Digital Commons Network^™

Rising From Ashes: Generalized Federated Learning Via Dynamic Parameter Reset, Jiahao Wu, Ming Hu, Yanxin Yang, Xiaofei Xie, Zekai Chen, Chenyu Song, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Federated Learning (FL) is promising for privacy-preserving collaborative model training, it suffers from low inference performance due to heterogeneous client data. Due to heterogeneous data across clients, FL training easily learns client-specific overfitting features. Existing FL methods adopt coarsegrained averaging, which can easily cause the global model to get stuck in local optima, leading to poor generalization. Specifically, this paper presents a novel FL framework, FedPhoenix, to address this issue. It stochastically resets partial parameters in each round to destroy some features of the global model, guiding FL training to learn multiple generalized features for inference rather than specific …

Instance-Level Video Depth In Groups Beyond Occlusions, Yuan Liang, Yang Zhou, Ziming Sun, Tianyi Xiang, Guiqing Li, Shengfeng He

Research Collection School Of Computing and Information Systems

Depth estimation in dynamic, multi-object scenes remains a major challenge, especially under severe occlusions. Existing monocular models, including foundation models, struggle with instance-wise depth consistency due to their reliance on global regression. We tackle this problem from two key aspects: data and methodology. First, we introduce the Group Instance Depth (GID) dataset, the first large-scale video depth dataset with instance-level annotations, featuring 101,500 frames from real-world activity scenes. GID bridges the gap between synthetic and real-world depth data by providing high-fidelity depth supervision for multi-object interactions. Second, we propose InstanceDepth, the first occlusion-aware depth estimation framework for multi-object environments. Our …

Efskip: A New Error Feedback With Linear Speedup For Compressed Federated Learning With Arbitrary Data Heterogeneity, Hongyan Bao, Pengwen Chen, Ying Sun, Zhize Li

Research Collection School Of Computing and Information Systems

Due to the communication bottleneck in distributed and decentralized federated learning applications, algorithms using compressed communication have attracted significant attention. The Error Feedback (EF) is a widely-studied compression framework for convergence with biased compressors such as top-k sparsification. Although various improvements have been obtained in recent years, the theoretical guarantee for EF-type framework is still limited. Previous works either 1) rely on strong assumptions such as bounded gradient/dissimilarity assumptions, thus can not deal with arbitrary data heterogeneity and also slow the convergence speed, or 2) can not enjoy linear speedup in the number of clients. In this work, we propose …

Scalable Graph Indexing Using Gpus For Approximate Nearest Neighbor Search, Zhonggen Li, Xiangyu Ke, Yifan Zhu, Bocheng Yu, Baihua Zheng, Yunjun Gao

Research Collection School Of Computing and Information Systems

Approximate nearest neighbor search (ANNS) in high-dimensional vector spaces has a wide range of real-world applications. Numerous methods have been proposed to handle ANNS efficiently, while graph-based indexes have gained prominence due to their high accuracy and efficiency. However, the indexing overhead of graph-based indexes remains substantial. With exponential growth in data volume and increasing demands for dynamic index adjustments, this overhead continues to escalate, posing a critical challenge.In this paper, we introduce Tagore, a fasT library accelerated by GPUs for graph indexing, which has powerful capabilities of constructing refinement-based graph indexes such as NSG and Vamana. We first introduce …

Does Social Media Undermine Trust? Institutional Trust In Civil Society And Governance Institutions, Christianna Sirindah Parr

Research Collection School of Social Sciences

What is the relationship between social media use and trust in civil society and governance institutions? In many parts of Asia, trust in government remains high despite limited political accountability and civil liberties. This study examines whether online political expression reshapes institutional trust in governance institutions and civil society organizations. The analysis considers the dual role of social media as a site for civic engagement and a channel for disaffection with formal authority. Using data from the Asian Barometer, the findings show that political expression on social media is associated with lower trust in governance institutions and higher trust in …

Upright-Net+: Enhanced Learning Of Upright Orientation For 3d Point Clouds, Xufang Pang, Feng Li, Hongjie Zhuang, Ning Ding, Xiaopin Zhong, Shengfeng He, Wenxi Liu, Bo Jiang

Research Collection School Of Computing and Information Systems

Automatic 3D shape analysis is heavily influenced by the pose of input 3D models, as the continuous nature of pose space introduces complexities that usually exceed the encoding capacities of standard deep learning frameworks. To tackle this challenge, we present Upright-Net+, an enhancement of our previous model, Upright-Net, specifically developed for estimating upright orientation in 3D point clouds. Our approach is grounded in the design principle that ”form ever follows function,” treating the natural base of an object as a functional structure that stabilizes it in its typical pose, influenced by physical laws and geometric properties. We reformulate the continuous …

Cssa-Fusion: Channel Selective And Spatial Alignment Infrared-Visible Image Fusion, Zhen Li, Zhi Zeng, Zhongrui Xiao, Ming Wen, Zhiyuan Zhang, Yibin Tian

Research Collection School Of Computing and Information Systems

Infrared-visible image fusion aims to integrate complementary information from two modalities to generate images with enriched semantic content. However, existing methods often neglect two critical aspects: the design of a local–global feature enhancement architecture and spatial alignment. To address these challenges, we propose Channel Selective and Spatial Alignment Fusion (CSSA-Fusion), a novel framework composed of two synergistic modules. The first is a selective channel and redundancy suppression module, which introduces a dual-branch selective channel attention mechanism to jointly capture local saliency and global channel importance for enhanced feature representation, and an informativeness–redundancy separation strategy to suppress redundant information while preserving …

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He

Research Collection School Of Computing and Information Systems

Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …

Pilot-C: Physics-Informed Low-Distortion Optimal Trajectory Compression, Kefei Wu, Baihua Zheng, Weiwei Sun

Research Collection School Of Computing and Information Systems

Location-aware devices continuously generate massive volumes of trajectory data, creating demand for efficient compression. Line simplification is a common solution but typically assumes 2D trajectories and ignores time synchronization and motion continuity. We propose PILOT-C, a novel trajectory compression framework that integrates frequency-domain physics modeling with error-bounded optimization. Unlike existing line simplification methods, PILOT-C supports trajectories in arbitrary dimensions, including 3D, by compressing each spatial axis independently. Evaluated on four real-world datasets, PILOT-C achieves superior performance across multiple dimensions. In terms of compression ratio, PILOT-C outperforms CISED-W, the current state-of-the-art SED-based line simplification algorithm, by an average of 19.2%. For …

General Test-Time Backdoor Detection In Split Neural Network-Based Vertical Federated Learning, Shunjie Yuan, Xinghua Li, Xuelin Cao, Haiyan Zhang, Robert H. Deng

Research Collection School Of Computing and Information Systems

As a new distributed machine learning framework, vertical federated learning (VFL) has been widely applied in the industry. However, recent studies have demonstrated that VFL faces serious challenges from backdoor attacks, which significantly hinder its further development. Although a few studies have focused on defending against VFL backdoor attacks, these defenses either do not consider the latest attack methods or show limited effectiveness. Moreover, most existing backdoor defense efforts primarily focus on backdoor attacks in horizontal federated learning (HFL) and centralized learning. Due to the unique architecture of VFL models, these methods cannot be directly applied to backdoor defense in …

Kpiroot+: An Efficient Integrated Framework For Anomaly Detection And Root Cause Analysis In Large-Scale Cloud Systems, Wenwei Gu, Renyi Zhong, Guangba Yu, Xinying Sun, Jinyang Liu, Yintong Huo, Zhuangbin Chen, Jianping Zhang, Jiazhen Gu, Yongqiang Yang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

To ensure the reliability of cloud systems, their runtime status reflecting the service quality is periodically monitored with monitoring metrics, i.e., KPIs (key performance indicators). When performance issues happen, root cause localization pinpoints the specific KPIs that are responsible for the degradation of overall service quality, facilitating prompt problem diagnosis and resolution. To this end, existing methods generally locate root-cause KPIs by identifying the KPIs that exhibit a similar anomalous trend to the overall service performance. While straightforward, solely relying on the similarity calculation may be ineffective when dealing with cloud systems with complicated interdependent services. Recent deep learning-based methods …

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module …

Towards Inclusive Digital Futures Of Cultural Heritage: Insights From A Critical Discourse Analysis Of Unesco Dialogues, Shiqing Huang, Keng Siau, Xiaoting Chen

Research Collection School Of Computing and Information Systems

Digital technologies are shaping many aspects of cultural heritage, but very little research has examined the implications of digital transformation. Drawing on concepts from Fairclough’s three-dimensional critical discourse analysis, this research examines the discourse using seven online dialogues (available on the UNESCO website) between 18 professionals who have different backgrounds and cultures to identify social practices related to the digital transformation of cultural heritage. We identify four digital transformation discourse types in professional dialogues: documentation, management, interpretation, and interaction. We also identify seven main groups: memory institutions including libraries, archives, and museums (LAMs), governments, international organizations, art and creative supporters, …

Cropcapsnet: Enhanced Capsule Network For Crop Disease Classification, Juan Qin, Linfan Deng, Cong Li, Junjie He, Haibo Pen, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

The prevention and treatment of crop diseases are crucial for the development of smart agriculture. The classification of crop diseases based on deep learning for early disease monitoring and control has become the mainstream direction of research. This paper proposes a novel deep learning model called ”CropCapsNet”, which combines Squeeze-and-Excitation Inception (SE-Inception) module and has improved capsule structure for crop disease classification. The network first extracts shallow features of input samples through double-layer convolution, then uses SE-Inception to achieve deep multi-scale feature acquisition, and finally outputs classification results through an improved capsule structure. SE-Inception adds Squeeze-and-Excitation(SE) attention after each multi-scale …

Copyright In The Generative Ai Era: Reimagining Creativity And Fairness, Huijuan Peng, David Tan

Research Collection Yong Pung How School Of Law

This article examines the need for copyright reform in response to the transformative impact of generative artificial intelligence. It identifies key legal challenges, including the absence of clear criteria for authorship and the infringement risks associated with both inputs (training of large language models) and outputs (AI-generated content). The authors argue that two overarching themes—creativity and fairness—will drive the future development of copyright law. Through a comparative analysis of how three jurisdictions—the United States, China, and Singapore—have addressed these challenges, the article offers practical and forward-looking insights for navigating the complex copyright landscape of the generative AI era.

This article …

Imprisonment When An Offender Cannot Pay A Fine, Benjamin Joshua Ong

Research Collection Yong Pung How School Of Law

According to a common-law rule in place since the 1993 case of Low Meng Chay v Public Prosecutor [1993] 1 SLR(R) 46, if the court is minded to impose a fine but the offender will clearly be unable to pay a fine, the offender should be sentenced to imprisonment instead (as opposed to a fine coupled with a default imprisonment term). While one can understand why the courts may apply this practice, the practice obscures the crucial distinction between: (a) being sentenced to a fine, then imprisoned in default of payment (which, it is submitted, is the correct course of …

A Cultural Identity Approach To The Generational Divide, Davelle Lee, Andree Hartanto

Research Collection School of Social Sciences

Some scholars have argued strongly against the idea that differences between generations are responsible for intergenerational conflict, calling for organisations and policymakers to do away with the notion of generations altogether. The current review argues that generations are an important social identity and makes the case for why generational identity should inform policy, despite inconsistent empirical evidence for generational differences. Drawing on cultural psychology and social identity theory, we find parallels between how racial and ethnic identities shape how people interpret and respond to racial diversity and so-called racial and ethnic “differences”, and how generational identity influences people's attitudes and …

Social Expectancies To Be Constantly Available And Productive As Antecedents And Consequences Of Burnout: A Longitudinal Bidirectional Investigation, Andree Hartanto, Meilan Hu, Adalia Y. H. Goh, Eddie M. W. Tong

Research Collection School of Social Sciences

Burnout has become increasingly prevalent in contemporary society, affecting not only those in the workplace but also students across various educational settings. The current study investigates whether the pervasive social expectancies to be constantly available and productive contribute to the onset and maintenance of academic burnout among university students. Using a 13-week longitudinal design and a random-intercept cross-lagged panel model, we examined the bidirectional association between social expectancies to be constantly available and productive and academic burnout. Our findings indicate that heightened social expectancies predict increases in emotional exhaustion and feelings of inadequacy in the following week. Furthermore, emotional exhaustion, …

Effectiveness Of Cognitive And Behavioral Interventions In The Treatment Of Schizophrenia: An Umbrella Review Of Meta-Analyses, Gabriel Xing Da Tan, Andree Hartanto, Zoey Khai Yee Eun, Meilan Hu, Kean J. Hsu, Nadyanna M. Majeed

Research Collection School of Social Sciences

Background: Cognitive and behavioral interventions have risen in popularity both as an adjunctive treatment to antipsychotic medication and as an alternative treatment for schizophrenia. With the growing number of such interventions, we performed an umbrella review to provide a comprehensive summary comparing the effectiveness of the different interventions among populations with schizophrenia. Methods: This umbrella review included meta-analyses evaluating cognitive and behavioral interventions for schizophrenia. Following PRISMA guidelines, the initial search yielded 4888 records, and after a three-stage screening procedure, 33 meta-analyses met the inclusion criteria for the final analysis. Results: Our findings from the 33 meta-analyses support the efficacy …

Contextual Stress Profiles And Trajectories Of Internalizing Symptoms Among Adolescents In Mexican Immigrant Families, Su Yeong Kim, Wen Wen, Kiera M. Coulter, Wei Xiang Sim, Tianlu Zhang, Jingyi Shen, Yang Hou, Yishan Shen, Ka I. Ip

Research Collection School of Social Sciences

Contextual stress experiences in early adolescents may predict distinct trajectories of depressive symptoms and anxiety across the course of adolescence. Data from 604 Mexican-origin adolescents collected from 2012 to 2020 (54% female; Mage = 12.92, SD = 0.92) showed that youth with high stress levels in multiple domains (Broadly Stressed) and those with high stress in language brokering domain only (Language Brokering Stressed) had similar levels of internalizing symptoms in early adolescence, and both groups reported higher stress than youth experiencing occasional levels of stress across domains (Occasionally Environmentally Stressed). However, youth in the Language Brokering Stressed group experienced slightly …

Reliability And Validity Of A Self-Administrated Online Assessment Of Intrinsic Capacity: A Singapore Cohort Study, Paulin Tay Straughan, William Tov, Lay Khoon Lau, Li Ling Grace Cheong, Chong Sheng Micah Tan, William Tov, Yew Yoong Ding, Wee Shiong Lim

Research Collection School of Social Sciences

Objective: To ascertain the construct validity and reliability of a self-administered web-based assessment of intrinsic capacity (IC). Design: Cross-sectional data analysis of a prospective cohort study. Settings and Participants: We included data from 6,434 respondents (age, mean (SD): 65.33 (5.81) years; 52.4% women) of the Singapore Life Panel population study who participated in the online surveys in March 2022 and May 2022.MethodsIncremental nested factor structures of IC were modelled with confirmatory factor analysis (CFA) and their goodness-of-fit were assessed mainly with root mean square error of approximation (RMSEA), comparative fit index (CFI), Tucker-Lewis index (TLI), and standardized root mean square …

Attachment To Artificial Intelligence: Development Of The Ai Attachment Scale, Construct Validation, And The Psychological Mechanisms Of Human-Ai Attachment, K Tennakoon Appuhamillage Sandeeshwara Kasturiratna, Andree Hartanto

Research Collection School of Social Sciences

Artificial intelligence (AI) systems are increasingly integrated into daily life, not only as tools but also as social partners that people may turn to for interaction and support. This raises important questions about whether, how, and why individuals form attachment-like bonds with AI, and the psychological implications of such attachments. Across five studies involving 1259 unique participants from Singapore and the U.S., the current work developed and validated the 15-item AI Attachment Scale and investigated the dispositional and motivational factors associated with attachment to AI, as well as its emotional and social outcomes. The AI Attachment Scale displayed strong psychometric …

Privately Owned Companies Dominate Renewable Energy Generation Ownership Around The World, Dyaran Bansraj, Theodor Florian Cojoianu, Xi Hu, Khaladdin Rzayev, Francisco Urzua

Research Collection College of Integrative Studies

Global sustainable finance policies are premised on publicly listed companies driving decarbonization through transparency, investor pressure, and capital market access. Analysing c. 20,000 corporate owners of renewable and fossil-fuel assets worldwide, we show the opposite: private firms own approximately 75% of global renewable generation capacity. This private dominance holds across all major technologies and regions, with listed ownership of renewable assets being the majority only in the oil & gas and technology sectors. The Paris Agreement did not alter this balance. Instead, ownership of the energy transition reflects countries' financial structures, with similar patterns observed across manufacturing, construction, and financial …

The Impact Of Value Co-Creation On Organizational Resilience In Small And Medium-Sized Traditional Foreign Trade Enterprises, Dan Yan

Dissertations and Theses Collection (Open Access)

Against the backdrop of increasing uncertainty in the global business environment, international scholarly attention to individual, group, and organizational resilience has risen significantly. Chinese export trading enterprises—especially small and medium-sized export trading enterprises(SMETEs)—face disadvantages such as small scale, weak financing capacity, limited access to information, and low brand strength. After experiencing shocks from digital transformation, the COVID-19 pandemic, the Russia–Ukraine war, and the European energy crisis, these firms have been compelled to reconsider how to enhance their organizational resilience in order to adapt to an increasingly turbulent external environment.

First, this study selects Company H as a representative case of …

Copyright Ownership And Duration Of Ai-Authored Works, Cheng Lim Saw

Research Collection Yong Pung How School Of Law

On the assumption that Parliament has endorsed the notion of AI authorship and the prospect that copyright may well subsist in works created autonomously by the AI itself, this essay further explores allied issues surrounding the ownership and duration of copyright in AI-authored works.

Stableguard: Towards Unified Copyright Protection And Tamper Localization In Latent Diffusion Models, Haoxin Yang, Bangzhen Liu, Xuemiao Xu, Cheng Xu, Yuyang Yu, Zikai Huang, Yi Wang, Shengfeng He

Research Collection School Of Computing and Information Systems

The advancement of diffusion models has enhanced the realism of AI-generated content but also raised concerns about misuse, necessitating robust copyright protection and tampering localization. Although recent methods have made progress toward unified solutions, their reliance on post hoc processing introduces considerable application inconvenience and compromises forensic reliability. We propose StableGuard, a novel framework that seamlessly integrates a binary watermark into the diffusion generation process, ensuring copyright protection and tampering localization in Latent Diffusion Models through an end-to-end design. We develop a Multiplexing Watermark VAE (MPW-VAE) by equipping a pretrained Variational Autoencoder (VAE) with a lightweight latent residual-based adapter, enabling …

Public Health Trade-Offs During A Pandemic: Mobility Decline And Hypertension Risk In India, Arpita Khanna, Tomoki Fujii

Research Collection School Of Economics

The Covid pandemic dramatically altered patterns of daily life, particularly through widespread declines in mobility due to lockdowns and social distancing measures. While the economic and epidemiological effects of these restrictions have been widely studied, their broader health implications remain underexplored. This paper investigates the relationship between mobility decline during the Covid pandemic and hypertension outcomes in India. Leveraging district-level variation in mobility from Google Community Mobility Reports and health data from the 2019–2021 Indian Demographic and Health Survey (DHS), we find that a 1 percentage point reduction in mobility over the 30 days prior to interview is associated with …

Constitutional Obiter Dicta On Male-Male Sex And Fundamental Rights In Singapore, Benjamin Joshua Ong

Research Collection Yong Pung How School Of Law

The Singapore Court of Appeal held a law prohibiting male–male sexual intercourse (s 377A of the Penal Code) unenforceable on non-rights-based grounds. The court's remarks about the rights to life and liberty (including whether sexual orientation is mutable), freedom of expression, and equality are obiter. But they are significant, since in Singapore, there are few constitutional rights cases and the courts focus on spelling out the limits to executive and legislative power without necessarily striking down exercises of such power on rights grounds. Indeed, the obiter dicta prompted the Legislature to repeal s 377A. Given the repeal, the obiter dicta …

Preparing For “Disease X”: Lessons From Tax And Non-Tax Policy Responses To The Covid-19 Pandemic In Singapore And Australia, Vincent Ooi

Research Collection Yong Pung How School Of Law

During the Covid-19 pandemic, a lack of pre-pandemic planning resulted in sub-optimal policy outcomes. Crucial lessons can be drawn from the experience of Singapore and Australia in the pandemic in implementing various tax and non-tax economic measures; lessons that can help in preparing for the next pandemic (“Disease X”). This article analyses and critically evaluates three main categories of economic measures: direct payments, tax measures and non-tax “other” measures. It finds that direct payment measures such as jobs support had a very significant impact on preserving jobs and supporting the economy. However, eligibility conditions have to be carefully designed for …

Local Problems, Global Solutions? Making It Rain In Hong Kong C. 1890-1930, Fiona Williamson

Research Collection College of Integrative Studies

The late nineteenth to early twentieth century saw a small but dedicated rise in experimental rainmaking. The possibility that humanity might one day be able to control the weather – especially to alleviate drought – was very attractive to governments and private investors. The late nineteenth century was an era of scientific optimism and a number of rainmaking experiments across the world had brought the potential for weather control out of the realms of discourse and literature and further into tangible near-future science. There has been a small but thorough historiographical literature on this subject, focusing largely on American, British, …