Physical Sciences and Mathematics Commons^™

Cosm2ic: Optimizing Real-Time Multi-Modal Instruction Comprehension, Weerakoon Mudiyanselage Dulanga Kaveesha Weerakoon, Vigneshwaran Subbaraju, Minh Anh Tuan Tran, Archan Misra

Research Collection School Of Computing and Information Systems

Supporting real-time, on-device execution of multi-modal referring instruction comprehension models is an important challenge to be tackled in embodied Human-Robot Interaction. However, state-of-the-art deep learning models are resource-intensive and unsuitable for real-time execution on embedded devices. While model compression can achieve a reduction in computational resources up to a certain point, further optimizations result in a severe drop in accuracy. To minimize this loss in accuracy, we propose the COSM2IC framework, with a lightweight Task Complexity Predictor, that uses multiple sensor inputs to assess the instructional complexity and thereby dynamically switch between a set of models of varying computational intensity …

Techniques To Enhance A Qubo Solver For Permutation-Based Combinatorial Optimization, Siong Thye Goh, Jianyuan Bo, Sabrish Gopalakrishnan, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Many combinatorial optimization problems can be formulated as a problem to determine the order of sequence or to find a corresponding mapping of the objects. We call such problems permutation-based optimization problems. Many such problems can be formulated as a quadratic unconstrained binary optimization (QUBO) or Ising model by introducing a penalty coefficient to the permutation constraint terms. While classical and quantum annealing approaches have been proposed to solve QUBOs to date, they face issues with optimality and feasibility. Here we treat a given QUBO solver as a black box and propose techniques to enhance its performance. First, to ensure …

A3gan: Attribute-Aware Anonymization Networks For Face De-Identification, Liming Zhai, Qing Guo, Xiaofei Xie, Lei Ma, Yi Estelle Wang, Yang Liu

Research Collection School Of Computing and Information Systems

Face de-identification (De-ID) removes face identity information in face images to avoid personal privacy leakage. Existing face De-ID breaks the raw identity by cutting out the face regions and recovering the corrupted regions via deep generators, which inevitably affect the generation quality and cannot control generation results according to subsequent intelligent tasks (e.g., facial expression recognition). In this work, for the first attempt, we think the face De-ID from the perspective of attribute editing and propose an attribute-aware anonymization network (A3GAN) by formulating face De-ID as a joint task of semantic suppression and controllable attribute injection. Intuitively, the semantic suppression …

Towards Aligning Slides And Video Snippets: Mitigating Sequence And Content Mismatches, Ziyuan Liu, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Slides are important form of teaching materials used in various courses at academic institutions. Due to their compactness, slides on their own may not stand as complete reference materials. To aid students’ understanding, it would be useful to supplement slides with other materials such as online videos. Given a deck of slides and a related video, we seek to align each slide in the deck to a relevant video snippet, if any. While this problem could be formulated as aligning two time series (each involving a sequence of text contents), we anticipate challenges in generating matches arising from differences in …

A Weakly Supervised Propagation Model For Rumor Verification And Stance Detection With Multiple Instance Learning, Ruichao Yang, Jing Ma, Hongzhan Lin, Wei Gao

Research Collection School Of Computing and Information Systems

The diffusion of rumors on social media generally follows a propagation tree structure, which provides valuable clues on how an original message is transmitted and responded by users over time. Recent studies reveal that rumor verification and stance detection are two relevant tasks that can jointly enhance each other despite their differences. For example, rumors can be debunked by cross-checking the stances conveyed by their relevant posts, and stances are also conditioned on the nature of the rumor. However, stance detection typically requires a large training set of labeled stances at post level, which are rare and costly to annotate. …

Enhancing A Qubo Solver Via Data Driven Multi-Start And Its Application To Vehicle Routing Problem, Whei Yeap Suen, Matthieu Parizy, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Quadratic unconstrained binary optimization (QUBO) models have garnered growing interests as a strong alternative modelling framework for solving combinatorial optimization problems. A wide variety of optimization problems that are usually studied using conventional Operations Research approaches can be formulated as QUBO problems. However, QUBO solvers do not guarantee optimality when solving optimization problems. Instead, obtaining high quality solutions using QUBO solvers entails tuning of multiple parameters. Here in our work, we conjecture that the initial states adjustment method used in QUBO solvers can be improved, where careful tuning will yield overall better results. We propose a data-driven multi-start algorithm that …

Test Mimicry To Assess The Exploitability Of Library Vulnerabilities, Hong Jin Kang, Truong Giang Nguyen, Bach Le, Corina S. Pasareanu, David Lo

Research Collection School Of Computing and Information Systems

Modern software engineering projects often depend on open-source software libraries, rendering them vulnerable to potential security issues in these libraries. Developers of client projects have to stay alert of security threats in the software dependencies. While there are existing tools that allow developers to assess if a library vulnerability is reachable from a project, they face limitations. Call graphonly approaches may produce false alarms as the client project may not use the vulnerable code in a way that triggers the vulnerability, while test generation-based approaches faces difficulties in overcoming the intrinsic complexity of exploiting a vulnerability, where extensive domain knowledge …

Using Constraint Programming And Graph Representation Learning For Generating Interpretable Cloud Security Policies, Mikhail Kazdagli, Mohit Tiwari, Akshat Kumar

Research Collection School Of Computing and Information Systems

Modern software systems rely on mining insights from business sensitive data stored in public clouds. A data breach usually incurs signifcant (monetary) loss for a commercial organization. Conceptually, cloud security heavily relies on Identity Access Management (IAM) policies that IT admins need to properly confgure and periodically update. Security negligence and human errors often lead to misconfguring IAM policies which may open a backdoor for attackers. To address these challenges, frst, we develop a novel framework that encodes generating optimal IAM policies using constraint programming (CP). We identify reducing dormant permissions of cloud users as an optimality criterion, which intuitively …

A Recommendation System Approach To Tune A Qubo Solver, Siong Thye Goh, Jianyuan Bo, Matthieu Parizy, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

There are two major challenges to solving constrained optimization problems using a QuadraticUnconstrained Binary Optimization or QUBO solver (QS). First, we need to tune both the underlyingproblem parameters and the algorithm parameters. Second, the solution returned from a QSmight not be feasible. While it is common to use automated tuners such as SMAC and Hyperopt totune the algorithm parameters, the initial search ranges input for the auto tuner affect the performanceof the QS. In this paper, we propose a framework that resembles the Algorithm Selection(AS) framework to tune algorithm parameters for an annealing-based QS. To cope with constraints,we focus on …

Uncovering Inclusivity Gaps In Design Pedagogy Through The Digital Design Marginalization Framework, Jaisie Sin, Cosmin Munteanu, Michael Nixon, Velian Pandeliev, Garreth W. Tigwell, Kristen Shinohara, Anthony Tang, Steve Szigeti

Research Collection School Of Computing and Information Systems

Designers play a key role in the design of inclusive and socially conscious interfaces. Thus, it is imperative for designers to be thoughtful of the ethical and social implications of design. However, gaps in the foundational training that designers receive (e.g., as university students) can negatively impact their ability to consider the social implications of their design practice. This can result in consequences such as digital marginalization, which, as defined by the Digital Design Marginalization (DDM) framework, is the “pushing away”, whether intentional or not, of a defined group of users from a digital or online service or system, where …

Multi-Objective Evolutionary Algorithm Based On Rbf Network For Solving The Stochastic Vehicle Routing Problem, Yunyun Niu, Jie Shao, Jianhua Xiao, Wen Song, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Solving the multi-objective vehicle routing problem with stochastic demand (MO-VRPSD) is challenging due to its non-deterministic property and conflicting objectives. Most multi -objective evolutionary algorithm dealing with this problem update current population without any guidance from previous searching experience. In this paper, a multi -objective evolutionary algorithm based on artificial neural networks is proposed to tackle the MO-VRPSD. Particularly, during the evolutionary process, a radial basis function net-work (RBFN) is exploited to learn the potential knowledge of individuals, generate hypoth-esis and instantiate hypothesis. The RBFN evaluates individuals with different scores and generates new individuals with higher quality while taking into …

A Mean-Field Markov Decision Process Model For Spatial Temporal Subsidies In Ride-Sourcing Markets, Zheng Zhu, Jintao Ke, Hai Wang

Research Collection School Of Computing and Information Systems

Ride-sourcing services are increasingly popular because of their ability to accommodate on-demand travel needs. A critical issue faced by ride-sourcing platforms is the supply-demand imbalance, as a result of which drivers may spend substantial time on idle cruising and picking up remote passengers. Some platforms attempt to mitigate the imbalance by providing relocation guidance for idle drivers who may have their own self-relocation strategies and decline to follow the suggestions. Platforms then seek to induce drivers to system-desirable locations by offering them subsidies. This paper proposes a mean-field Markov decision process (MF-MDP) model to depict the dynamics in ride-sourcing markets …

Self-Guided Learning To Denoise For Robust Recommendation, Yunjun Gao, Yuntao Du, Yujia Hu, Lu Chen, Xinjun Zhu, Ziquan Fang, Baihua Zheng

Research Collection School Of Computing and Information Systems

The ubiquity of implicit feedback makes them the default choice to build modern recommender systems. Generally speaking, observed interactions are considered as positive samples, while unobserved interactions are considered as negative ones. However, implicit feedback is inherently noisy because of the ubiquitous presence of noisy-positive and noisy-negative interactions. Recently, some studies have noticed the importance of denoising implicit feedback for recommendations, and enhanced the robustness of recommendation models to some extent. Nonetheless, they typically fail to (1) capture the hard yet clean interactions for learning comprehensive user preference, and (2) provide a universal denoising solution that can be applied to …

Proceedings Of The 13th International Workshop On Graph Computation Models (Gcm 2022), Reiko Heckel, Christopher M. Poskitt

Research Collection School Of Computing and Information Systems

This volume contains the proceedings of the Thirteenth International Workshop on Graph Computation Models (GCM 2022) , which was held in Nantes, France on 6th July 2022 as part of the STAF federation of conferences. Graphs are common mathematical structures that are visual and intuitive. They constitute a natural and seamless way for system modelling in science, engineering, and beyond, including computer science, biology, and business process modelling. Graph computation models constitute a class of very high-level models where graphs are first-class citizens. The aim of the International GCM Workshop series is to bring together researchers interested in all aspects …

Cross-Lingual Transfer Learning For Statistical Type Inference, Zhiming Li, Xiaofei Xie, Haoliang Li, Zhengzi Xu, Yi Li, Yang Liu

Research Collection School Of Computing and Information Systems

Hitherto statistical type inference systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label large amounts of data. Most Turing-complete imperative languages share similar control- and data-flow structures, which make it possible to transfer knowledge learned from one language to another. In this paper, we propose a cross-lingual transfer learning framework, Plato, for statistical type inference, which allows us to leverage prior knowledge learned from the labeled dataset of one language and transfer it to the others, e.g., Python to JavaScript, Java to JavaScript, etc. Plato is powered by a novel kernelized attention mechanism …

An Empirical Study On Data Distribution-Aware Test Selection For Deep Learning Enhancement, Qiang Hu, Yuejun Guo, Maxime Cordy, Xiaofei Xie, Lei Ma, Mike Papadakis, Yves Le Traon

Research Collection School Of Computing and Information Systems

Similar to traditional software that is constantly under evolution, deep neural networks need to evolve upon the rapid growth of test data for continuous enhancement (e.g., adapting to distribution shift in a new environment for deployment). However, it is labor intensive to manually label all of the collected test data. Test selection solves this problem by strategically choosing a small set to label. Via retraining with the selected set, deep neural networks will achieve competitive accuracy. Unfortunately, existing selection metrics involve three main limitations: (1) using different retraining processes, (2) ignoring data distribution shifts, and (3) being insufficiently evaluated. To …

Enabling Ai And Robotic Coaches For Physical Rehabilitation Therapy: Iterative Design And Evaluation With Therapists And Post-Stroke Survivors, Min Hun Lee, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez I Badia

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) and robotic coaches promise the improved engagement of patients on rehabilitation exercises through social interaction. While previous work explored the potential of automatically monitoring exercises for AI and robotic coaches, the deployment of these systems remains a challenge. Previous work described the lack of involving stakeholders to design such functionalities as one of the major causes. In this paper, we present our efforts on eliciting the detailed design specifications on how AI and robotic coaches could interact with and guide patient’s exercises in an effective and acceptable way with four therapists and five post-stroke survivors. Through iterative …

Docee: A Large-Scale And Fine-Grained Benchmark For Document-Level Event Extraction, Meihan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

Research Collection School Of Computing and Information Systems

Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentencelevel event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major barrier to promote documentlevel event extraction has been the lack of large-scale and practical training and evaluation datasets. In this paper, we present DocEE, a new document-level event extraction dataset including 27,000+ events, 180,000+ arguments. We highlight three features: largescale manual annotations, fine-grained argument types and application-oriented settings. Experiments show that there is still a big …

End-To-End Open-Set Semi-Supervised Node Classification With Out-Of-Distribution Detection, Tiancheng Huang, Donglin Wang, Yuan Fang

Research Collection School Of Computing and Information Systems

Out-Of-Distribution (OOD) samples are prevalent in real-world applications. The OOD issue becomes even more severe on graph data, as the effect of OOD nodes can be potentially amplified by propagation through the graph topology. Recent works have considered the OOD detection problem, which is critical for reducing the uncertainty in learning and improving the robustness. However, no prior work considers simultaneously OOD detection and node classification on graphs in an end-to-end manner. In this paper, we study a novel problem of end-to-end open-set semisupervised node classification (OSSNC) on graphs, which deals with node classification in the presence of OOD nodes. …

Finding Top-M Leading Records In Temporal Data, Yiyi Wang

Dissertations and Theses Collection (Open Access)

A traditional top-k query retrieves the records that stand out at a certain point in time. On the other hand, a durable top-k query considers how long the records retain their supremacy, i.e., it reports those records that are consistently among the top-k in a given time interval. In this thesis, we introduce a new query to the family of durable top-k formulations. It finds the top-m leading records, i.e., those that rank among the top-k for the longest duration within the query interval. Practically, this query assesses the records based on how long …

Towards Improving System Performance In Large Scale Multi-Agent Systems With Selfish Agents, Rajiv Ranjan Kumar

Dissertations and Theses Collection (Open Access)

Intelligent agents are becoming increasingly prevalent in a wide variety of domains including but not limited to transportation, safety and security. To better utilize the intelligence, there has been increasing focus on frameworks and methods for coordinating these intelligent agents. This thesis is specifically targeted at providing solution approaches for improving large scale multi-agent systems with selfish intelligent agents. In such systems, the performance of an agent depends on not just his/her own efforts, but also on other agent’s decisions. The complexity of interactions among multiple agents, coupled with the large scale nature of the problem domains and the uncertainties …

Deepcause: Verifying Neural Networks With Abstraction Refinement, Nguyen Hua Gia Phuc

Dissertations and Theses Collection (Open Access)

Neural networks have been becoming essential parts in many safety-critical systems (such
as self-driving cars and medical diagnosis). Due to that, it is desirable that neural networks
not only have high accuracy (which traditionally can be validated using a test set) but also
satisfy some safety properties (such as robustness, fairness, or free of backdoor). To verify
neural networks against desired safety properties, there are many approaches developed
based on classical abstract interpretation. However, like in program verification, these
approaches suffer from false alarms, which may hinder the deployment of the networks.

One natural remedy to tackle the problem adopted …

Communicative Strategies For Building Public Confidence In Data Governance: Analyzing Singapore's Covid-19 Contact-Tracing Initiatives, Gordon Kuo Siong Tan, Sun Sun Lim

Research Collection College of Integrative Studies

Effective social data governance rests on a bedrock of social support. Without securing trust from the populace whose information is being collected, analyzed, and deployed, policies on which such data are based will be undermined by a lack of public confidence. The COVID-19 pandemic has accelerated digitalization and datafication by governments for the purposes of contact tracing and epidemiological investigation. However, concerns about surveillance and data privacy have stunted the adoption of such contact-tracing initiatives. This commentary analyzes Singapore's contact-tracing initiative to uncover the reasons for public resistance and efforts by the state to address them. The government's contact-tracing program …

Deep One-Class Classification Via Interpolated Gaussian Descriptor, Yuanhong Chen, Yu Tian, Guansong Pang, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

One-class classification (OCC) aims to learn an effective data description to enclose all normal training samples and detect anomalies based on the deviation from the data description. Current state-of-the-art OCC models learn a compact normality description by hyper-sphere minimisation, but they often suffer from overfitting the training data, especially when the training set is small or contaminated with anomalous samples. To address this issue, we introduce the interpolated Gaussian descriptor (IGD) method, a novel OCC model that learns a one-class Gaussian anomaly classifier trained with adversarially interpolated training samples. The Gaussian anomaly classifier differentiates the training samples based on their …

Desire: An Efficient Dynamic Cluster-Based Forest Indexing For Similarity Search In Multi-Metric Spaces, Yifan Zhu, Lu Chen, Yunjun Gao, Baihua Zheng, Pengfei Wang

Research Collection School Of Computing and Information Systems

Similarity search fnds similar objects for a given query object based on a certain similarity metric. Similarity search in metric spaces has attracted increasing attention, as the metric space can accommodate any type of data and support fexible distance metrics. However, a metric space only models a single data type with a specifc similarity metric. In contrast, a multi-metric space combines multiple metric spaces to simultaneously model a variety of data types and a collection of associated similarity metrics. Thus, a multi-metric space is capable of performing similarity search over any combination of metric spaces. Many studies focus on indexing …

Faithful Extreme Rescaling Via Generative Prior Reciprocated Invertible Representations, Zhixuan Zhong, Liangyu Chai, Yang Zhou, Bailin Deng, Jia Pan, Shengfeng He

Research Collection School Of Computing and Information Systems

This paper presents a Generative prior ReciprocAted Invertible rescaling Network (GRAIN) for generating faithful high-resolution (HR) images from low-resolution (LR) invertible images with an extreme upscaling factor (64×). Previous researches have leveraged the prior knowledge of a pretrained GAN model to generate high-quality upscaling results. However, they fail to produce pixel-accurate results due to the highly ambiguous extreme mapping process. We remedy this problem by introducing a reciprocated invertible image rescaling process, in which high-resolution information can be delicately embedded into an invertible low-resolution image and generative prior for a faithful HR reconstruction. In particular, the invertible LR features not …

Cross-Lingual Adaptation For Recipe Retrieval With Mixup, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Wing-Kwong Chan

Research Collection School Of Computing and Information Systems

Cross-modal recipe retrieval has attracted research attention in recent years, thanks to the availability of large-scale paired data for training. Nevertheless, obtaining adequate recipe-image pairs covering the majority of cuisines for supervised learning is difficult if not impossible. By transferring knowledge learnt from a data-rich cuisine to a data-scarce cuisine, domain adaptation sheds light on this practical problem. Nevertheless, existing works assume recipes in source and target domains are mostly originated from the same cuisine and written in the same language. This paper studies unsupervised domain adaptation for image-to-recipe retrieval, where recipes in source and target domains are in different …

Reinforcement Learning-Based Interactive Video Search, Zhixin Ma, Jiaxin Wu, Zhijian Hou, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Despite the rapid progress in text-to-video search due to the advancement of cross-modal representation learning, the existing techniques still fall short in helping users to rapidly identify the search targets. Particularly, in the situation that a system suggests a long list of similar candidates, the user needs to painstakingly inspect every search result. The experience is frustrated with repeated watching of similar clips, and more frustratingly, the search targets may be overlooked due to mental tiredness. This paper explores reinforcement learning-based (RL) searching to relieve the user from the burden of brute force inspection. Specifically, the system maintains a graph …

Group Contextualization For Video Recognition, Yanbin Hao, Hao Zhang, Chong-Wah Ngo, Xiangnan He

Research Collection School Of Computing and Information Systems

Learning discriminative representation from the complex spatio-temporal dynamic space is essential for video recognition. On top of those stylized spatio-temporal computational units, further refining the learnt feature with axial contexts is demonstrated to be promising in achieving this goal. However, previous works generally focus on utilizing a single kind of contexts to calibrate entire feature channels and could hardly apply to deal with diverse video activities. The problem can be tackled by using pair-wise spatio-temporal attentions to recompute feature response with cross-axis contexts at the expense of heavy computations. In this paper, we propose an efficient feature refinement method that …

Reinforcement Learning Approach To Solve Dynamic Bi-Objective Police Patrol Dispatching And Rescheduling Problem, Waldy Joe, Hoong Chuin Lau, Jonathan Pan

Research Collection School Of Computing and Information Systems

Police patrol aims to fulfill two main objectives namely to project presence and to respond to incidents in a timely manner. Incidents happen dynamically and can disrupt the initially-planned patrol schedules. The key decisions to be made will be which patrol agent to be dispatched to respond to an incident and subsequently how to adapt the patrol schedules in response to such dynamically-occurring incidents whilst still fulfilling both objectives; which sometimes can be conflicting. In this paper, we define this real-world problem as a Dynamic Bi-Objective Police Patrol Dispatching and Rescheduling Problem and propose a solution approach that combines Deep …