularity due to its remarkable ability in language understanding and human-like responses. ChatGPT, based on GPT-3.5 architecture, has shown great promise for revolutionizing various research fields, including code generation. However, the reliability and quality of code generated by ChatGPT remain unexplored, raising concerns about potential risks associated with the widespread use of ChatGPT-driven code generation.In this article, we systematically study the quality of 4,066 ChatGPT-generated programs of code implemented in two popular programming languages, i.e., Java and Python, for 2,033 programming tasks. The goal of this work is threefold. First, …
Network-Based Representations And Dynamic Discrete Choice Models For Multiple Discrete Choice Analysis, Huy Hung Tran, Tien Mai
Network-Based Representations And Dynamic Discrete Choice Models For Multiple Discrete Choice Analysis, Huy Hung Tran, Tien Mai
Research Collection School Of Computing and Information Systems
In many choice modeling applications, consumer demand is frequently characterized as multiple discrete, which means that consumer choose multiple items simultaneously. The analysis and prediction of consumer behavior in multiple discrete choice situations pose several challenges. In this paper, to address this, we propose a random utility maximization (RUM) based model that considers each subset of choice alternatives as a composite alternative, where individuals choose a subset according to the RUM framework. While this approach offers a natural and intuitive modeling approach for multiple-choice analysis, the large number of subsets of choices in the formulation makes its estimation and application …
Smart Hpa: A Resource-Efficient Horizontal Pod Auto-Scaler For Microservice Architectures, Hussain Ahmad, Christoph Treude, Markus Wagner, Claudia Szabo
Smart Hpa: A Resource-Efficient Horizontal Pod Auto-Scaler For Microservice Architectures, Hussain Ahmad, Christoph Treude, Markus Wagner, Claudia Szabo
Research Collection School Of Computing and Information Systems
Microservice architectures have gained prominence in both academia and industry, offering enhanced agility, reusability, and scalability. To simplify scaling operations in microservice architectures, container orchestration platforms such as Kubernetes feature Horizontal Pod Auto-scalers (HPAs) designed to adjust the resources of microservices to accommodate fluctuating workloads. However, existing HPAs are not suitable for resourceconstrained environments, as they make scaling decisions based on the individual resource capacities of microservices, leading to service unavailability and performance degradation. Furthermore, HPA architectures exhibit several issues, including inefficient data processing and a lack of coordinated scaling operations. To address these concerns, we propose Smart HPA, a …
Violet: Visual Analytics For Explainable Quantum Neural Networks, Shaolun Ruan, Zhiding Liang, Qiang Guan, Paul Robert Griffin, Xiaolin Wen, Yanna Lin, Yong Wang
Violet: Visual Analytics For Explainable Quantum Neural Networks, Shaolun Ruan, Zhiding Liang, Qiang Guan, Paul Robert Griffin, Xiaolin Wen, Yanna Lin, Yong Wang
Research Collection School Of Computing and Information Systems
With the rapid development of Quantum Machine Learning, quantum neural networks (QNN) have experienced great advancement in the past few years, harnessing the advantages of quantum computing to significantly speed up classical machine learning tasks. Despite their increasing popularity, the quantum neural network is quite counter-intuitive and difficult to understand, due to their unique quantum-specific layers (e.g., data encoding and measurement) in their architecture. It prevents QNN users and researchers from effectively understanding its inner workings and exploring the model training status. To fill the research gap, we propose VIOLET , a novel visual analytics approach to improve the explainability …
Dappscan: Building Large-Scale Datasets For Smart Contract Weaknesses In Dapp Projects, Zibin Zheng, Jianzhong Su, Jiachi Chen, David Lo, Zhijie Zhong, Mingxi Ye
Dappscan: Building Large-Scale Datasets For Smart Contract Weaknesses In Dapp Projects, Zibin Zheng, Jianzhong Su, Jiachi Chen, David Lo, Zhijie Zhong, Mingxi Ye
Research Collection School Of Computing and Information Systems
The Smart Contract Weakness Classification Registry (SWC Registry) is a widely recognized list of smart contract weaknesses specific to the Ethereum platform. Despite the SWC Registry not being updated with new entries since 2020, the sustained development of smart contract analysis tools for detecting SWC-listed weaknesses highlights their ongoing significance in the field. However, evaluating these tools has proven challenging due to the absence of a large, unbiased, real-world dataset. To address this problem, we aim to build a large-scale SWC weakness dataset from real-world DApp projects. We recruited 22 participants and spent 44 person-months analyzing 1,199 open-source audit reports …
Inceptionnext: When Inception Meets Convnext, Weihao Yu, Pan Zhou, Shuicheng Yan, Xinchao Wang
Inceptionnext: When Inception Meets Convnext, Weihao Yu, Pan Zhou, Shuicheng Yan, Xinchao Wang
Research Collection School Of Computing and Information Systems
Inspired by the long-range modeling ability of ViTs, large-kernel convolutions are widely studied and adopted recently to enlarge the receptive field and improve model performance, like the remarkable work ConvNeXt which employs 7×7 depthwise convolution. Although such depthwise operator only consumes a few FLOPs, it largely harms the model efficiency on powerful computing devices due to the high memory access costs. For example, ConvNeXtT has similar FLOPs with ResNet-50 but only achieves ∼ 60% throughputs when trained on A100 GPUs with full precision. Although reducing the kernel size of ConvNeXt can improve speed, it results in significant performance degradation, which …
Jollygesture: Exploring Dual-Purpose Gestures In Vr Presentations, Gun Woo Warren Park, Anthony Tang, Fanny Chevalier
Jollygesture: Exploring Dual-Purpose Gestures In Vr Presentations, Gun Woo Warren Park, Anthony Tang, Fanny Chevalier
Research Collection School Of Computing and Information Systems
Virtual reality (VR) offers new opportunities for presenters to use expressive body language to engage their audience. Yet, most VR presentation systems have adopted control mechanisms that mimic those found in face-to-face presentation systems. We explore the use of gestures that have dual-purpose: first, for the audience, a communicative purpose; second, for the presenter, a control purpose to alter content in slides. To support presenters, we provide guidance on what gestures are available and their effects. We realize our design approach in JollyGesture, a VR technology probe that recognizes dual-purpose gestures in a presentation scenario. We evaluate our approach through …
Usability Versus Collectibility In Nft: The Case Of Web3 Domain Names, Ping Fan Ke, Yi Meng Lau
Usability Versus Collectibility In Nft: The Case Of Web3 Domain Names, Ping Fan Ke, Yi Meng Lau
Research Collection School Of Computing and Information Systems
This study examines the market’s inclination towards usability and collectibility aspects of Non-Fungible Tokens (NFTs) within Web3 domain name marketplaces, drawing insights from resale records. Our findings reveal a prevailing preference for usability, as evidenced by consistently higher average resale prices observed for Ethereum Name Service (ENS) domains compared to Linagee Name Registrar (LNR) domains. However, domains with diminished usability, such as those containing non-ASCII characters, tend to attract investors due to their enhanced collectibility. Our analysis on the effect from previous resale suggests a potential aversion towards second-hand acquisitions among NFT investors when value derives primarily from usability, while …
Poster: Profiling Event Vision Processing On Edge Devices, Ila Nitin Gokarn, Archan Misra
Poster: Profiling Event Vision Processing On Edge Devices, Ila Nitin Gokarn, Archan Misra
Research Collection School Of Computing and Information Systems
As RGB camera resolutions and frame-rates improve, their increased energy requirements make it challenging to deploy fast, efficient, and low-power applications on edge devices. Newer classes of sensors, such as the biologically inspired neuromorphic event-based camera, capture only changes in light intensity per-pixel to achieve operational superiority in sensing latency (O(μs)), energy consumption (O(mW)), high dynamic range (140dB), and task accuracy such as in object tracking, over traditional RGB camera streams. However, highly dynamic scenes can yield an event rate of up to 12MEvents/second, the processing of which could overwhelm …
Predicting Mild Cognitive Impairment Through Ambient Sensing And Artificial Intelligence, Ah-Hwee Tan, Weng Yan Ying, Budhitama Subagdja, Anni Huang, Shanthoshigaa D, Tony Chin-Ian Tay, Iris Rawtaer
Predicting Mild Cognitive Impairment Through Ambient Sensing And Artificial Intelligence, Ah-Hwee Tan, Weng Yan Ying, Budhitama Subagdja, Anni Huang, Shanthoshigaa D, Tony Chin-Ian Tay, Iris Rawtaer
Research Collection School Of Computing and Information Systems
This paper reports an emerging application leveraging ambient and artificial intelligence techniques for in-home sensing and cognitive health assessment. The application involves a prospective longitudinal study, wherein non-pervasive sensing devices are installed in homes of over 63 real users undergoing clinical cognitive assessment, and digital signals of the users’ activities and behaviour are transmitted to a central cloud-based data server for further processing and analysis. Based on the sensor readings, we identify a set of digital biomarkers covering four key aspects of daily living, namely physical, activity, cognitive, and sleep, and develop a suite of customized feature extraction methods for …
Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames, Ning Han, Xun Yang, Ee-Peng Lim, Hao Chen, Qianru Sun
Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames, Ning Han, Xun Yang, Ee-Peng Lim, Hao Chen, Qianru Sun
Research Collection School Of Computing and Information Systems
Cross-modal video retrieval aims to retrieve semantically relevant videos when given a textual query, and is one of the fundamental multimedia tasks. Most top-performing methods primarily leverage Vision Transformer (ViT) to extract video features [1]-[3]. However, they suffer from the high computational complexity of ViT, especially when encoding long videos. A common and simple solution is to uniformly sample a small number (e.g., 4 or 8) of frames from the target video (instead of using the whole video) as ViT inputs. The number of frames has a strong influence on the performance of ViT, e.g., using 8 frames yields better …
Enhancing Code Vulnerability Detection Via Vulnerability-Preserving Data Augmentation, Shangqing Liu, Wei Ma, Jian Wang, Xiaofei Xie, Ruitao Feng, Yang Liu
Enhancing Code Vulnerability Detection Via Vulnerability-Preserving Data Augmentation, Shangqing Liu, Wei Ma, Jian Wang, Xiaofei Xie, Ruitao Feng, Yang Liu
Research Collection School Of Computing and Information Systems
Source code vulnerability detection aims to identify inherent vulnerabilities to safeguard software systems from potential attacks. Many prior studies overlook diverse vulnerability characteristics, simplifying the problem into a binary (0-1) classification task for example determining whether it is vulnerable or not. This poses a challenge for a single deep-learning based model to effectively learn the wide array of vulnerability characteristics. Furthermore, due to the challenges associated with collecting large-scale vulnerability data, these detectors often overfit limited training datasets, resulting in lower model generalization performance. To address the aforementioned challenges, in this work, we introduce a fine-grained vulnerability detector namely FGVulDet. …
Applicability And Challenges Of Indoor Localization Using One-Sided Round Trip Time Measurements, Quang Hai Truong, Xi Kai Justin Lam, Guru Anand Anish, Rajesh Krishna Balan
Applicability And Challenges Of Indoor Localization Using One-Sided Round Trip Time Measurements, Quang Hai Truong, Xi Kai Justin Lam, Guru Anand Anish, Rajesh Krishna Balan
Research Collection School Of Computing and Information Systems
Radio Frequency fingerprinting, based on WiFi or cellular signals, has been a popular approach for localization. However, adoptions in real-world applications have confronted with challenges due to low accuracy, especially in crowded environments. The received signal strength (RSS) could be easily interfered by a large number of other devices or strictly depends on physical surrounding environments, which may cause localization errors of a few meters. On the other hand, the fine time measurement (FTM) round-trip time (RTT) has shown compelling improvement in indoor localization with ~1-2 meter accuracy in both 2D and 3D environments [13]. This method relies on the …
Fully Automated Selfish Mining Analysis In Efficient Proof Systems Blockchains, Krishnendu Chatterjee, Amirali Ebrahimzadeh, Mehrdad Karrabi, Krzysztof Pietrzak, Michelle Yeo, Dorde Zikelic
Fully Automated Selfish Mining Analysis In Efficient Proof Systems Blockchains, Krishnendu Chatterjee, Amirali Ebrahimzadeh, Mehrdad Karrabi, Krzysztof Pietrzak, Michelle Yeo, Dorde Zikelic
Research Collection School Of Computing and Information Systems
We study selfish mining attacks in longest-chain blockchains like Bitcoin, but where the proof of work is replaced with efficient proof systems - like proofs of stake or proofs of space - and consider the problem of computing an optimal selfish mining attack which maximizes expected relative revenue of the adversary, thus minimizing the chain quality. To this end, we propose a novel selfish mining attack that aims to maximize this objective and formally model the attack as a Markov decision process (MDP). We then present a formal analysis procedure which computes an ϵ-tight lower bound on the optimal expected …
Neuron Sensitivity Guided Test Case Selection, Dong Huang, Qingwen Bu, Yichao Fu, Yuhao Qing, Xiaofei Xie, Junjie Chen, Heming Cui
Neuron Sensitivity Guided Test Case Selection, Dong Huang, Qingwen Bu, Yichao Fu, Yuhao Qing, Xiaofei Xie, Junjie Chen, Heming Cui
Research Collection School Of Computing and Information Systems
Deep Neural Networks (DNNs) have been widely deployed in software to address various tasks (e.g., autonomous driving, medical diagnosis). However, they can also produce incorrect behaviors that result in financial losses and even threaten human safety. To reveal and repair incorrect behaviors in DNNs, developers often collect rich, unlabeled datasets from the natural world and label them to test DNN models. However, properly labeling a large number of datasets is a highly expensive and time-consuming task. To address the above-mentioned problem, we propose NSS, Neuron Sensitivity Guided Test Case Selection, which can reduce the labeling time by selecting valuable test …
Criticality Aware Canvas-Based Visual Perception At The Edge, Ila Gokarn
Criticality Aware Canvas-Based Visual Perception At The Edge, Ila Gokarn
Research Collection School Of Computing and Information Systems
Efficient and effective machine perception remains a formidable challenge in sustaining high fidelity and high throughput of perception tasks on affordable edge devices. This is especially due to the continuing increase in resolution of sensor streams (e.g., video input streams generated by 4K/8K cameras and neuromorphic event cameras that produce ≥ 10 MEvents/second) and computational complexity of Deep Neural Network (DNN) models, which overwhelms edge platforms, adversely impacting machine perception efficiency. Given the insufficiency of the available computation resources, a question then arises on whether selected regions/components of the perception task can be prioritized (and executed preferentially) to achieve highest …
Unmasking The Lurking: Malicious Behavior Detection For Iot Malware With Multi-Label Classification, Ruitao Feng, Sen Li, Sen Chen, Mengmeng Ge, Xuewei Li, Xiaohong Li
Unmasking The Lurking: Malicious Behavior Detection For Iot Malware With Multi-Label Classification, Ruitao Feng, Sen Li, Sen Chen, Mengmeng Ge, Xuewei Li, Xiaohong Li
Research Collection School Of Computing and Information Systems
Current methods for classifying IoT malware predominantly utilize binary and family classifications. However, these outcomes lack the detailed granularity to describe malicious behavior comprehensively. This limitation poses challenges for security analysts, failing to support further analysis and timely preventive actions. To achieve fine-grained malicious behavior identification in the lurking stage of IoT malware, we propose MaGraMal. This approach, leveraging masked graph representation, supplements traditional classification methodology, empowering analysts with critical insights for rapid responses. Through the empirical study, which took three person-months, we identify and summarize four fine-grained malicious behaviors during the lurking stage, constructing an annotated dataset. Our evaluation …
Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou
Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou
Research Collection School Of Computing and Information Systems
Chain-of-Thought (CoT) [2, 3] guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs — a nonsequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus …
Learning Dynamic Multimodal Network Slot Concepts From The Web For Forecasting Environmental, Social And Governance Ratings, Meng Kiat Gary Ang, Ee-Peng Lim
Learning Dynamic Multimodal Network Slot Concepts From The Web For Forecasting Environmental, Social And Governance Ratings, Meng Kiat Gary Ang, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Dynamic multimodal networks are networks with node attributes from different modalities where the at- tributes and network relationships evolve across time, i.e., both networks and multimodal attributes are dynamic; for example, dynamic relationship networks between companies that evolve across time due to changes in business strategies and alliances, which are associated with dynamic company attributes from multiple modalities such as textual online news, categorical events, and numerical financial-related data. Such information can be useful in predictive tasks involving companies. Environmental, social, and gov- ernance (ESG) ratings of companies are important for assessing the sustainability risks of companies. The process of …
Few-Shot Learner Parameterization By Diffusion Time-Steps, Zhongqi Yue, Pan Zhou, Richang Hong, Hanwang Zhang, Sun Qianru
Few-Shot Learner Parameterization By Diffusion Time-Steps, Zhongqi Yue, Pan Zhou, Richang Hong, Hanwang Zhang, Sun Qianru
Research Collection School Of Computing and Information Systems
Even when using large multi-modal foundation models, few-shot learning is still challenging—if there is no proper inductive bias, it is nearly impossible to keep the nuanced class attributes while removing the visually prominent attributes that spuriously correlate with class labels. To this end, we find an inductive bias that the time-steps of a Diffusion Model (DM) can isolate the nuanced class attributes, i.e., as the forward diffusion adds noise to an image at each time-step, nuanced attributes are usually lost at an earlier time-step than the spurious attributes that are visually prominent. Building on this, we propose Time-step Few-shot (TiF) …
Gts: Gpu-Based Tree Index For Fast Similarity Search, Yifan Zhu, Ruiyao Ma, Baihua Zheng, Xiangyu Ke, Lu Chen, Yunjun Gao
Gts: Gpu-Based Tree Index For Fast Similarity Search, Yifan Zhu, Ruiyao Ma, Baihua Zheng, Xiangyu Ke, Lu Chen, Yunjun Gao
Research Collection School Of Computing and Information Systems
Similarity search, the task of identifying objects most similar to a given query object under a specific metric, has gathered significant attention due to its practical applications. However, the absence of coordinate information to accelerate similarity search and the high computational cost of measuring object similarity hinder the efficiency of existing CPU-based methods. Additionally, these methods struggle to meet the demand for high throughput data management. To address these challenges, we propose GTS, a GPU-based tree index designed for the parallel processing of similarity search in general metric spaces, where only the distance metric for measuring object similarity is known. …
To Protect Or To Hide: An Investigation On Corporate Redacted Disclosure Motives Under New Fast Act Regulation, Yan Ma, Qian Mao, Nan Hu
To Protect Or To Hide: An Investigation On Corporate Redacted Disclosure Motives Under New Fast Act Regulation, Yan Ma, Qian Mao, Nan Hu
Research Collection School Of Computing and Information Systems
China adopted amendments allowing companies to redact filings without prior approval in 2016. Leveraging this change as a quasi-nature experiment, we explore whether managers utilize redacted information to withhold bad information in the more lenient regulatory environment. Our investigation uncovers a significant shift in managerial behavior: Since 2016, managers incline to employ redactions to obscure negative news rather than safeguarding proprietary data. Furthermore, we find that the poorer firm performance and a higher cost of equity are associated with the redacted disclosures after 2016, suggesting that investors perceive an increase in firm-specific risk attributed to withholding bad news through redactions.
Friendly Sharpness-Aware Minimization, Tao Li, Pan Zhou, Zhengbao He, Xinwen Cheng, Xiaolin Huang
Friendly Sharpness-Aware Minimization, Tao Li, Pan Zhou, Zhengbao He, Xinwen Cheng, Xiaolin Huang
Research Collection School Of Computing and Information Systems
Sharpness-Aware Minimization (SAM) has been instrumental in improving deep neural network training by minimizing both training loss and loss sharpness. Despite the practical success, the mechanisms behind SAM’s generalization enhancements remain elusive, limiting its progress in deep learning optimization. In this work, we investigate SAM’s core components for generalization improvement and introduce “Friendly-SAM” (F-SAM) to further enhance SAM’s generalization. Our investigation reveals the key role of batch-specific stochastic gradient noise within the adversarial perturbation, i.e., the current minibatch gradient, which significantly influences SAM’s generalization performance. By decomposing the adversarial perturbation in SAM into full gradient and stochastic gradient noise components, …