Computer Sciences Commons^™

Co-Embedding Attributed Networks With External Knowledge, Pei-Chi Lo, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Attributed network embedding aims to learn representations of nodes and their attributes in a low-dimensional space that preserves their semantics. The existing embedding models, however, consider node connectivity and node attributes only while ignoring external knowledge that can enhance node representations for downstream applications. In this paper, we propose a set of new VAE-based embedding models called External Knowledge-Aware Co-Embedding Attributed Network (ECAN) Embeddings to incorporate associations among attributes from relevant external knowledge. Such external knowledge can be extracted from text corpus and knowledge graphs. We use multi-VAE structures to model the attribute associations. To cope with joint encoding of …

Robust, Fine-Grained Occupancy Estimation Via Combined Camera & Wifi Indoor Localization, Anuradha Ravi, Archan Misra

Research Collection School Of Computing and Information Systems

We describe the development of a robust, accurate and practically-validated technique for estimating the occupancy count in indoor spaces, based on a combination of WiFi & video sensing. While fusing these two sensing-based inputs is conceptually straightforward, the paper demonstrates and tackles the complexity that arises from several practical artefacts, such as (i) over-counting when a single individual uses multiple WiFi devices and under-counting when the individual has no such device; (ii) corresponding errors in image analysis due to real-world artefacts, such as occlusion, and (iii) the variable errors in mapping image bounding boxes (which can include multiple possible types …

Jointly Optimizing Sensing Pipelines For Multimodal Mixed Reality Interaction, Darshana Rathnayake, Ashen De Silva, Dasun Puwakdandawa, Lakmal Meegahapola, Archan Misra, Indika Perera

Research Collection School Of Computing and Information Systems

Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate comprehension of such multimodal instructions (MMI), on resource-constrained wearable devices, remains an open challenge, especially as the state-of-the-art comprehension techniques for each individual modality increasingly utilize complex Deep Neural Network models. We demonstrate the possibility of overcoming the core limitation of latency--vs.--accuracy tradeoff by exploiting cross-modal dependencies -- i.e., by compensating for the inferior performance of one model with an increased accuracy of more complex model of a different modality. We …

Prediction Of Nocturia In Live Alone Elderly Using Unobtrusive In-Home Sensors, Barry Nuqoba, Hwee-Pink Tan

Research Collection School Of Computing and Information Systems

Nocturia, or the need to void (or urinate) one or more times in the middle of night time sleeping, represents a significant economic burden for individuals and healthcare systems. Although it can be diagnosed in the hospital, most people tend to regard nocturia as a usual event, resulting in underreported diagnosis and treatment. Data from self-reporting via a voiding diary may be irregular and subjective especially among the elderly due to memory problems. This study aims to detect the presence of nocturia through passive in-home monitoring to inform intervention (e.g., seeking diagnosis and treatment) to improve the physical and mental …

Secure And Verifiable Inference In Deep Neural Networks, Guowen Xu, Hongwei Li, Hao Ren, Jianfei Sun, Shengmin Xu, Jianting Ning, Haoming Yang, Kan Yang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Outsourced inference service has enormously promoted the popularity of deep learning, and helped users to customize a range of personalized applications. However, it also entails a variety of security and privacy issues brought by untrusted service providers. Particularly, a malicious adversary may violate user privacy during the inference process, or worse, return incorrect results to the client through compromising the integrity of the outsourced model. To address these problems, we propose SecureDL to protect the model’s integrity and user’s privacy in Deep Neural Networks (DNNs) inference process. In SecureDL, we first transform complicated non-linear activation functions of DNNs to low-degree …

Analysis Of Online Posts To Discover Student Learning Challenges And Inform Targeted Curriculum Improvement Actions, Michelle L. F. Cheong, Jean Y. C. Chen, Bingtian Dai

Research Collection School Of Computing and Information Systems

Past research on analysing end-of-term student feedback tend to result in only high-level course improvement suggestions, and some recent research even argued that student feedback is a poor indicator of teaching effectiveness and student learning. Our intelligent Q&A platform with machine learning prediction and engagement features allow students to ask self-directed questions and provide answers in an out-of-class informal setting. By analysing such high quality and truthful posts which represent the students’ queries and knowledge about the course content, we can better identify the exact course topics which the students face learning challenges. We have implemented our Q&A platform for …

Identifying And Characterizing Alternative News Media On Facebook, Samuel S. Guimaraes, Julia C. S. Reis, Lucas Lima, Filipe N. Ribeiro, Marisa Vasconcelos, Jisun An, Haewoon Kwak, Fabricio Benevenuto

Research Collection School Of Computing and Information Systems

As Internet users increasingly rely on social media sites to receive news, they are faced with a bewildering number of news media choices. For example, thousands of Facebook pages today are registered and categorized as some form of news media outlets. This situation boosted the so-called independent journalism, also known as alternative news media. Identifying and characterizing all the news pages that play an important role in news dissemination is key for understanding the news ecosystems of a country. In this work, we propose a graph-based semi-supervised method to measure the political bias of pages on most countries and show …

A Deep Learning Framework Supporting Model Ownership Protection And Traitor Tracing, Guowen Xu, Hongwei Li, Yuan Zhang, Xiaodong Lin, Robert H. Deng, Xuemin (Sherman) Shen

Research Collection School Of Computing and Information Systems

Cloud-based deep learning (DL) solutions have been widely used in applications ranging from image recognition to speech recognition. Meanwhile, as commercial software and services, such solutions have raised the need for intellectual property rights protection of the underlying DL models. Watermarking is the mainstream of existing solutions to address this concern, by primarily embedding pre-defined secrets in a model's training process. However, existing efforts almost exclusively focus on detecting whether a target model is pirated, without considering traitor tracing. In this paper, we present SecureMark_DL, which enables a model owner to embed a unique fingerprint for every customer within parameters …

Artificial Intelligence For Social Impact: Learning And Planning In The Data-To-Deployment Pipeline, Andrew Perrault, Fei Fang, Arunesh Sinha, Milind Tambe

Research Collection School Of Computing and Information Systems

With the maturing of artificial intelligence (AI) and multiagent systems research, we have a tremendous opportunity to direct these advances toward addressing complex societal problems. In pursuit of this goal of AI for social impact, we as AI researchers must go beyond improvements in computational methodology; it is important to step out in the field to demonstrate social impact. To this end, we focus on the problems of public safety and security, wildlife conservation, and public health in low-resource communities, and present research advances in multiagent systems to address one key cross-cutting challenge: how to effectively deploy our limited intervention …

The Spatial And Temporal Impact Of Agricultural Crop Residual Burning On Local Land Surface Temperature In Three Provinces Across China From 2015 To 2017, Wenting Zhang, Mengmeng Yu, Qingqing He, Tianwei Wang, Lu Lin, Kai Cao, Wei Huang, Peihong Fu, Jiaxin Chen

Research Collection School Of Computing and Information Systems

China has suffered from severe crop residue burning (CRB) for a long time. As a type of biomass burning, CRB leads to a huge alteration in climate due to the emission of greenhouse gases and particulates in the atmosphere and damages to surface characteristics on land. At present, a growing body of research focuses on the impact of biomass burning (BB) (e.g., forest fire, grass fire, and CRB) on climate change from the aspect of atmospheric process. Meanwhile, a small number of research studies have started to pay attention on the damage caused by BB (e.g. forest fire) on land …

Optimal Collaborative Path Planning For Unmanned Surface Vehicles Carried By A Parent Boat Along A Planned Route, Ari Carisza Graha Prasetia, I-Lin Wang, Aldy Gunawan

Research Collection School Of Computing and Information Systems

In this paper, an effective mechanism using a fleet of unmanned surface vehicles (USVs) carried by a parent boat (PB) is proposed to complete search or scientific tasks over multiple target water areas within a shorter time . Specifically, multiple USVs can be launched from the PB to conduct such operations simultaneously, and each USV can return to the PB for battery recharging or swapping and data collection in order to continue missions in a more extended range. The PB itself follows a planned route with a flexible schedule taking into consideration locational constraints or collision avoidance in a real-world …

Co-Embedding Attributed Networks With External Knowledge, Pei-Chi Lo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Attributed network embedding aims to learn representations of nodes and their attributes in a low-dimensional space that preserves their semantics. The existing embedding models, however, consider node connectivity and node attributes only while ignoring external knowledge that can enhance node representations for downstream applications. In this paper, we propose a set of new VAE-based embedding models called External Knowledge-Aware Co-Embedding Attributed Network (ECAN) Embeddings to incorporate associations among attributes from relevant external knowledge. Such external knowledge can be extracted from text corpus and knowledge graphs. We use multi-VAE structures to model the attribute associations. To cope with joint encoding of …

Learning To Dispatch For Job Shop Scheduling Via Deep Reinforcement Learning, Cong Zhang, Wen Song, Zhiguang Cao, Jie Zhang, Puay Siew Tan, Xu Chi

Research Collection School Of Computing and Information Systems

Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP). However, the design of effective PDRs is a tedious task, requiring a myriad of specialized knowledge and often delivering limited performance. In this paper, we propose to automatically learn PDRs via an end-to-end deep reinforcement learning agent. We exploit the disjunctive graph representation of JSSP, and propose a Graph Neural Network based scheme to embed the states encountered during solving. The resulting policy network is size-agnostic, effectively enabling generalization on large-scale instances. Experiments show that the agent can learn high-quality PDRs from scratch with elementary raw …

Jointly Optimizing Sensing Pipelines For Multimodal Mixed Reality Interaction, Ramesh Darshana Rathnayake Kanatta Gamage, Ashen De Silva, Dasun Puwakdandawa, Lakmal Meegahapola, Archan Misra, Indika Perera

Research Collection School Of Computing and Information Systems

Natural human interactions for Mixed Reality Applications are overwhelmingly multimodal: humans communicate intent and instructions via a combination of visual, aural and gestural cues. However, supporting low-latency and accurate comprehension of such multimodal instructions (MMI), on resource-constrained wearable devices, remains an open challenge, especially as the state-of-the-art comprehension techniques for each individual modality increasingly utilize complex Deep Neural Network models. We demonstrate the possibility of overcoming the core limitation of latency–vs.–accuracy tradeoff by exploiting cross-modal dependencies–i.e., by compensating for the inferior performance of one model with an increased accuracy of more complex model of a different modality. We present a …

Graphmp: I/O-Efficient Big Graph Analytics On A Single Commodity Machine, Peng Sun, Yonggang Wen, Nguyen Binh Duong Ta, Xiaokui Xiao

Research Collection School Of Computing and Information Systems

Recent studies showed that single-machine graph processing systems can be as highly competitive as cluster-based approaches on large-scale problems. While several out-of-core graph processing systems and computation models have been proposed, the high disk I/O overhead could significantly reduce performance in many practical cases. In this paper, we propose GraphMP to tackle big graph analytics on a single machine. GraphMP achieves low disk I/O overhead with three techniques. First, we design a vertex-centric sliding window (VSW) computation model to avoid reading and writing vertices on disk. Second, we propose a selective scheduling method to skip loading and processing unnecessary edge …

A Near-Optimal Change-Detection Based Algorithm For Piecewise-Stationary Combinatorial Semi-Bandits, Huozhi Zhou, Lingda Wang, Lav N. Varshney, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

We investigate the piecewise-stationary combinatorial semi-bandit problem. Compared to the original combinatorial semi-bandit problem, our setting assumes the reward distributions of base arms may change in a piecewise-stationary manner at unknown time steps. We propose an algorithm, GLR-CUCB, which incorporates an efficient combinatorial semi-bandit algorithm, CUCB, with an almost parameter-free change-point detector, the Generalized Likelihood Ratio Test (GLRT). Our analysis shows that the regret of GLR-CUCB is upper bounded by O(√NKT logT), where N is the number of piecewise-stationary segments, K is the number of base arms, and T is the number of time steps. As a complement, we also …

Sharper Generalisation Bounds For Pairwise Learning, Yunwen Lei, Antoine Ledent, Marius Kloft

Research Collection School Of Computing and Information Systems

Pairwise learning refers to learning tasks with loss functions depending on a pair of training examples, which includes ranking and metric learning as specific examples. Recently, there has been an increasing amount of attention on the generalization analysis of pairwise learning to understand its practical behavior. However, the existing stability analysis provides suboptimal high-probability generalization bounds. In this paper, we provide a refined stability analysis by developing generalization bounds which can be √nn-times faster than the existing results, where nn is the sample size. This implies excess risk bounds of the order O(n−1/2) (up to a logarithmic factor) for both …

A Hybrid Approach For Detecting Prerequisite Relations In Multi-Modal Food Recipes, Liangming Pan, Jingjing Chen, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Modeling the structure of culinary recipes is the core of recipe representation learning. Current approaches mostly focus on extracting the workflow graph from recipes based on text descriptions. Process images, which constitute an important part of cooking recipes, has rarely been investigated in recipe structure modeling. We study this recipe structure problem from a multi-modal learning perspective, by proposing a prerequisite tree to represent recipes with cooking images at a step-level granularity. We propose a simple-yet-effective two-stage framework to automatically construct the prerequisite tree for a recipe by (1) utilizing a trained classifier to detect pairwise prerequisite relations that fuses …

Differential Privacy Protection Over Deep Learning: An Investigation Of Its Impacted Factors, Ying Lin, Ling-Yan Bao, Ze-Minghui Li, Shu-Sheng Si, Chao-Hsien Chu

Research Collection School Of Computing and Information Systems

Deep learning (DL) has been widely applied to achieve promising results in many fields, but it still exists various privacy concerns and issues. Applying differential privacy (DP) to DL models is an effective way to ensure privacy-preserving training and classification. In this paper, we revisit the DP stochastic gradient descent (DP-SGD) method, which has been used by several algorithms and systems and achieved good privacy protection. However, several factors, such as the sequence of adding noise, the models used etc., may impact its performance with various degrees. We empirically show that adding noise first and clipping second will not only …

Lightning-Fast And Privacy-Preserving Outsourced Computation In The Cloud, Ximeng Liu, Robert H. Deng, Pengfei Wu, Yang Yang

Research Collection School Of Computing and Information Systems

In this paper, we propose a framework for lightning-fast privacy-preserving outsourced computation framework in the cloud, which we refer to as LightCom. Using LightCom, a user can securely achieve the outsource data storage and fast, secure data processing in a single cloud server different from the existing multi-server outsourced computation model. Specifically, we first present a general secure computation framework for LightCom under the cloud server equipped with multiple Trusted Processing Units (TPUs), which face the side-channel attack. Under the LightCom, we design two specified fast processing toolkits, which allow the user to achieve the commonly-used secure integer computation and …

Walls Have Ears: Eavesdropping User Behaviors Via Graphics-Interrupt-Based Side Channel, Haoyu Ma, Jianwen Tian, Debin Gao, Jia Chunfu

Research Collection School Of Computing and Information Systems

Graphics Processing Units (GPUs) are now playing a vital role in many devices and systems including computing devices, data centers, and clouds, making them the next target of side-channel attacks. Unlike those targeting CPUs, existing side-channel attacks on GPUs exploited vulnerabilities exposed by application interfaces like OpenGL and CUDA, which can be easily mitigated with software patches. In this paper, we investigate the lower-level and native interface between GPUs and CPUs, i.e., the graphics interrupts, and evaluate the side channel they expose. Being an intrinsic profile in the communication between a GPU and a CPU, the pattern of graphics interrupts …

Generating Concept Based Api Element Comparison Using A Knowledge Graph, Yang Liu, Mingwei Liu, Xin Peng, Christoph Treude, Zhenchang Xing, Xiaoxin Zhang

Research Collection School Of Computing and Information Systems

Recommender systems are a valuable tool for software engineers. For example, they can provide developers with a ranked list of files likely to contain a bug, or multiple auto-complete suggestions for a given method stub. However, the way these recommender systems interact with developers is often rudimentary—a long list of recommendations only ranked by the model’s confidence. In this vision paper, we lay out our research agenda for re-imagining how recommender systems for software engineering communicate their insights to developers. When issuing recommendations, our aim is to recommend diverse rather than redundant solutions and present them in ways that highlight …

Adelaidecyc At Semeval-2020 Task 12: Ensemble Of Classifiers For Offensive Language Detection In Social Media, Mahen Herath, Thushari Atapattu, Hoang Anh Dung, Christoph Treude, Katrina Falkner

Research Collection School Of Computing and Information Systems

This paper describes the systems our team (AdelaideCyC) has developed for SemEval Task 12 (OffensEval 2020) to detect offensive language in social media. The challenge focuses on three subtasks – offensive language identification (subtask A), offense type identification (subtask B), and offense target identification (subtask C). Our team has participated in all the three subtasks. We have developed machine learning and deep learning-based ensembles of models. We have achieved F1-scores of 0.906, 0.552, and 0.623 in subtask A, B, and C respectively. While our performance scores are promising for subtask A, the results demonstrate that subtask B and C still …

Improving Gan Training With Probability Ratio Clipping And Sample Reweighting, Yue Wu, Pan Zhou, Andrew Wilson Gordon, Eric Xing, Zhiting Hu

Research Collection School Of Computing and Information Systems

Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation. To solve this issue, we propose a new variational GAN training framework which enjoys superior training stability. Our approach is inspired by a connection of GANs and reinforcement learning under a variational perspective. The connection leads to (1) probability ratio clipping that regularizes generator training to prevent excessively large updates, and (2) a sample re-weighting mechanism that improves discriminator training by downplaying bad-quality fake samples. Moreover, our variational GAN framework can provably …

Theory-Inspired Path-Regularized Differential Network Architecture Search, Pan Zhou, Caiming Xiong, Richard Socher, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g. convolution, skip connection and zero operation, to the network optimization. We prove that the architectures with more skip connections can converge faster than the other candidates, and thus are selected by DARTS. This result, for the first time, theoretically and explicitly …

Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam In Deep Learning, Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven C. H. Hoi, Weinan E

Research Collection School Of Computing and Information Systems

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing their local convergence behaviors. Specifically, we observe the heavy tails of gradient noise in these algorithms. This motivates us to analyze these algorithms through their Lévy-driven stochastic differential equations (SDEs) because of the similar convergence behaviors of an algorithm and its SDE. Then we establish the escaping time of these SDEs from a local basin. The result shows that (1) the escaping time of both SGD …

Algorithms And Hardness Results For Computing Cores Of Markov Chains, Ali Ahmadi, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Tobias Meggendorfer, Roodabeh Safavi, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Given a Markov chain M = (V,v0,δ), with state space V and a starting state v0, and a probability threshold ϵ, an ϵ-core is a subset C of states that is left with probability at most ϵ. More formally, C ⊆V is an ϵ-core, iff P reach(V\C) ≤ ϵ. Cores have been applied in a wide variety of verification problems over Markov chains, Markov decision processes, and probabilistic programs, as a means of discarding uninteresting and low-probability parts of a probabilistic system and instead being able to focus on the states that are likely to be encountered in a real-world …

Variational Bayesian Inference For Crowdsourcing Predictions, Desmond Cai, Duc Thien Nguyen, Shiau Hong Lim, Laura Wynter

Research Collection School Of Computing and Information Systems

Crowdsourcing has emerged as an effective means for performing a number of machine learning tasks such as annotation and labelling of images and other data sets. In most early settings of crowdsourcing, the task involved classification, that is assigning one of a discrete set of labels to each task. Recently, however, more complex tasks have been attempted including asking crowdsource workers to assign continuous labels, or predictions. In essence, this involves the use of crowdsourcing for function estimation. We are motivated by this problem to drive applications such as collaborative prediction, that is, harnessing the wisdom of the crowd to …

A Fast And Exact Motif Enumeration Algorithm For Dynamic Networks, Abbas Al-Thaedan

Theses and Dissertations

From social to biological networks, prior research in complex networks have demonstrated the importance of the frequency and distribution of different types of motifs to important network functions and properties. A network motif (or graphlet) is defined as a small connected sub-pattern which is over-represented in a network. Network motifs have been widely applied in a wide range of applications, namely biological, social, and technical networks. The counting of the network motif involves expensive enumeration of graph sub-patterns along with the detection of graph isomorphism. In general, network motif detection algorithms are computationally expensive and often designed to operate over …

Implementation Of An Electronic Alert For Improving Adherence To Diabetic Foot Exam Screenings In Type 2 Diabetic Patients In Primary Care Clinics, Ruby Denson

Student Scholarly Projects

Practice Problem: Patients with type 2 diabetes mellitus (T2DM) are at an increased risk of complications including foot ulcerations (Harris-Hayes et al., 2020). Preventive care is essential for the early detection of foot ulcers but despite the advantages of preventive screening, a limited number of primary care providers perform annual foot exams (Williams et al., 2018).

PICOT: The clinical question that guided this project was, “In adult patients with T2DM receiving care in a primary care setting, will the implementation of an electronic clinical reminder alert (ECR) increase provider adherence to performing an annual diabetic foot exam and risk …