Databases and Information Systems Commons^™

Lighttransfer: Your Long-Context Llm Is Secretly A Hybrid Model With Effortless Adaptation, Xuan Zhang, Fengzhuo Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin

Research Collection School Of Computing and Information Systems

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large transformer backbones, we explore transitioning transformer models into hybrid architectures for a more efficient generation. In this work, we propose LightTransfer, a lightweight method that transforms models such as LLaMA into hybrid variants. Our approach identifies lazy layers -- those focusing on recent or initial tokens -- and replaces their full attention with streaming attention. This transformation can be performed without any training for long-context …

Ponzilens+: Visualizing Bytecode Actions For Smart Ponzi Scheme Identification, Xiaolin Wen, Tai D. Nguyen, Shaolun Ruan, Qiaomu Shen, Jun Sun, Feida Zhu, Yong Wang

Research Collection School Of Computing and Information Systems

With the prevalence of smart contracts, smart Ponzi schemes have become a common fraud on blockchain and have caused significant financial loss to cryptocurrency investors in the past few years. Despite the critical importance of detecting smart Ponzi schemes, a reliable and transparent identification approach adaptive to various smart Ponzi schemes is still missing. To fill the research gap, we first extract semantic-meaningful actions to represent the execution behaviors specified in smart contract bytecodes, which are derived from a literature review and in-depth interviews with domain experts. We then propose PonziLens+, a novel visual analytic approach that provides an intuitive …

Bridging The Great Wall: China’S Evolving Cross-Border Data Flow Policies And Implications For Global Data Governance, Sheng Zhang, Henry S. Gao

Research Collection Yong Pung How School Of Law

Despite the rapid expansion of the digital economy, the global regulatory framework for data flows remains fragmented, with countries adopting divergent approaches shaped by their own regulatory priorities. As a key player in the Internet economy, China’s approach to cross-border data flows (CBDF) not only defines its domestic digital landscape but also influences emerging global norms. This paper takes a comprehensive view of the evolution of China’s CBDF regime, examining its development through both domestic and international lenses. Domestically, China’s regulation of CBDF has evolved from a security-first approach to one that seeks to balance security with economic development. This …

Optimal Abort Policy For Mission-Critical Systems Under Imperfect Condition Monitoring, Qiuzhuang Sun, Jiawen Hu, Zhi-Sheng Ye

Research Collection College of Integrative Studies

Although most on-demand mission-critical systems are engineered to be reliable to support critical tasks, occasional failures may still occur during missions. To increase system survivability, a common practice is to abort the mission before an imminent failure. We consider optimal mission abort for a system whose deterioration follows a general three-state (normal, defective, failed) semi-Markov chain. The failure is assumed self-revealed, whereas the healthy and defective states have to be inferred from imperfect condition-monitoring data. Because of the non-Markovian process dynamics, optimal mission abort for this partially observable system is an intractable stopping problem. For a tractable solution, we introduce …

Deep Graph Anomaly Detection: A Survey And New Perspectives, Hezhe Qiao, Hanghang Tong, Nanyang Technological University, Irwin King, Charu Aggarwal, Guansong Pang

Research Collection School Of Computing and Information Systems

Graph anomaly detection (GAD), which aims to identify unusual graph instances (e.g., nodes, edges, subgraphs, or graphs), has attracted increasing attention in recent years due to its significance in a wide range of applications. Deep learning approaches, graph neural networks (GNNs) in particular, have been emerging as a promising paradigm for GAD, owing to its strong capability in capturing complex structure and/or node attributes in graph data. Considering the large number of methods proposed for GNN-based GAD, it is of paramount importance to summarize the methodologies and findings in the existing GAD studies, so that we can pinpoint effective model …

Storage Location Optimization In Automated Storage And Retrieval Systems: A Deep Reinforcement Learning Approach, Lingjun Wang, Aldy Gunawan, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

This study investigates the optimization of storage location in automated storage and retrieval systems (AS/RS). We introduce an optimization approach based on the Deep Q-Network (DQN) algorithm to enhance warehouse task efficiency and minimize stacker travel during storage and retrieval. To accelerate the algorithm training process, we integrate a prioritized experience replay mechanism. Furthermore, we decouple action selection from value estimation within the DQN framework to address the issue of value overestimation. The proposed model is evaluated against three heuristic methods. The experimental results demonstrate that our approach significantly outperforms these baselines.

Optimal Transport Alignment Of User Preferences From Ratings And Texts, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Modeling hidden factors driving user preferences is crucial for recommendation yet challenging due to sparse rating data. While aligning preference factors from ratings and texts, as a solution, shows improvements, existing methods impose restrictive one-to-one factor correspondences and underutilize cross-modal interest signals. We propose an optimal transport (OT) approach to address these gaps. By modeling rating- and text-based preference factors as distributions, we compute an OT plan that captures their probabilistic relationships. This plan serves dual roles: 1) to regularize cross-modal preference factors without rigid correspondence assumptions, and 2) to blend preference signals across modalities through barycentric mapping. Experiments on …

Causalabstain: Enhancing Multilingual Llms With Causal Reasoning For Trustworthy Abstention, Yuxi Sun, Aoqi Zuo, Wei Gao, Jing Ma

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to abstain when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current abstention strategies for multilingual scenarios primarily rely on generating feedback in various languages using LLMs and performing self-reflection. However, these methods can be adversely impacted by inaccuracies and biases in the generated feedback. To address this, from a causal perspective, we introduce CausalAbstain, a method that helps LLMs determine whether to utilize multiple generated feedback responses and how to identify the most useful ones. Extensive experiments demonstrate that CausalAbstain effectively …

Non-Homophilic Graph Pre-Training And Prompt Learning, Xingtong Yu, Jie Zhang, Yuan Fang, Renhe Jiang

Research Collection School Of Computing and Information Systems

Graphs are ubiquitous for modeling complex relationships between objects across various fields. Graph neural networks (GNNs) have become a mainstream technique for graph-based applications, but their performance heavily relies on abundant labeled data. To reduce labeling requirement, pre-training and prompt learning has become a popular alternative. However, most existing prompt methods do not distinguish between homophilic and heterophilic characteristics in graphs. In particular, many real-world graphs are non-homophilic-neither strictly nor uniformly homophilic-as they exhibit varying homophilic and heterophilic patterns across graphs and nodes. In this paper, we propose ProNoG, a novel pre-training and prompt learning framework for such non-homophilic graphs. …

The 6th International Workshop On Talent And Management Computing (Tmc 2025), Hengshu Zhu, Yong Ge, Hui Xiong, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

In today's competitive and fast-evolving business environment, it is a critical time for organizations to rethink how to deal with talent and management-related tasks in a quantitative manner. Indeed, thanks to the era of big data, the availability of large-scale talent data provides unparalleled opportunities for leaders to deliver intelligence for effective management for organizations. In the past few years, talent and management computing have increasingly attracted attention from KDD communities, and a number of research/applied data science efforts have been devoted. To this end, the purpose of this workshop, i.e., the 6th International Workshop on Talent and Management Computing …

Rl4co: An Extensive Reinforcement Learning For Combinatorial Optimization Benchmark, Federico Berto, Et. Al

Research Collection School Of Computing and Information Systems

Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant benefits in solving CO problems, reducing reliance on domain expertise and improving computational efficiency. However, the absence of a unified benchmarking framework leads to inconsistent evaluations, limits reproducibility, and increases engineering overhead, raising barriers to adoption for new researchers. To address these challenges, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 27 CO problem environments and 23 state-of-the-art baselines. Built on efficient software libraries and best practices in …

Learning Frame-Level Classifiers For Video-Based Real-Time Assessment Of Stroke Rehabilitation Exercises From Weakly Annotated Datasets, Ana Rita Cóias, Min Hun Lee, Alexandre Bernardino, Asim Smailagic, Mariana Mateus, David Fernandes, Sofia Trapola

Research Collection School Of Computing and Information Systems

Autonomous rehabilitation support solutions, such as virtual coaches, should provide real-time feedback to improve motor function and maintain patient engagement. However, fully annotated dataset collection for real-time exercise assessment is time-consuming and costly, posing a barrier to evaluating proposed methods. In this work, we present a novel framework that learns a frame-level classifier using weakly annotated videos for real-time assessment of compensatory motions in stroke rehabilitation exercises by generating pseudo-labels at a frame level. We consider three approaches: 1) a baseline approach that uses a source dataset to train a frame-level classifier, 2) a transfer learning approach that uses target …

Cami: A Counselor Agent Supporting Motivational Interviewing Through State Inference And Topic Exploration, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Phey Ling Kit, Nicholas Gabriel Lim, Cameron Shi Ern Tan, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Conversational counselor agents have become essential tools for addressing the rising demand for scalable and accessible mental health support. This paper introduces CAMI, a novel automated counselor agent grounded in Motivational Interviewing (MI) – a client-centered counseling approach designed to address ambivalence and facilitate behavior change. CAMI employs a novel STAR framework, consisting of client’s state inference, motivation topic exploration, and response generation modules, leveraging large language models (LLMs). These components work together to evoke change talk, aligning with MI principles and improving counseling outcomes for diverse clients. We evaluate CAMI’s performance through both automated and expert evaluations, utilizing simulated …

Towards Context-Aware Traffic Classification Via Time-Wavelet Fusion Network, Ziming Zhao, Zhuoxue Song, Xiaofei Xie, Zhaoxuan Li, Jiongchi Yu, Fan Terry Zhang, Tingting Li

Research Collection School Of Computing and Information Systems

Encrypted traffic classification occupies a significant role in cybersecurity and network management. The existing encrypted traffic classification technology mostly relies on intra-flow semantics for extracting features. However, considering that some attack behaviors inherently have similar patterns to legitimate behaviors, and powerful adversaries could simulate benign users to conceal their attack intentions, intra-flow features may be similar between different categories. In this paper, we propose TrafficScope, a time-wavelet fusion network based on Transformer to enhance the performance of encrypted traffic classification. Specifically, in addition to using intra-flow semantics, TrafficScope also extracts contextual information to construct more comprehensive representations. Moreover, to cope …

Gradients As An Action: Towards Communication-Efficient Federated Recommender Systems Via Adaptive Action Sharing, Zhufeng Lu, Chentao Jia, Ming Hu, Xiaofei Xie, Mingsong Chen

Research Collection School Of Computing and Information Systems

As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly suffer from two major problems: i) extremely high communication overhead due to massive item embeddings involved in recommendation systems, and ii) intolerably low training efficiency caused by the entanglement of both heterogeneous network environments and client devices. Although existing methods attempt to employ various compression techniques to reduce communication overhead, due to the parameter errors introduced by model compression, they inevitably suffer from model performance degradation. To simultaneously address the above problems, this …

Fine‑Tuning Multimodal Large Language Models For Product Bundling, Xiaohao Liu, Jie Wu, Zhulin Tao, Yunshan Ma, Yinwei Wei, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context Learning (ICL) to explore the potential of large language models (LLMs) for their extensive knowledge and complex reasoning abilities. However, these efforts are inadequate in understanding mulitmodal data and exploiting LLMs' knowledge for product bundling. To bridge the gap, we introduce Bundle-MLLM, a novel framework that fine-tunes LLMs through a hybrid item tokenization approach within a well-designed optimization strategy. Specifically, we integrate textual, media, and relational data into a unified …

Anomalygfm: Graph Foundation Model For Zero/Few-Shot Anomaly Detection, Hezhe Qiao, Chaoxi Niu, Ling Chen, Guansong Pang

Research Collection School Of Computing and Information Systems

Graph anomaly detection (GAD) aims to identify abnormal nodes that differ from the majority of the nodes in a graph, which has been attracting significant attention in recent years. Existing generalist graph models have achieved remarkable success in different graph tasks but struggle to generalize to the GAD task. This limitation arises from their difficulty in learning generalized knowledge for capturing the inherently infrequent, irregular and heterogeneous abnormality patterns in graphs from different domains. To address this challenge, we propose AnomalyGFM, a GAD-oriented graph foundation model that supports zero-shot inference and few-shot prompt tuning for GAD in diverse graph datasets. …

Affinitytune: A Prompt-Tuning Framework For Few-Shot Anomaly Detection On Graphs, Jingyan Chen, Guanghui Zhu, Guansong Pang, Chunfeng Yuan, Yihua Huang

Research Collection School Of Computing and Information Systems

Graph anomaly detection (GAD) is a critical task with applications in domains such as networking, finance, and bioinformatics. % However, the scarcity of labeled anomalies and the limitations of unsupervised methods hinder effective detection. % While semi-supervised and few-shot learning approaches offer improvements, they struggle with knowledge transfer and rely heavily on labeled data. % Recent advancements in prompt tuning on graphs provide a promising direction, but their application to heterophilous graphs in anomaly detection remains underexplored. % In this work, we propose AffinityTune, a novel framework for few-shot graph anomaly detection based on prompt tuning. % Our approach introduces …

Fashiondpo: Fine‑Tune Fashion Outfit Generation Model Using Direct Preference Optimization, Mingzhe Yu, Yunshan Ma, Lei Wu, Changshuo Wang, Xue Li, Lei Meng

Research Collection School Of Computing and Information Systems

Personalized outfit generation aims to construct a set of compatible and personalized fashion items as an outfit. Recently, generative AI models have received widespread attention, as they can generate fashion items for users to complete an incomplete outfit or create a complete outfit. However, they have limitations in terms of lacking diversity and relying on the supervised learning paradigm. Recognizing this gap, we propose a novel framework FashionDPO, which fine-tunes the fashion outfit generation model using direct preference optimization. This framework aims to provide a general fine-tuning approach to fashion generative models, refining a pre-trained fashion outfit generation model using …

Finir: The 2nd Workshop On Financial Information Retrieval In The Era Of Generative Ai, Fengbin Zhu, Yunshan Ma, Fuli Feng, Chao Wang, Huanbo Luan, Guangnan Ye, Shuo Zhang, Dhagash Mehta, Pingping Chen, Bing Xiang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Recent advancements in Generative AI, such as Large Language Models (LLMs), have demonstrated remarkable success across various general tasks. Extensive studies have explored leveraging generative models in finance, but significant challenges persist. This half-day workshop explores potential approaches and research directions to address these challenges by equipping generative models with advanced Information Retrieval (IR) models. Specifically, this workshop seeks to provide a platform for discussing innovative ideas that facilitate the advancement of IR technology to enrich generative models in finance from four key perspectives: (i) financial IR techniques (ii) financial IR benchmarking and evaluation (iii) financial systems and agents/assistants (iv) …

Wa-Fdnet: A Unified Weight Adaptation Network For Multimodal Image Fusion And Object Detection, Yanyin Guo, Ying Luo, Junwei Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

Multimodal image fusion and object detection are critical tasks in computer vision, particularly in scenarios requiring robust perception under low illumination conditions. Existing approaches that attempt to combine these tasks often rely on cascaded or loosely coupled designs, which can result in suboptimal performance due to gradient conflicts and task imbalance. In this paper, we propose WA-FDNet, a novel Weight Adaptation Fusion Detection Network that unifies multimodal image fusion and object detection into a single end-to-end framework. WA-FDNet adopts a shared encoder–private decoder architecture, enabling efficient feature sharing while preserving task-specific characteristics. The image fusion branch employs a spatial attention-based …

The B2biers System: A Content-Based Perspective On Maximizing Influence And Subscription In Social Networks, Konstantinos Theocharidis, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

The popular problem of Influence Maximization (IM) asks for the k users who can maximize the influence of a fixed post in a social network. In contrast, the problem of Content- Aware Influence Maximization (CAIM) asks for the k features to form a viral tunable post in a social network starting its diffusion from a fixed set of initial adopters. CAIM paves the way for a number of novel problems to be studied that altogether can lead to the development of a system that would be valuable for advertisers who manage social network pages. This holds since features (brands) in …

Dual-Target Disjointed Cross-Domain Recommendation Mediated Via Latent User Preferences, Dinh Hieu Do, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Users often navigate multiple platforms online, each characterized by its own set of scarce data. Recommender systems face a significant challenge in such fragmented environments. This paper proposes a novel approach to enhance recommendation systems by leveraging connections across distinct yet conceptually similar datasets from multiple platforms. We introduce a unique scenario of dual-target overlapping-free cross-platform recommendation, presenting a bridging mechanism to mutually improve across platforms and learn latent user preferences. Our approach addresses the data sparsity prevalent in each platform and enhances recommendation quality by harnessing redundant, rich, and similar domain data. Experiments validate the effectiveness of our method, …

An Efficient Diffusion-Based Non-Autoregressive Solver For Traveling Salesman Problem, Mingzhao Wang, You Zhou, Zhiguang Cao, Yubin Xiao, Xuan Wu, Wei Pang, Yuan Jiang, Hui Yang, Peng Zhao, Yuanshu Li

Research Collection School Of Computing and Information Systems

Recent advances in neural models have shown considerable promise in solving Traveling Salesman Problems (TSPs) without relying on much hand-crafted engineering. However, while non-autoregressive (NAR) approaches benefit from faster inference through parallelism, they typically deliver solutions of inferior quality compared to autoregressive ones. To enhance the solution quality while maintaining fast inference, we propose DEITSP, a diffusion model with efficient iterations tailored for TSP that operates in a NAR manner. Firstly, we introduce a one-step diffusion model that integrates the controlled discrete noise addition process with self-consistency enhancement, enabling optimal solution prediction through simultaneous denoising of multiple solutions. Secondly, we …

Sparse-To-Dense: A Free Lunch For Lossless Acceleration Of Video Understanding In Llms, Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang, Wei Gao, Qian Liu

Research Collection School Of Computing and Information Systems

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually very long. We observe that during decoding, the attention scores of most tokens in Video-LLMs tend to be sparse and concentrated, with only certain tokens requiring comprehensive full attention. Based on this insight, we introduce Sparse-to-Dense (StD), a novel decoding strategy that integrates two distinct modules: one leveraging sparse top-K attention and the other employing dense full attention. These modules collaborate to accelerate Video-LLMs without loss. …

Adapting Large Language Models For Parameter-Efficient Log Anomaly Detection, Ying Fu Lim, Jiawen Zhu, Guansong Pang

Research Collection School Of Computing and Information Systems

Log Anomaly Detection (LAD) seeks to identify atypical patterns in log data that are crucial to assessing the security and condition of systems. Although Large Language Models (LLMs) have shown tremendous success in various fields, the use of LLMs in enabling the detection of log anomalies is largely unexplored. This work aims to fill this gap. Due to the prohibitive costs involved in fully fine-tuning LLMs,we explore the use of parameter-efficient fine-tuning techniques (PEFTs) for adapting LLMs to LAD.To have an in-depth exploration of the potential of LLM-driven LAD, we present a comprehensive investigation of leveraging two of the most …

Alayadb: The Data Foundation For Efficient And Effective Long-Context Llm Inference, Yangshen Deng, Zhengxin You, Long Xiang, Qilong Li, Peiqi Yuan, Zhaoyang Hong, Yitao Zheng, Wanting Li, Runzhong Li, Haotian Liu, Kyriakos Mouratidis, Man Lung Yiu, Huan Li, Qiaomu Shen, Rui Mao, Bo Tang

Research Collection School Of Computing and Information Systems

AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specifically, it decouples the KV cache and attention computation from the LLM inference systems, and encapsulates them into a novel vector database system. For the Model as a Service providers (MaaS), AlayaDB consumes fewer hardware resources and offers higher generation quality for various workloads with different kinds of Service Level Objectives (SLOs), when compared with the existing alternative solutions (e.g., KV cache disaggregation, retrieval-based sparse attention). The crux of AlayaDB is that it abstracts the attention computation …

Rich Models And Methods For On-Demand Same Day Deliveries, Zhiqin Zhang

Dissertations and Theses Collection (Open Access)

Same-day delivery has brought numerous conveniences to people’s lives, but it has also presented challenges in terms of service management. To effectively optimize on-demand same-day delivery operations within urban logistics, intelligent decision-making strategies capable of adapting to rapidly changing circumstances are essential. Employing effective decisionmaking strategies that account for order allocation, route planning, courier scheduling, and other relevant factors, is pivotal in advancing logistics operations, enhancing efficiency, customer satisfaction, and resource utilization in the context of dynamic same-day delivery problems.

The focus of this thesis revolves around different emerging challenges presented by on-demand same-day delivery problems, with a particular emphasis …

Lessons Learned From Sandboxing, Piloting And Policy Experimentation With Ai And Other Digital Initiatives: Part 1, Summary Report, Steven M. Miller

Research Collection School Of Computing and Information Systems

This report, "Lessons Learned from Sandboxing, Piloting and Policy Experimentation with AI and Other Digital Initiatives," captures insights and experiences from project experts involved in recent digital innovation initiatives with the governments of Bangladesh, Maldives, and Kazakhstan, and from project experts actively involved with the use of AI for delivering government digital services in the EU, New Zealand, Rwanda, Singapore, United States, and Uzbekistan. The ten in-depth interview write-ups produced from these nine different country settings provide a small but highly informative sample of rich descriptions of some of the important realities, approaches, nuances, issues and challenges related to testing …

Hd-Epic: A Highly-Detailed Egocentric Video Dataset, Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha, Omar Emara, Sam Pollard, Kranti Kumar Parida, Kaiting Liu, Prajwal Gatti, Siddhant Bansal, Kevin Flanagan, Jacob Chalk, Zhifan Zhu, Rhodri Guerrier, Fahd Abdelazim, Bin Zhu, Davide Moltisanti, Michael Wray, Hazel Doughty, Dima Damen

Research Collection School Of Computing and Information Systems

We present a validation dataset of newly-collected kitchenbased egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those in controlled lab environments. We show the potential of our highly-detailed annotations through a challenging VQA benchmark of 26K questions assessing the capability to …