Digital Commons Network^™

Difference Of Convex Functions Programming For Policy Optimization In Reinforcement Learning, Akshat Kumar

Research Collection School Of Computing and Information Systems

We formulate the problem of optimizing an agent's policy within the Markov decision process (MDP) model as a difference-of-convex functions (DC) program. The DC perspective enables optimizing the policy iteratively where each iteration constructs an easier-to-optimize lower bound on the value function using the well known concave-convex procedure. We show that several popular policy gradient based deep RL algorithms (both for discrete and continuous state, action spaces, and stochastic/deterministic policies) such as actor-critic, deterministic policy gradient (DPG), and soft actor critic (SAC) can be derived from the DC perspective. Additionally, the DC formulation enables more sample efficient learning approaches by …

Learning Multi-Faceted Prototypical User Interests, Nhu Thuat Tran, Hady W. Lauw

Research Collection School Of Computing and Information Systems

We seek to uncover the latent interest units from behavioral data to better learn user preferences under the VAE framework. Existing practices tend to ignore the multiple facets of item characteristics, which may not capture it at appropriate granularity. Moreover, current studies equate the granularity of item space to that of user interests, which we postulate is not ideal as user interests would likely map to a small subset of item space. In addition, the compositionality of user interests has received inadequate attention, preventing the modeling of interactions between explanatory factors driving a user's decision. To resolve this, we propose …

Hjg: An Effective Hierarchical Joint Graph For Anns In Multi-Metric Spaces, Yifan Zhu, Lu Chen, Yunjun Gao, Ruiyao Ma, Baihua Zheng, Jingwen Zhao

Research Collection School Of Computing and Information Systems

Owing to the widespread deployment of smartphones and networked devices, massive amount of data in different types are generated every day, including numeric data, locations, text data, images, etc. Nearest neighbour search in multi-metric spaces has attracted much attention, as it can accommodate any type of data and support search on flexible combinations of multiple metrics. However, most existing methods focus on single metric queries, failing to answer multi-metric queries efficiently due to the complex metric combinations. In this paper, for the first time, we study the approximate nearest neighbour search (ANNS) in multi-metric spaces, and propose HJG, a hierarchical …

Unraveling The ‘Anomaly’ In Time Series Anomaly Detection: A Self-Supervised Tri-Domain Solution, Yuting Sun, Guansong Pang, Guanhua Ye, Tong Chen, Xia Hu, Hongzhi Yin

Research Collection School Of Computing and Information Systems

The ongoing challenges in time series anomaly detection (TSAD), including the scarcity of anomaly labels and the variability in anomaly lengths and shapes, have led to the need for a more robust and efficient solution. As limited anomaly labels hinder traditional supervised models in anomaly detection, various state-of-the-art (SOTA) deep learning (DL) techniques (e.g., self-supervised learning) are introduced to tackle this issue. However, they encounter difficulties handling variations in anomaly lengths and shapes, limiting their adaptability to diverse anomalies. Additionally, many benchmark datasets suffer from the problem of having explicit anomalies that even random functions can detect. This problem is …

Grasper: A Generalist Pursuer For Pursuit-Evasion Problems, Pengdeng Li, Shuxin Li, Xinrun Wang, Jakub Cerny, Youzhi Zhang, Stephen Mcaleer, Hau Chan, Bo An

Research Collection School Of Computing and Information Systems

Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an evader in graph-based environments such as urban street networks. Recent advancements have demonstrated the effectiveness of the pre-training and fine-tuning paradigm in Policy-Space Response Oracles (PSRO) to improve scalability in solving large-scale PEGs. However, these methods primarily focus on specific PEGs with fixed initial conditions that may vary substantially in real-world scenarios, which significantly hinders the applicability of the traditional methods. To address this issue, we introduce Grasper, a GeneRAlist purSuer for Pursuit-Evasion pRoblems, capable of efficiently generating pursuer policies tailored to specific PEGs. Our contributions are threefold: …

Plug-And-Play Policy Planner For Large Language Model Powered Dialogue Agents, Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs. Most existing studies enable the dialogue policy planning of LLMs using various prompting schemes or iteratively enhance this capability in handling the given case with verbal AI feedback. However, these approaches are either bounded by the policy planning capability of the frozen LLMs or hard to be transferred to new cases. In this work, we introduce a new dialogue policy planning paradigm to strategize LLMs for proactive dialogue …

Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm, Xuan Zhang, Wei Gao

Research Collection School Of Computing and Information Systems

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents …

Ein Bericht Aus Einer Akademie: Writing About Germany's Lost Jewish Scholars, 80 Years On, J.G. Allen

Research Collection Yong Pung How School Of Law

This volume explores the life and work of F.A. Mann—a German-born and (mostly) German-educated jurist who spent the operative parts of his professional life in the United Kingdom (UK). The project on which the volume is based set out to understand Mann’s life as a lawyer and describe his legacy—in English law, and also in German, European, and international law.

Instant3d: Instant Text-To-3d Generation, Ming Li, Pan Zhou, Jia-Wei Liu, Jussi Keppo, Shuicheng Yan, Xiangyu Xu

Research Collection School Of Computing and Information Systems

Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core …

The Impact Of Avatar Completeness On Embodiment And The Detectability Of Hand Redirection In Virtual Reality, Martin Feick, Andre Zenner, Simon Seibert, Anthony Tang, Antonio Krüger

Research Collection School Of Computing and Information Systems

To enhance interactions in VR, many techniques introduce offsets between the virtual and real-world position of users’ hands. Nevertheless, such hand redirection (HR) techniques are only effective as long as they go unnoticed by users—not disrupting the VR experience. While several studies consider how much unnoticeable redirection can be applied, these focus on mid-air floating hands that are disconnected from users’ bodies. Increasingly, VR avatars are embodied as being directly connected with the user’s body, which provide more visual cue anchoring, and may therefore reduce the unnoticeable redirection threshold. In this work, we studied more complete avatars and their effect …

Vaid: Indexing View Designs In Visual Analytics System, Lu Ying, Aoyu Wu, Haotian Li, Zikun Deng, Ji Lan, Jiang Wu, Yong Wang, Huamin Qu, Dazhen Deng, Yingcai Wu

Research Collection School Of Computing and Information Systems

Visual analytics (VA) systems have been widely used in various application domains. However, VA systems are complex in design, which imposes a serious problem: although the academic community constantly designs and implements new designs, the designs are difficult to query, understand, and refer to by subsequent designers. To mark a major step forward in tackling this problem, we index VA designs in an expressive and accessible way, transforming the designs into a structured format. We first conducted a workshop study with VA designers to learn user requirements for understanding and retrieving professional designs in VA systems. Thereafter, we came up …

Reinforcement Learning With Maskable Stock Representation For Portfolio Management In Customizable Stock Pools, Wentao Zhang, Yilei Zhao, Shuo Sun, Jie Ying, Yonggang Xie, Zitao Song, Xinrun Wang, Bo An

Research Collection School Of Computing and Information Systems

Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting with financial markets. However, existing work mostly focuses on fixed stock pools, which is inconsistent with investors’ practical demand. Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e.g., adding one popular stocks), which lead to customizable stock pools (CSPs). Existing …

From Tweets To Token Sales: Assessing Ico Success Through Social Media Sentiments, Donghao Huang, S. Samuel, Quoc Toan Huynh, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

With the advent of social network technology, the influence of collective opinions has significantly impacted business, marketing, and fundraising. Particularly in the blockchain space, Initial Coin Offerings (ICOs) gain substantial exposure across various online platforms. Yet, the intricate relationships among these elements remain largely unexplored. This study aims to investigate the relationships between social media sentiment, engagement metrics, and ICO success. We hypothesize a positive correlation between favorable sentiment in ICO-related tweets and overall project success. Additionally, we recognize social media engagement indicators (mentions, retweets, likes, follower counts) as critical factors affecting ICO performance. Employing machine learning techniques, we conduct …

Algorithms For Canvas-Based Attention Scheduling With Resizing, Yigong Hu, Ila Gokarn, Shengzhong Liu, Archan Misra, Tarek Adbelzaher

Research Collection School Of Computing and Information Systems

Canvas-based attention scheduling was recently pro-posed to improve the efficiency of real-time machine perception systems. This framework introduces a notion of focus locales, referring to those areas where the attention of the inference system should “allocate its attention”. Data from these locales (e.g., parts of the input video frames containing objects of interest) are packed together into a smaller canvas frame which is processed by the downstream machine learning algorithm. Compared with processing the entire input data frame, this practice saves resources while maintaining inference quality. Previous work was limited to a simplified solution where the focus locales are quantized …

Anomalyclip: Object-Agnostic Prompt Learning For Zero-Shot Anomaly Detection, Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, Jiming Chen

Research Collection School Of Computing and Information Systems

Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due to various concerns, e.g., data privacy, yet it is challenging since the models need to generalize to anomalies across different domains where the appearance of foreground objects, abnormal regions, and background features, such as defects/tumors on different products/ organs, can vary significantly. Recently large pre-trained vision-language models (VLMs), such as CLIP, have demonstrated strong zero-shot recognition ability in various vision tasks, including anomaly detection. However, their …

Multiple Continuous Top-K Queries Over Data Stream, Rui Zhu, Yujin Jia, Xiaochun Yang, Baihua Zheng, Bin Wang, Chuanyu Zong

Research Collection School Of Computing and Information Systems

Continuous top-k" role="presentation" style="box-sizing: border-box; display: inline-block; line-height: 0; font-size: 18.72px; font-size-adjust: none; overflow-wrap: normal; word-spacing: normal; text-wrap-mode: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border: 0px; margin: 0px; padding: 1px 0px; position: relative;">kk query over sliding window is a fundamental challenge in the domain of streaming data management. Specifically, a continuous top-k query q" role="presentation" style="box-sizing: border-box; display: inline-block; line-height: 0; font-size: 18.72px; font-size-adjust: none; overflow-wrap: normal; word-spacing: normal; text-wrap-mode: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border: 0px; margin: 0px; padding: 1px 0px; position: relative;" …

Discovering Personalized Characteristic Communities In Attributed Graphs, Yudong Niu, Yuchen Li, Panagiotis Karras, Yanhao Wang, Zhao Li

Research Collection School Of Computing and Information Systems

What is the widest community in which a person exercises a strong impact? Although extensive attention has been devoted to searching communities containing given individuals, the problem of finding their unique communities of influence has barely been examined. In this paper, we study the novel problem of Characteristic cOmmunity Discovery (COD) in attributed graphs. Our goal is to identify the largest community, taking into account the query attribute, in which the query node has a significant impact. The key challenge of the COD problem is that it requires evaluating the influence of the query node over a large number of …

Quantum Machine Learning For Credit Scoring, Nikolaos Schetakis, Davit Aghamalyan, Micheael Boguslavsky, Agnieszka Rees, Marc Rakotomalala, Paul Robert Griffin

Research Collection School Of Computing and Information Systems

This study investigates the integration of quantum circuits with classical neural networks for enhancing credit scoring for small- and medium-sized enterprises (SMEs). We introduce a hybrid quantum–classical model, focusing on the synergy between quantum and classical rather than comparing the performance of separate quantum and classical models. Our model incorporates a quantum layer into a traditional neural network, achieving notable reductions in training time. We apply this innovative framework to a binary classification task with a proprietary real-world classical credit default dataset for SMEs in Singapore. The results indicate that our hybrid model achieves efficient training, requiring significantly fewer epochs …

Scaling Up Cooperative Multi-Agent Reinforcement Learning Systems, Minghong Geng

Research Collection School Of Computing and Information Systems

Cooperative multi-agent reinforcement learning methods aim to learn effective collaborative behaviours of multiple agents performing complex tasks. However, existing MARL methods are commonly proposed for fairly small-scale multi-agent benchmark problems, wherein both the number of agents and the length of the time horizons are typically restricted. My initial work investigates hierarchical controls of multi-agent systems, where a unified overarching framework coordinates multiple smaller multi-agent subsystems, tackling complex, long-horizon tasks that involve multiple objectives. Addressing another critical need in the field, my research introduces a comprehensive benchmark for evaluating MARL methods in long-horizon, multi-agent, and multi-objective scenarios. This benchmark aims to …

Cornac-Ab : An Open-Source Recommendation Framework With Native A/B Testing Integration, Rong Sheng Ong, Quoc Tuan Truong, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Recommender systems significantly impact user experience across diverse domains, yet existing frameworks often prioritize offline evaluation metrics, neglecting the crucial integration of A/B testing for forward-looking assessments. In response, this paper introduces a new framework seamlessly incorporating A/B testing into the Cornac recommendation library. Leveraging a diverse collection of model implementations in Cornac, our framework enables effortless A/B testing experiment setup from offline trained models. We introduce a carefully designed dashboard and a robust backend for efficient logging and analysis of user feedback. This not only streamlines the A/B testing process but also enhances the evaluation of recommendation models in …

Term Importance For Transformer-Based Qa Retrieval : A Case Study Of Stackexchange, Bryan Zhi Yang Tan, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Question-answering (QA) retrieval is the task of retrieving the most relevant answer to a given question from a collection of answers. Various approaches to QA retrieval have been developed recently. One successful and popular model is Contextualized Late Interaction over BERT (ColBERT), a transformer-based approach that adopts a query-document scoring mechanism that retains the granularity of transformer matching, whilst improving on efficiency. However, one key limitation is that it requires further fine-tuning for new query or collection types. In this work, we explore and propose several non-parametric retrieval augmentation methods based on explicit signals of term importance that improve over …

Baffle : Hiding Backdoors In Offline Reinforcement Learning Datasets, Chen Gong, Zhou Yang, Yunpeng Bai, Junda He, Jieke Shi, Kecen Li, Arunesh Sinha, Bowen Xu, Xinwen Hou, David Lo, Tianhao Wang

Research Collection School Of Computing and Information Systems

Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL paradigm because it saves the interactions with environments. In offline RL, data providers share large pre-collected datasets, and others can train high-quality agents without interacting with the environments. This paradigm has demonstrated effectiveness in critical tasks like robot control, autonomous driving, etc. However, less attention is paid to investigating the security threats to the offline RL system. This paper focuses on backdoor attacks, where some perturbations are added to the data (observations) such that given …

Learning Adversarial Semantic Embeddings For Zero-Shot Recognition In Open Worlds, Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning

Research Collection School Of Computing and Information Systems

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side semantic information is known during training. Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes. To tackle this combined ZSL and OSR problem, we consider the case of “Zero-Shot Open-Set Recognition” (ZS-OSR), where a model is trained under the ZSL …

An Evaluation Of Heart Rate Monitoring With In-Ear Microphones Under Motion, Kayla-Jade Butkow, Ting Dang, Andrea Ferlini, Dong Ma, Yang Liu, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

With the soaring adoption of in-ear wearables, the research community has started investigating suitable in-ear heart rate detection systems. Heart rate is a key physiological marker of cardiovascular health and physical fitness. Continuous and reliable heart rate monitoring with wearable devices has therefore gained increasing attention in recent years. Existing heart rate detection systems in wearables mainly rely on photoplethysmography (PPG) sensors, however, these are notorious for poor performance in the presence of human motion. In this work, leveraging the occlusion effect that enhances low-frequency bone-conducted sounds in the ear canal, we investigate for the first time in-ear audio-based motion-resilient …

Cmd: Co-Analyzed Iot Malware Detection And Forensics Via Network And Hardware Domains, Ziming Zhao, Zhaoxuan Li, Jiongchi Yu, Fan Zhang, Xiaofei Xie, Haitao Xu, Binbin Chen

Research Collection School Of Computing and Information Systems

With the widespread use of Internet of Things (IoT) devices, malware detection has become a hot spot for both academic and industrial communities. Existing approaches can be roughly categorized into network-side and host-side. However, existing network-side methods are difficult to capture contextual semantics from cross-source traffic, and previous host-side methods could be adversary-perceived and expose risks for tampering. More importantly, a single perspective cannot comprehensively track the multi-stage lifecycle of IoT malware. In this paper, we present CMD, a co-analyzed IoT malware detection and forensics system by combining hardware and network domains. For the network part, CMD proposes a tailored …

Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt ( PTP ) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects …

Time-Controllable Keyword Search Scheme With Efficient Revocation In Mobile E-Health Cloud, Yinbin Miao, Feng Li, Xinghua Li, Zhiquan Liu, Jianting Ning, Hongwei Li, Kim-Kwang Raymond Choo, Deng, Robert H.

Research Collection School Of Computing and Information Systems

Electronic health (e-health) systems may outsource data such as patient e-health records to mobile cloud servers for efficiency gains (e.g., minimizing local storage and computation costs). However, such a move may result in privacy implications in the presence of semi-honest cloud servers. Searchable Encryption (SE) can potentially facilitate privacy-preserving searches based on keywords for encrypted data stored in the mobile cloud, but most existing SE solutions do not support temporal access control (i.e., a mechanism that grants access permissions to users for specified time ranges). Hence, in this paper we design a time-controllable keyword search scheme by using an attribute-based …

A Survey On Searchable Symmetric Encryption, Feng Li, Jianfeng Ma, Yinbin Miao, Ximeng Liu, Jianting Ning, Robert H. Deng

Research Collection School Of Computing and Information Systems

Outsourcing data to the cloud has become prevalent, so Searchable Symmetric Encryption (SSE), one of the methods for protecting outsourced data, has arisen widespread interest. Moreover, many novel technologies and theories have emerged, especially for the attacks on SSE and privacy-preserving. But most surveys related to SSE concentrate on one aspect (e.g., single keyword search, fuzzy keyword search) or lack in-depth analysis. Therefore, we revisit the existing work and conduct a comprehensive analysis and summary. We provide an overview of state-of-the-art in SSE and focus on the privacy it can protect. Generally, (1) we study the work of the past …

Ethical Imperatives In Ai-Driven Educational Assessment: Framework And Implications, Ming Soon Tristan Lim

Dissertations and Theses Collection (Open Access)

This dissertation embarks on an extensive exploration of the ethical challenges emerging from the integration of AI in educational assessments. It uncovers the complex interplay between AI and the ethical imperatives these technologies pose within educational assessments.

Amidst the rapid development of AI-enabled educational technologies, such as Ubiquitous, Adaptive, and Immersive technologies, this research identifies a notable gap in literature specifically concerning the ethical imperatives and implications of AI in educational assessments. Addressing this gap, the dissertation has three primary objectives: to comprehend and analyze the underpinning educational technologies driving assessments, to elucidate the intricate relationship between AI, ethics, and …

Is This Behavior Impressive Or Repulsive? The Influence Of Our Ecology On Our Social Evaluations, Kai Lin Lynn Tan

Dissertations and Theses Collection (Open Access)

Sexual unrestrictedness, impulsivity, and seeking immediate gratification—these traits generally carry negative connotations and tend to be frowned upon. However, are they necessarily maladaptive? Evolutionary psychologists map these traits onto a behavioural cluster known as a fast life strategy. While a wide body of work has examined many types of prejudices (e.g., sexism, ageism, racism, classism, attractiveness bias etc.) the literature has yet to examine prejudices against people who display behaviours that lie on the life history strategy continuum. I propose that in our modern world where life is relatively predictable and mortality rates are lower than in ancestral times, there …