Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 871 - 900 of 6891

Full-Text Articles in Physical Sciences and Mathematics

Autopruner: Transformer-Based Call Graph Pruning, Cong Thanh Le, Hong Jin Kang, Truong Giang Nguyen, Stefanus Agus Haryono, David Lo, Xuan-Bach D. Le, Huynh Quyet Thang Nov 2022

Autopruner: Transformer-Based Call Graph Pruning, Cong Thanh Le, Hong Jin Kang, Truong Giang Nguyen, Stefanus Agus Haryono, David Lo, Xuan-Bach D. Le, Huynh Quyet Thang

Research Collection School Of Computing and Information Systems

Constructing a static call graph requires trade-offs between soundness and precision. Program analysis techniques for constructing call graphs are unfortunately usually imprecise. To address this problem, researchers have recently proposed call graph pruning empowered by machine learning to post-process call graphs constructed by static analysis. A machine learning model is built to capture information from the call graph by extracting structural features for use in a random forest classifier. It then removes edges that are predicted to be false positives. Despite the improvements shown by machine learning models, they are still limited as they do not consider the source code …

Go to article

In War And Peace: The Impact Of World Politics On Software Ecosystems, Raula Kula, Christoph Treude Nov 2022

In War And Peace: The Impact Of World Politics On Software Ecosystems, Raula Kula, Christoph Treude

Research Collection School Of Computing and Information Systems

Reliance on third-party libraries is now commonplace in contemporary software engineering. Being open source in nature, these libraries should advocate for a world where the freedoms and opportunities of open source software can be enjoyed by all. Yet, there is a growing concern related to maintainers using their influence to make political stances (i.e., referred to as protestware). In this paper, we reflect on the impact of world politics on software ecosystems, especially in the context of the ongoing War in Ukraine. We show three cases where world politics has had an impact on a software ecosystem, and how these …

Go to article

Photovoltaic Cells For Energy Harvesting And Indoor Positioning, Hamada Rizk, Dong Ma, Mahbub Hassan, Moustafa Youssef Nov 2022

Photovoltaic Cells For Energy Harvesting And Indoor Positioning, Hamada Rizk, Dong Ma, Mahbub Hassan, Moustafa Youssef

Research Collection School Of Computing and Information Systems

We propose SoLoc, a lightweight probabilistic fingerprinting-based technique for energy-free device-free indoor localization. The system harnesses photovoltaic currents harvested by the photovoltaic cells in smart environments for simultaneously powering digital devices and user positioning. The basic principle is that the location of the human interferes with the lighting received by the photovoltaic cells, thus producing a location fingerprint on the generated photocurrents. To ensure resilience to noisy measurements, SoLoc constructs probability distributions as a photovoltaic fingerprint at each location. Then, we employ a probabilistic graphical model for estimating the user location in the continuous space. Results show that SoLoc can …

Go to article

Recipegen++: An Automated Trigger Action Programs Generator, Imam Nur Bani Yusuf, Diyanah Abdul Jamal, Lingxiao Jiang, David Lo Nov 2022

Recipegen++: An Automated Trigger Action Programs Generator, Imam Nur Bani Yusuf, Diyanah Abdul Jamal, Lingxiao Jiang, David Lo

Research Collection School Of Computing and Information Systems

Trigger Action Programs (TAPs) are event-driven rules that allow users to automate smart-devices and internet services. Users can write TAPs by specifying triggers and actions from a set of predefined channels and functions. Despite its simplicity, composing TAPs can still be challenging for users due to the enormous search space of available triggers and actions. The growing popularity of TAPs is followed by the increasing number of supported devices and services, resulting in a huge number of possible combinations between triggers and actions. Motivated by such a fact, we improve our prior work and propose RecipeGen++, a deep-learning-based approach that …

Go to article

A Quality Metric For K-Means Clustering Based On Centroid Locations, Manoj Thulasidas Nov 2022

A Quality Metric For K-Means Clustering Based On Centroid Locations, Manoj Thulasidas

Research Collection School Of Computing and Information Systems

K-Means clustering algorithm does not offer a clear methodology to determine the appropriate number of clusters; it does not have a built-in mechanism for K selection. In this paper, we present a new metric for clustering quality and describe its use for K selection. The proposed metric, based on the locations of the centroids, as well as the desired properties of the clusters, is developed in two stages. In the initial stage, we take into account the full covariance matrix of the clustering variables, thereby making it mathematically similar to a reduced chi2. We then extend it to account for …

Go to article

Cscw 2022 Chairs' Welcome, Gary Hsieh, Anthony Tang Nov 2022

Cscw 2022 Chairs' Welcome, Gary Hsieh, Anthony Tang

Research Collection School Of Computing and Information Systems

We are excited to bring you the 25th ACM Conference on Computer-Supported Cooperative Work and Social Computing – CSCW 2022 – virtually. We were initially poised to hold CSCW 2022 in Taiwan to help strengthen the CSCW community’s relationship with Asia, but the uncertainty around COVID-19 pandemic restrictions made this an impractical idea. Yet, as designers, we view challenges as learning opportunities and know learning opportunities lead to new ideas and approaches. From the online and virtual conferences experiences of the past few years, we considered questions like: what makes conferences interesting, what makes conferences worth attending, how can we …

Go to article

Predictive Self-Organizing Neural Networks For In-Home Detection Of Mild Cognitive Impairment, Seng Khoon Teh, Iris Rawtaer, Ah-Hwee Tan Nov 2022

Predictive Self-Organizing Neural Networks For In-Home Detection Of Mild Cognitive Impairment, Seng Khoon Teh, Iris Rawtaer, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

In-home sensing of daily living patterns from older adults coupled with machine learning is a promisingapproach to detect Mild Cognitive Impairment (MCI), a potentially reversible condition with early detectionand appropriate intervention. However, the number of subjects involved in such real-world studies istypically limited, posing the so-called small data problem to most predictive models which rely on a sizablenumber of labeled data. In this work, a predictive self-organizing neural network known as fuzzy AdaptiveResonance Associate Map (fuzzy ARAM) is proposed to detect MCI using in-home sensor data collected from aunique Singapore cross-sectional study. Specifically, mean and standard deviation of nine in-home …

Go to article

Daot: Domain-Agnostically Aligned Optimal Transport For Domain-Adaptive Crowd Counting, Huilin Zhu, Jingling Yuan, Xian Zhong, Zhengwei Yang, Zheng Wang, Shengfeng He Nov 2022

Daot: Domain-Agnostically Aligned Optimal Transport For Domain-Adaptive Crowd Counting, Huilin Zhu, Jingling Yuan, Xian Zhong, Zhengwei Yang, Zheng Wang, Shengfeng He

Research Collection School Of Computing and Information Systems

Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets. However, existing domain adaptation methods tend to focus on inter-dataset differences while overlooking the intra-differences within the same dataset, leading to additional learning ambiguities. These domain-agnostic factors,e.g., density, surveillance perspective, and scale, can cause significant in-domain variations, and the misalignment of these factors across domains can lead to a drop in performance in cross-domain crowd counting. To address this issue, we propose a Domain-agnostically Aligned Optimal Transport (DAOT) strategy that aligns domain-agnostic factors between domains. The DAOT consists of three steps. First, individual-level differences …

Go to article

How To Formulate Specific How-To Questions In Software Development?, Mingwei Liu, Xin Peng, Andrian Marcus, Christoph Treude, Jiazhan Xie, Huanjun Xu, Yanjun Yang Nov 2022

How To Formulate Specific How-To Questions In Software Development?, Mingwei Liu, Xin Peng, Andrian Marcus, Christoph Treude, Jiazhan Xie, Huanjun Xu, Yanjun Yang

Research Collection School Of Computing and Information Systems

Developers often ask how-to questions using search engines, technical Q&A communities, and interactive Q&A systems to seek help for specific programming tasks. However, they often do not formulate the questions in a specific way, making it hard for the systems to return the best answers. We propose an approach (TaskKG4Q) that interactively helps developers formulate a programming related how-to question. TaskKG4Q is using a programming task knowledge graph (task KG in short) mined from Stack Overflow questions, which provides a hierarchical conceptual structure for tasks in terms of [actions], [objects], and [constraints]. An empirical evaluation of the intrinsic quality of …

Go to article

Epic-Kitchens Visor Benchmark: Video Segmentations And Object Relations, Ahmad Ak Dar Khalil, Dandan Shan, Bin Zhu, Jian Ma, Amlan Kar, Richard Higgins, David Fouhey, Sanja Fidler, Dima Damen Nov 2022

Epic-Kitchens Visor Benchmark: Video Segmentations And Object Relations, Ahmad Ak Dar Khalil, Dandan Shan, Bin Zhu, Jian Ma, Amlan Kar, Richard Higgins, David Fouhey, Sanja Fidler, Dima Damen

Research Collection School Of Computing and Information Systems

We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, …

Go to article

Shell Theory: A Statistical Model Of Reality, Wen-Yan Lin, Siying Liu, Changhao Ren, Ngai-Man Cheung, Hongdong Li, Yasuyuki Matsushita Oct 2022

Shell Theory: A Statistical Model Of Reality, Wen-Yan Lin, Siying Liu, Changhao Ren, Ngai-Man Cheung, Hongdong Li, Yasuyuki Matsushita

Research Collection School Of Computing and Information Systems

Machine learning's grand ambition is the mathematical modeling of reality. The recent years have seen major advances using deep-learned techniques that model reality implicitly; however, corresponding advances in explicit mathematical models have been noticeably lacking. We believe this dichotomy is rooted in the limitations of the current statistical tools, which struggle to make sense of the high dimensional generative processes that natural data seems to originate from. This paper proposes a new, distance based statistical technique which allows us to develop elegant mathematical models of such generative processes. Our model suggests that each semantic concept has an associated distinctive-shell which …

Go to article

Investigating Accessibility Challenges And Opportunities For Users With Low Vision Disabilities In Customer-To-Customer (C2c) Marketplaces, Bektur Ryskeldiev, Kotaro Hara, Mariko Kobayashi, Koki Kusano Oct 2022

Investigating Accessibility Challenges And Opportunities For Users With Low Vision Disabilities In Customer-To-Customer (C2c) Marketplaces, Bektur Ryskeldiev, Kotaro Hara, Mariko Kobayashi, Koki Kusano

Research Collection School Of Computing and Information Systems

Inaccessible e-commerce websites and mobile applications exclude people with visual impairments (PVI) from online shopping. Customer-to-customer (C2C) marketplaces, a form of e-commerce where trading happens not between businesses and customers but between customers, could pose a unique set of challenges in the interactions that the platform brings about. Through online questionnaire and remote interviews, we investigate problems experienced by people with low vision disabilities in common C2C scenarios. Our study with low vision participants (N = 12) reveal both previously known general accessibility issues (e.g., web and mobile interface accessibility) and C2C specific accessibility issues (e.g., inability to confirm item …

Go to article

Cvfnet: Real-Time 3d Object Detection By Learning Cross View Features, Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, Xijun Zhao, Zhiyuan Zhang Oct 2022

Cvfnet: Real-Time 3d Object Detection By Learning Cross View Features, Jiaqi Gu, Zhiyu Xiang, Pan Zhao, Tingming Bai, Lingxuan Wang, Xijun Zhao, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

In recent years 3D object detection from LiDAR point clouds has made great progress thanks to the development of deep learning technologies. Although voxel or point based methods are popular in 3D object detection, they usually involve time-consuming operations such as 3D convolutions on voxels or ball query among points, making the resulting network inappropriate for time critical applications. On the other hand, 2D view-based methods feature high computing efficiency while usually obtaining inferior performance than the voxel or point based methods. In this work, we present a real-time view-based single stage 3D object detector, namely CVFNet to fulfill this …

Go to article

Dynamic Temporal Filtering In Video Models, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei Oct 2022

Dynamic Temporal Filtering In Video Models, Fuchen Long, Zhaofan Qiu, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Video temporal dynamics is conventionally modeled with 3D spatial-temporal kernel or its factorized version comprised of 2D spatial kernel and 1D temporal kernel. The modeling power, nevertheless, is limited by the fixed window size and static weights of a kernel along the temporal dimension. The pre-determined kernel size severely limits the temporal receptive fields and the fixed weights treat each spatial location across frames equally, resulting in sub-optimal solution for longrange temporal modeling in natural scenes. In this paper, we present a new recipe of temporal feature learning, namely Dynamic Temporal Filter (DTF), that novelly performs spatial-aware temporal modeling in …

Go to article

Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei Oct 2022

Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly employ down-sampling operations (e.g., average pooling) over keys/values to dramatically reduce the computational cost. In this work, we argue that such over-aggressive down-sampling design is not invertible and inevitably causes information dropping especially for high-frequency components in objects (e.g., texture details). Motivated by the wavelet theory, we construct a new Wavelet Vision Transformer (Wave-ViT) that formulates the invertible down-sampling with wavelet transforms and self-attention learning in a unified way. …

Go to article

Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo Oct 2022

Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes �� times longer sequence than the latter under the current attention of quadratic complexity (�� 2�� 2 ). The existing works treat the temporal axis as a simple extension of spatial axes, focusing on shortening the spatio-temporal sequence by either generic pooling or local windowing without utilizing temporal redundancy. However, videos naturally contain redundant information between neighboring frames; thereby, we could potentially suppress attention on visually similar frames in a dilated manner. Based on this hypothesis, we propose the LAPS, a long-term “Leap …

Go to article

Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo Oct 2022

Interactive Video Corpus Moment Retrieval Using Reinforcement Learning, Zhixin Ma, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Known-item video search is effective with human-in-the-loop to interactively investigate the search result and refine the initial query. Nevertheless, when the first few pages of results are swamped with visually similar items, or the search target is hidden deep in the ranked list, finding the know-item target usually requires a long duration of browsing and result inspection. This paper tackles the problem by reinforcement learning, aiming to reach a search target within a few rounds of interaction by long-term learning from user feedbacks. Specifically, the system interactively plans for navigation path based on feedback and recommends a potential target that …

Go to article

Mando: Multi-Level Heterogeneous Graph Embeddings For Fine-Grained Detection Of Smart Contract Vulnerabilities, Huu Hoang Nguyen, Nhat Minh Nguyen, Chunyao Xie, Zahra Ahmadi, Daniel Kudenko, Thanh Nam Doan, Lingxiao Jiang Oct 2022

Mando: Multi-Level Heterogeneous Graph Embeddings For Fine-Grained Detection Of Smart Contract Vulnerabilities, Huu Hoang Nguyen, Nhat Minh Nguyen, Chunyao Xie, Zahra Ahmadi, Daniel Kudenko, Thanh Nam Doan, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Learning heterogeneous graphs consisting of different types of nodes and edges enhances the results of homogeneous graph techniques. An interesting example of such graphs is control-flow graphs representing possible software code execution flows. As such graphs represent more semantic information of code, developing techniques and tools for such graphs can be highly beneficial for detecting vulnerabilities in software for its reliability. However, existing heterogeneous graph techniques are still insufficient in handling complex graphs where the number of different types of nodes and edges is large and variable. This paper concentrates on the Ethereum smart contracts as a sample of software …

Go to article

Towards Understanding The Faults Of Javascript-Based Deep Learning Systems, Lili Quan, Qianyu Guo, Xiaofei Xie, Sen Chen, Xiaohong Li, Yang Liu Oct 2022

Towards Understanding The Faults Of Javascript-Based Deep Learning Systems, Lili Quan, Qianyu Guo, Xiaofei Xie, Sen Chen, Xiaohong Li, Yang Liu

Research Collection School Of Computing and Information Systems

Quality assurance is of great importance for deep learning (DL) systems, especially when they are applied in safety-critical applications. While quality issues of native DL applications have been extensively analyzed, the issues of JavaScript-based DL applications have never been systematically studied. Compared with native DL applications, JavaScript-based DL applications can run on major browsers, making the platform- and device-independent. Specifically, the quality of JavaScript-based DL applications depends on the 3 parts: the application, the third-party DL library used and the underlying DL framework (e.g., TensorFlow.js), called JavaScript-based DL system. In this paper, we conduct the first empirical study on the …

Go to article

Compressing Pre-Trained Models Of Code Into 3 Mb, Jieke Shi, Zhou Yang, Bowen Xu, Hong Jin Kang, David Lo Oct 2022

Compressing Pre-Trained Models Of Code Into 3 Mb, Jieke Shi, Zhou Yang, Bowen Xu, Hong Jin Kang, David Lo

Research Collection School Of Computing and Information Systems

Although large pre-trained models of code have delivered significant advancements in various code processing tasks, there is an impediment to the wide and fluent adoption of these powerful models in software developers’ daily workflow: these large models consume hundreds of megabytes of memory and run slowly on personal devices, which causes problems in model deployment and greatly degrades the user experience. It motivates us to propose Compressor, a novel approach that can compress the pre-trained models of code into extremely small models with negligible performance sacrifice. Our proposed method formulates the design of tiny models as simplifying the pre-trained model …

Go to article

Improving Knowledge-Aware Recommendation With Multi-Level Interactive Contrastive Learning, Ding Zou, Wei Wei, Ziyang Wang, Xian-Ling Mao, Feida Zhu, Rui Fang, Dangyang Chen Oct 2022

Improving Knowledge-Aware Recommendation With Multi-Level Interactive Contrastive Learning, Ding Zou, Wei Wei, Ziyang Wang, Xian-Ling Mao, Feida Zhu, Rui Fang, Dangyang Chen

Research Collection School Of Computing and Information Systems

Incorporating Knowledge Graphs (KG) into recommeder system as side information has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs). However, the extremely sparse user-item interactions significantly degrade the performance of the GNN-based models, from the following aspects: 1) the sparse interaction, itself, means inadequate supervision signals and limits the supervised GNN-based models; 2) the combination of sparse interactions (CF part) and redundant KG facts (KG part) further results in an unbalanced information utilization. Besides, the GNN paradigm aggregates local neighbors for node representation learning, while ignoring …

Go to article

Social Access And Representation For Autistic Adult Livestreamers, Terrance Mok, Anthony Tang, Adam Mccrimmon, Lora Oehlberg Oct 2022

Social Access And Representation For Autistic Adult Livestreamers, Terrance Mok, Anthony Tang, Adam Mccrimmon, Lora Oehlberg

Research Collection School Of Computing and Information Systems

We interviewed 10 autistic livestreamers to understand their motivations for livestreaming on Twitch. Our participants explained that streaming helped them fulfill social desires by: supporting them in making meaningful social connections with others; giving them a safe space to practice social skills like “small talk”; and empowering them to be autistic role models and to share their true selves. This work offers an early report on how autistic individuals leverage livestreaming as a beneficial social platform while struggling with audience expectations.

Go to article

Pixel-Wise Energy-Biased Abstention Learning For Anomaly Segmentation On Complex Urban Driving Scenes, Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro Oct 2022

Pixel-Wise Energy-Biased Abstention Learning For Anomaly Segmentation On Complex Urban Driving Scenes, Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise abstention learning (AL) with a model that learns an adaptive pixel-level anomaly class, and an energy-based model (EBM) that learns inlier pixel distribution. More specifically, PEBAL is …

Go to article

Physical Adversarial Attack On A Robotic Arm, Yifan Jia, Christopher M. Poskitt, Jun Sun, Sudipta Chattopadhyay Oct 2022

Physical Adversarial Attack On A Robotic Arm, Yifan Jia, Christopher M. Poskitt, Jun Sun, Sudipta Chattopadhyay

Research Collection School Of Computing and Information Systems

Collaborative Robots (cobots) are regarded as highly safety-critical cyber-physical systems (CPSs) owing to their close physical interactions with humans. In settings such as smart factories, they are frequently augmented with AI. For example, in order to move materials, cobots utilize object detectors based on deep learning models. Deep learning, however, has been demonstrated as vulnerable to adversarial attacks: a minor change (noise) to benign input can fool the underlying neural networks and lead to a different result. While existing works have explored such attacks in the context of picture/object classification, less attention has been given to attacking neural networks used …

Go to article

Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing, Liang Li, Baihua Zheng, Weiwei Sun Oct 2022

Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing, Liang Li, Baihua Zheng, Weiwei Sun

Research Collection School Of Computing and Information Systems

Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting entity relations from texts. However, it usually suffers from the long-tail issue. The training data mainly concentrates on a few types of relations, leading to the lack of sufficient annotations for the remaining types of relations. In this paper, we propose a general approach to learn relation prototypes from unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient training data. We learn relation prototypes as an implicit factor between entities, which reflects the meanings of relations as well …

Go to article

Interactive Contrastive Learning For Self-Supervised Entity Alignment, Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Jing Wan, Juanzi Li Oct 2022

Interactive Contrastive Learning For Self-Supervised Entity Alignment, Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Jing Wan, Juanzi Li

Research Collection School Of Computing and Information Systems

Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without the use of pre-aligned entity pairs. The current state-of-the-art (SOTA) selfsupervised EA approach draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, it advocates the minimum information requirement for self-supervised EA, while we argue that self-described KG’s side information (e.g., entity name, relation name, …

Go to article

Stitching Weight-Shared Deep Neural Networks For Efficient Multitask Inference On Gpu, Zeyu Wang, Xiaoxi He, Zimu Zhou, Xu Wang, Qiang Ma, Xin Miao, Zhuo Liu, Lothar Thiele, Zheng. Yang Oct 2022

Stitching Weight-Shared Deep Neural Networks For Efficient Multitask Inference On Gpu, Zeyu Wang, Xiaoxi He, Zimu Zhou, Xu Wang, Qiang Ma, Xin Miao, Zhuo Liu, Lothar Thiele, Zheng. Yang

Research Collection School Of Computing and Information Systems

Intelligent personal and home applications demand multiple deep neural networks (DNNs) running on resourceconstrained platforms for compound inference tasks, known as multitask inference. To fit multiple DNNs into low-resource devices, emerging techniques resort to weight sharing among DNNs to reduce their storage. However, such reduction in storage fails to translate into efficient execution on common accelerators such as GPUs. Most DNN graph rewriters are blind for multiDNN optimization, while GPU vendors provide inefficient APIs for parallel multi-DNN execution at runtime. A few prior graph rewriters suggest cross-model graph fusion for low-latency multiDNN execution. Yet they request duplication of the shared …

Go to article

Adding Context To Source Code Representations For Deep Learning, Fuwei Tian, Christoph Treude Oct 2022

Adding Context To Source Code Representations For Deep Learning, Fuwei Tian, Christoph Treude

Research Collection School Of Computing and Information Systems

Deep learning models have been successfully applied to a variety of software engineering tasks, such as code classification, summarisation, and bug and vulnerability detection. In order to apply deep learning to these tasks, source code needs to be represented in a format that is suitable for input into the deep learning model. Most approaches to representing source code, such as tokens, abstract syntax trees (ASTs), data flow graphs (DFGs), and control flow graphs (CFGs) only focus on the code itself and do not take into account additional context that could be useful for deep learning models. In this paper, we …

Go to article

Taming Multi-Output Recommenders For Software Engineering, Christoph Treude Oct 2022

Taming Multi-Output Recommenders For Software Engineering, Christoph Treude

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 …

Go to article

Video Graph Transformer For Video Question Answering, Junbin Xiao, Pan Zhou, Tat-Seng Chua, Shuicheng Yan Oct 2022

Video Graph Transformer For Video Question Answering, Junbin Xiao, Pan Zhou, Tat-Seng Chua, Shuicheng Yan

Research Collection School Of Computing and Information Systems

This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT’s uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal reasoning; and 2) it exploits disentangled video and text Transformers for relevance comparison between the video and text to perform QA, instead of entangled crossmodal Transformer for answer classification. Vision-text communication is done by additional cross-modal interaction modules. With more reasonable video encoding and QA solution, we show that VGT can achieve much better performances on VideoQA tasks …

Go to article

First Prev Next Last