Digital Commons Network^™

Task Scheduling Strategy For 3dpcp Considering Multidynamic Information Perturbation In Green Scene, Jianjia He, Jian Wu, Keng Siau

Research Collection School Of Computing and Information Systems

The 3D printing cloud platform (3DPCP) plays a pivotal role in breaking down the information silos between supply and demand, effectively reducing waste through information integration and intelligent production. However, due to the complexity of 3DPCP scheduling in green scenes and the multidynamic information perturbations, unveils problems in traditional task scheduling methods in 3DPCP. These issues manifest as incomplete considerations, subpar green performance, and weak adaptability to dynamic changes. There is an urgent need to design practical methods to realize the multidynamic information perturbations in green scenes within 3DPCP. Therefore, this article first defines the 3DPCP task scheduling problem for …

Peep With A Mirror: Breaking The Integrity Of Android App Sandboxing Via Unprivileged Cache Side Channel, Yan Lin, Joshua Wong, Xiang Li, Haoyu Ma, Debin Gao

Research Collection School Of Computing and Information Systems

Application sandboxing is a well-established security principle employed in the Android platform to safeguard sensitive information. However, hardware resources, specifically the CPU caches, are beyond the protection of this software-based mechanism, leaving room for potential side-channel attacks. Existing attacks against this particular weakness of app sandboxing mainly target shared components among apps, hence can only observe system-level program dynamics (such as UI tracing). In this work, we advance cache side-channel attacks by demonstrating the viability of non-intrusive and fine-grained probing across different app sandboxes, which have the potential to uncover app-specific and private program behaviors, thereby highlighting the importance of …

Optimization Of Customer Service And Driver Dispatch Areas For On-Demand Food Delivery, Jingfeng Yang, Hoong Chuin Lau, Hai Wang

Research Collection School Of Computing and Information Systems

With the rapid development and popularization of mobile and wireless communication technologies, on-demand food delivery (OFD) platforms have been able to connect restaurants, customers, and drivers in real time, drastically changing dining and food delivery services. Motivated by the critical need for supply and demand management in the on-demand food delivery market, we focus on the optimization of customer service area and driver dispatch area for on-demand food delivery services. Specifically, for each restaurant, the platform needs to decide the (1) customer service area (CSA), i.e., the surrounding area within which customers can see the restaurant’s information and order food …

Anopay: Anonymous Payment For Vehicle Parking With Updatable Credential, Yang Yang, Wenyi Xue, Yonghua Zhan, Minming Huang, Yingjiu Li, Robert H. Deng

Research Collection School Of Computing and Information Systems

Many existing anonymous parking payment schemes lack high efficiency and flexibility. For instance, the calculation and communication costs involved in payment may linearly increase with the payment amount. In this paper, we propose an anonymous payment system (dubbed AnoPay) for vehicle parking, which leverages updatable attribute-based anonymous credentials and efficient zero-knowledge proof (ZKP) to achieve user anonymity and constant overhead for parking fee payment. To further improve the efficiency, we design a secure parking fee aggregation protocol based on linear homomorphic encryption to aggregate parking transactions, where the amount of each parking transaction is hidden and the privacy of the …

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 …

Sibo : A Simple Booster For Parameter-Efficient Fine-Tuning, Zhihao Wen, Jie Zhang, Yuan Fang

Research Collection School Of Computing and Information Systems

Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time. Latest advancements in parameter-efficient fine-tuning (PEFT) techniques, such as Adapter tuning and LoRA, allow for adjustments to only a minor fraction of the parameters of these LLMs. Concurrently, it has been noted that the issue of over-smoothing diminishes the effectiveness of these Transformer-based LLMs, resulting in suboptimal performances in downstream tasks. In this paper, we present SIBO, which is a SImple BOoster to enhance PEFT, by injecting an initial residual. SIBO is straightforward and readily extensible to a range of state-of-the-art PEFT techniques to alleviate …

Tackling Stackelberg Network Interdiction Against A Boundedly Rational Adversary, Tien Mai, Avinandan Bose, Arunesh Sinha, Thanh Nguyen, Ayushman Kumar Singh

Research Collection School Of Computing and Information Systems

This work studies Stackelberg network interdiction games --- an important class of games in which a defender first allocates (randomized) defense resources to a set of critical nodes on a graph while an adversary chooses its path to attack these nodes accordingly. We consider a boundedly rational adversary in which the adversary's response model is based on a dynamic form of classic logit-based (quantal response) discrete choice models. The resulting optimization is non-convex and additionally, involves complex terms that sum over exponentially many paths. We tackle these computational challenges by presenting new efficient algorithms with solution guarantees. First, we present …

Planning Like Human : A Dual-Process Framework For Dialogue Planning, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, Bing Qin

Research Collection School Of Computing and Information Systems

In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to their reactive nature. Traditional approaches to enhance dialogue planning in LLMs, ranging from elaborate prompt engineering to the integration of policy networks, either face efficiency issues or deliver suboptimal performance. Inspired by the dual-process theory in psychology, which identifies two distinct modes of thinking—intuitive (fast) and analytical (slow), we propose the Dual-Process Dialogue Planning (DPDP) framework. DPDP embodies this theory through two complementary planning systems: an instinctive policy model for familiar …

Analyzing Temporal Complex Events With Large Language Models? A Benchmark Towards Temporal, Long Context Understanding, Zhihan Zhang, Yixin Cao, Chenchen Ye, Ma. Yunshan, Lizi Liao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events.We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, …

Synergizing Large Language Models And Pre-Trained Smaller Models For Conversational Intent Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang

Research Collection School Of Computing and Information Systems

In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs’ feature space to correct cluster distortion and promote robust learning …

A Survey On Neural Question Generation : Methods, Applications, And Prospects, Shasha Guo, Lizi Liao, Cuiping Li, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

In this survey, we present a detailed examination of the advancements in Neural Question Generation (NQG), a field leveraging neural network techniques to generate relevant questions from diverse inputs like knowledge bases, texts, and images. The survey begins with an overview of NQG’s background, encompassing the task’s problem formulation, prevalent benchmark datasets, established evaluation metrics, and notable applications. It then methodically classifies NQG approaches into three predominant categories: structured NQG, which utilizes organized data sources, unstructured NQG, focusing on more loosely structured inputs like texts or visual content, and hybrid NQG, drawing on diverse input modalities. This classification is followed …

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 …

Firm-Level Ai Ethical Awareness: Measurement And Effects, Yan Ma, Nan Hu

Research Collection School Of Computing and Information Systems

With rapid integration of AI technologies into business operation, ethical issues associated with AI development, implementation, and deployment, has become increasingly conspicuous. An effective measure of firm-level AI Ethical Awareness (FAIEA) is crucial for both academics and practitioners to assess FAIEA efficiently. In this study, based on qualitative information in earning conference call, we construct and validate a firm specific measure of FAIEA. Upon establishing a reliable measure, we explore the determinants and consequence of FAIEA. We find Corporate Social Responsibility (CSR) engagement and the presence of a Chief Information Officer (CIO) as key determinants of higher FAIEA, suggesting the …

Unifying Global-Local Representations In Salient Object Detection With Transformers, Sucheng Ren, Nanxuan Zhao, Qiang Wen, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of local details. In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the representations from shallow to deep layers. With the global view in very shallow layers, the transformer encoder preserves more local representations to recover the spatial details in final saliency maps. Besides, as each layer can capture …

Speaker Verification In Agent-Generated Conversations, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

The recent success of large language models (LLMs) has attracted widespread interest to develop role-playing conversational agents personalized to the characteristics and styles of different speakers to enhance their abilities to perform both general and special purpose dialogue tasks. However, the ability to personalize the generated utterances to speakers, whether conducted by human or LLM, has not been well studied. To bridge this gap, our study introduces a novel evaluation challenge: speaker verification in agent-generated conversations, which aimed to verify whether two sets of utterances originate from the same speaker. To this end, we assemble a large dataset collection encompassing …

Towards Gradient-Based Time-Series Explanations Through A Spatiotemporal Attention Network, Min Hun Lee

Research Collection School Of Computing and Information Systems

In this paper, we explore the feasibility of using a transformer-based, spatiotemporal attention network (STAN) for gradient-based time-series explanations. First, we trained the STAN model for video classifications using the global and local views of data and weakly supervised labels on time-series data (i.e. the type of an activity). We then leveraged a gradient-based XAI technique (e.g. saliency map) to identify salient frames of time-series data. According to the experiments using the datasets of four medically relevant activities, the STAN model demonstrated its potential to identify important frames of videos.

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 …

Larp: Language Audio Relational Pre‑Training For Cold‑Start Playlist Continuation, Rebecca Salganik, Xiaohao Liu, Yunshan Ma, Jian Kang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital to the success of music streaming services. Currently, many existing playlist continuation approaches rely on collaborative filtering methods to perform their recommendations. However, such methods will struggle to recommend songs that lack interaction data, an issue known as the cold-start problem. Current approaches to this challenge design complex mechanisms for extracting relational signals from sparse collaborative signals and integrating them into content representations. However, these approaches …

An Llm-Assisted Easy-To-Trigger Poisoning Attack On Code Completion Models: Injecting Disguised Vulnerabilities Against Strong Detection, Shenao Yan, Shen Wang, Yue Duan, Hanbin Hong, Kiho Lee, Doowon Kim, Yuan Hong

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can covertly alter the model outputs. To address this critical security challenge, we introduce CODEBREAKER, a pioneering LLM-assisted backdoor attack framework on code completion models. Unlike recent attacks that embed malicious payloads in detectable or irrelevant sections of the code (e.g., comments), CODEBREAKER leverages LLMs (e.g., GPT-4) for sophisticated payload transformation (without affecting functionalities), ensuring that both the poisoned data for fine-tuning and generated code can evade strong …

Path-Choice-Constrained Bus Bridging Design Under Urban Rail Transit Disruptions, Yiyang Zhu, Jian Gang Jin, Hai Wang

Research Collection School Of Computing and Information Systems

Although urban rail transit systems play a crucial role in urban mobility, they frequently suffer from unexpected disruptions due to power loss, severe weather, equipment failure, and other factors that cause significant disruptions in passenger travel and, in turn, socioeconomic losses. To alleviate the inconvenience of affected passengers, bus bridging services are often provided when rail service has been suspended. Prior research has yielded various methodologies for effective bus bridging services; however, they are mainly based on the strong assumption that passengers must follow predetermined bus bridging routes. Less attention is paid to passengers’ path choice behaviors, which could affect …

Nonfactoid Question Answering As Query-Focused Summarization With Graph-Enhanced Multihop Inference, Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam

Research Collection School Of Computing and Information Systems

Nonfactoid question answering (QA) is one of the most extensive yet challenging applications and research areas in natural language processing (NLP). Existing methods fall short of handling the long-distance and complex semantic relations between the question and the document sentences. In this work, we propose a novel query-focused summarization method, namely a graph-enhanced multihop query-focused summarizer (GMQS), to tackle the nonfactoid QA problem. Specifically, we leverage graph-enhanced reasoning techniques to elaborate the multihop inference process in nonfactoid QA. Three types of graphs with different semantic relations, namely semantic relevance, topical coherence, and coreference linking, are constructed for explicitly capturing the …

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 …

Neural Network Semantic Backdoor Detection And Mitigation: A Causality-Based Approach, Bing Sun, Jun Sun, Wayne Koh, Jie Shi

Research Collection School Of Computing and Information Systems

Different from ordinary backdoors in neural networks which are introduced with artificial triggers (e.g., certain specific patch) and/or by tampering the samples, semantic backdoors are introduced by simply manipulating the semantic, e.g., by labeling green cars as frogs in the training set. By focusing on samples with rare semantic features (such as green cars), the accuracy of the model is often minimally affected. Since the attacker is not required to modify the input sample during training nor inference time, semantic backdoors are challenging to detect and remove. Existing backdoor detection and mitigation techniques are shown to be ineffective with respect …

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 …

Clamber: A Benchmark Of Identifying And Clarifying Ambiguous Information Needs In Large Language Models, Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction. To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy. Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs.Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries, even enhanced by chain-of-thought (CoT) and few-shot prompting. These techniques may result in overconfidence …

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) …

Catalysing Growth: State Of Asean University Innovation And Entrepreneurship: Report 2024, Abdullah Khurshid, Dexter Ye Kai Tan, Gabrielle Lay Khim Tan

Research Collection Institute of Innovation and Entrepreneurship

Over the past few years, Southeast Asia has captured global attention with its remarkable economic growth, driven by strong tailwinds. This has led to the expansion of its middle-class consumer base that is actively participating in while benefitting from the region’s rapidly expanding digital economy. In such a climate, there is tremendous potential for Innovation and Entrepreneurship (I&E) to be a critical economic driver. Homegrown startups in different Southeast Asian countries have introduced technology-first solutions that have scaled across the region, pushing businesses to innovate rapidly. Moreover, startups promote inclusive growth by leveraging scalable internet platforms and novel technologies to …

"Digital-First Libraries" Developing And Managing Digital Platforms And Services In Smu Libraries, Salihin Mohammed Ali

Research Collection Library

Agenda:

SMU Background

Digital Transformation Areas

Platform Management

Trends & Challenges

Cross-Exchange Crypto Risk: A High-Frequency Dynamic Network Perspective, Yifu Wang, Wanbo Lu, Min-Bin Liu, Rui Ren, Wolfgang Karl Hardle

Sim Kee Boon Institute for Financial Economics

Cross-exchange crypto trading presents inherent risks, particularly for centralized exchanges. Investors observe exacerbating crypto volatility and counterparty risk and would like to quantify these elements of crypto trades. The multiple exchanges require a multivariate view on the structures of risk spillover across exchanges. Here, a Multivariate Heterogeneous AutoRegression (MHAR) model is designed and analyzed, accommodating the stylized facts of crypto markets, including 24/7 trading and the long-memory effect on return variations. The proposed MHAR approach clearly reveals the intensity of interconnectedness among exchanges during extreme events, e.g., the Bitcoin market. Additionally, one observes extremely volatile eigenvector centralities of Futures Exchange …

Hiv Estimation Using Population-Based Surveys With Non-Response: A Partial Identification Approach, Oyelola A. Adegboye, Tomoki Fujii, Denis H. Y. Leung, Siyu Li

Research Collection School Of Economics

HIV estimation using data from the demographic and health surveys (DHS) is limited by the presence of non-response and test refusals. Conventional adjustments such as imputation require the data to be missing at random. Methods that use instrumental variables allow the possibility that prevalence is different between the respondents and non-respondents, but their performance depends critically on the validity of the instrument. Using Manski's partial identification approach, we form instrumental variable bounds for HIV prevalence from a pool of candidate instruments. Our method does not require all candidate instruments to be valid. We use a simulation study to evaluate and …