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

Artificial Intelligence and Robotics Commons™

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

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 961 - 990 of 1664

Full-Text Articles in Artificial Intelligence and Robotics

Fleet Sizing And Allocation For On-Demand Last-Mile Transportation Systems, Karmel Shehadeh, Hai Wang, Peter Zhang Nov 2021

Fleet Sizing And Allocation For On-Demand Last-Mile Transportation Systems, Karmel Shehadeh, Hai Wang, Peter Zhang

Research Collection School Of Computing and Information Systems

The last-mile problem refers to the provision of travel service from the nearest public transportation node to home or other destination. Last-Mile Transportation Systems (LMTS), which have recently emerged, provide on-demand shared transportation. In this paper, we investigate the fleet sizing and allocation problem for the on-demand LMTS. Specifically, we consider the perspective of a last-mile service provider who wants to determine the number of servicing vehicles to allocate to multiple last-mile service regions in a particular city. In each service region, passengers demanding last-mile services arrive in batches, and allocated vehicles deliver passengers to their final destinations. The passenger …

Go to article

Predicting Anti-Asian Hateful Users On Twitter During Covid-19, Jisun An, Haewoon Kwak, Claire Seungeun Lee, Bogang Jun, Yong-Yeol Ahn Nov 2021

Predicting Anti-Asian Hateful Users On Twitter During Covid-19, Jisun An, Haewoon Kwak, Claire Seungeun Lee, Bogang Jun, Yong-Yeol Ahn

Research Collection School Of Computing and Information Systems

We investigate predictors of anti-Asian hate among Twitter users throughout COVID-19. With the rise of xenophobia and polarization that has accompanied widespread social media usage in many nations, online hate has become a major social issue, attracting many researchers. Here, we apply natural language processing techniques to characterize social media users who began to post anti-Asian hate messages during COVID-19. We compare two user groups—those who posted anti-Asian slurs and those who did not—with respect to a rich set of features measured with data prior to COVID-19 and show that it is possible to predict who later publicly posted anti-Asian …

Go to article

Stock Market Trend Forecasting Based On Multiple Textual Features: A Deep Learning Method, Zhenda Hu, Zhaoxia Wang, Seng-Beng Ho, Ah-Hwee Tan Nov 2021

Stock Market Trend Forecasting Based On Multiple Textual Features: A Deep Learning Method, Zhenda Hu, Zhaoxia Wang, Seng-Beng Ho, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Stock market trend forecasting is a valuable and challenging research task for both industry and academia. In order to explore the influence of stock news information on the stock market trend, a textual embedding construction method is proposed to encode multiple textual features, including topic features, sentiment features, and semantic features extracted from stock news textual content. In addition, a deep learning method is designed by using financial data and multiple textual features obtained from multiple news textual embeddings for short-term stock market trend prediction. For evaluation, extensive experiments on real stock market data are conducted. The experimental results illustrate …

Go to article

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua Nov 2021

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Task-oriented dialogue agents are built to assist users in completing various tasks. Generating appropriate responses for satisfactory task completion is the ultimate goal. Hence, as a convenient and straightforward way, metrics such as success rate, inform rate etc., have been widely leveraged to evaluate the generated responses. However, beyond task completion, there are several other factors that largely affect user satisfaction, which remain under-explored. In this work, we focus on analyzing different agent behavior patterns that lead to higher user satisfaction scores. Based on the findings, we design a neural response generation model EnRG. It naturally combines the power of …

Go to article

Self-Supervised Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh Nov 2021

Self-Supervised Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) that requires only normal (healthy) training images is an important tool for enabling the development of medical image analysis (MIA) applications, such as disease screening, since it is often difficult to collect and annotate abnormal (or disease) images in MIA. However, heavily relying on the normal images may cause the model training to overfit the normal class. Self-supervised pre-training is an effective solution to this problem. Unfortunately, current self-supervision methods adapted from computer vision are sub-optimal for MIA applications because they do not explore MIA domain knowledge for designing the pretext tasks or the training process. …

Go to article

Design Of A Two-Echelon Freight Distribution System In Last-Mile Logistics Considering Covering Locations And Occasional Drivers, Vincent F. Yu, Panca Jodiawan, Ming-Lu Hou, Aldy Gunawan Oct 2021

Design Of A Two-Echelon Freight Distribution System In Last-Mile Logistics Considering Covering Locations And Occasional Drivers, Vincent F. Yu, Panca Jodiawan, Ming-Lu Hou, Aldy Gunawan

Research Collection School Of Computing and Information Systems

This research addresses a new variant of the vehicle routing problem, called the two-echelon vehicle routing problem with time windows, covering options, and occasional drivers (2E-VRPTW-CO-OD). In this problem, two types of fleets are available to serve customers, city freighters and occasional drivers (ODs), while two delivery options are available to customers, home delivery and alternative delivery. For customers choosing the alternative delivery, their demands are delivered to one of the available covering locations for them to pick up. The objective of 2E-VRPTW-CO-OD is to minimize the total cost consisting of routing costs, connection costs, and compensations paid to ODs …

Go to article

Mlcatchup: Automated Update Of Deprecated Machine-Learning Apis In Python, Stefanus Agus Haryono, Thung Ferdian, David Lo, Julia Lawall, Lingxiao Jiang Oct 2021

Mlcatchup: Automated Update Of Deprecated Machine-Learning Apis In Python, Stefanus Agus Haryono, Thung Ferdian, David Lo, Julia Lawall, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Machine learning (ML) libraries are gaining vast popularity, especially in the Python programming language. Using the latest version of such libraries is recommended to ensure the best performance and security. When migrating to the latest version of a machine learning library, usages of deprecated APIs need to be updated, which is a time-consuming process. In this paper, we propose MLCatchUp, an automated API usage update tool for deprecated APIs of popular ML libraries written in Python. MLCatchUp automatically infers the required transformation to migrate usages of deprecated API through the differences between the deprecated and updated API signatures. MLCatchUp offers …

Go to article

Target-Guided Emotion-Aware Chat Machine, Wei Wei, Jiayi Liu, Xianling Mao, Guibing Guo, Feida Zhu, Pan Zhou, Yuchong Hu, Shanshan Feng Oct 2021

Target-Guided Emotion-Aware Chat Machine, Wei Wei, Jiayi Liu, Xianling Mao, Guibing Guo, Feida Zhu, Pan Zhou, Yuchong Hu, Shanshan Feng

Research Collection School Of Computing and Information Systems

The consistency of a response to a given post at the semantic level and emotional level is essential for a dialogue system to deliver humanlike interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem and proposes a unified end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leveraging target information to generate more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed …

Go to article

Conquer: Contextual Query-Aware Ranking For Video Corpus Moment Retrieval, Zhijian Hou, Chong-Wah Ngo, W. K. Chan Oct 2021

Conquer: Contextual Query-Aware Ranking For Video Corpus Moment Retrieval, Zhijian Hou, Chong-Wah Ngo, W. K. Chan

Research Collection School Of Computing and Information Systems

This paper tackles a recently proposed Video Corpus Moment Retrieval task. This task is essential because advanced video retrieval applications should enable users to retrieve a precise moment from a large video corpus. We propose a novel CONtextual QUery-awarE Ranking (CONQUER) model for effective moment localization and ranking. CONQUER explores query context for multi-modal fusion and representation learning in two different steps. The first step derives fusion weights for the adaptive combination of multi-modal video content. The second step performs bi-directional attention to tightly couple video and query as a single joint representation for moment localization. As query context is …

Go to article

Disambiguating Mentions Of Api Methods In Stack Overflow Via Type Scoping, Kien Luong, Ferdian Thung, David Lo Oct 2021

Disambiguating Mentions Of Api Methods In Stack Overflow Via Type Scoping, Kien Luong, Ferdian Thung, David Lo

Research Collection School Of Computing and Information Systems

Stack Overflow is one of the most popular venues for developers to find answers to their API-related questions. However, API mentions in informal text content of Stack Overflow are often ambiguous and thus it could be difficult to find the APIs and learn their usages. Disambiguating these API mentions is not trivial, as an API mention can match with names of APIs from different libraries or even the same one. In this paper, we propose an approach called DATYS to disambiguate API mentions in informal text content of Stack Overflow using type scoping. With type scoping, we consider API methods …

Go to article

Burst-Induced Multi-Armed Bandit For Learning Recommendation, Rodrigo Alves, Antoine Ledent, Marius Kloft Oct 2021

Burst-Induced Multi-Armed Bandit For Learning Recommendation, Rodrigo Alves, Antoine Ledent, Marius Kloft

Research Collection School Of Computing and Information Systems

In this paper, we introduce a non-stationary and context-free Multi-Armed Bandit (MAB) problem and a novel algorithm (which we refer to as BMAB) to solve it. The problem is context-free in the sense that no side information about users or items is needed. We work in a continuous-time setting where each timestamp corresponds to a visit by a user and a corresponding decision regarding recommendation. The main novelty is that we model the reward distribution as a consequence of variations in the intensity of the activity, and thereby we assist the exploration/exploitation dilemma by exploring the temporal dynamics of the …

Go to article

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua Oct 2021

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Task-oriented dialogue agents are built to assist users in completing various tasks. Generating appropriate responses for satisfactory task completion is the ultimate goal. Hence, as a convenient and straightforward way, metrics such as success rate, inform rate etc., have been widely leveraged to evaluate the generated responses. However, beyond task completion, there are several other factors that largely affect user satisfaction, which remain under-explored. In this work, we focus on analyzing different agent behavior patterns that lead to higher user satisfaction scores. Based on the findings, we design a neural response generation model EnRG. It naturally combines the power of …

Go to article

Eargate: Gait-Based User Identification With In-Ear Microphones, Andrea Ferlini, Dong Ma, Cecilia Mascolo Oct 2021

Eargate: Gait-Based User Identification With In-Ear Microphones, Andrea Ferlini, Dong Ma, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Human gait is a widely used biometric trait for user identification and recognition. Given the wide-spreading, steady diffusion of earworn wearables (Earables) as the new frontier of wearable devices, we investigate the feasibility of earable-based gait identification. Specifically, we look at gait-based identification from the sounds induced by walking and propagated through the musculoskeletal system in the body. Our system, EarGate, leverages an in-ear facing microphone which exploits the earable’s occlusion effect to reliably detect the user’s gait from inside the ear canal, without impairing the general usage of earphones. With data collected from 31 subjects, we show that EarGate …

Go to article

Solarslam: Battery-Free Loop Closure For Indoor Localisation, Bo Wei, Weitao Xu, Chengwen Luo, Guillaume Zoppi, Dong Ma, Sen Wang Oct 2021

Solarslam: Battery-Free Loop Closure For Indoor Localisation, Bo Wei, Weitao Xu, Chengwen Luo, Guillaume Zoppi, Dong Ma, Sen Wang

Research Collection School Of Computing and Information Systems

In this paper, we propose SolarSLAM, a batteryfree loop closure method for indoor localisation. Inertial Measurement Unit (IMU) based indoor localisation method has been widely used due to its ubiquity in mobile devices, such as mobile phones, smartwatches and wearable bands. However, it suffers from the unavoidable long term drift. To mitigate the localisation error, many loop closure solutions have been proposed using sophisticated sensors, such as cameras, laser, etc. Despite achieving high-precision localisation performance, these sensors consume a huge amount of energy. Different from those solutions, the proposed SolarSLAM takes advantage of an energy harvesting solar cell as a …

Go to article

Weakly-Supervised Video Anomaly Detection With Contrastive Learning Of Long And Short-Range Temporal Features, Yu Tian, Guansong Pang, Yuanhong Chen, Rajvinder Singh, Johan W. Verjans, Gustavo Carneiro Oct 2021

Weakly-Supervised Video Anomaly Detection With Contrastive Learning Of Long And Short-Range Temporal Features, Yu Tian, Guansong Pang, Yuanhong Chen, Rajvinder Singh, Johan W. Verjans, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

Anomaly detection with weakly supervised video-level labels is typically formulated as a multiple instance learning (MIL) problem, in which we aim to identify snippets containing abnormal events, with each video represented as a bag of video snippets. Although current methods show effective detection performance, their recognition of the positive instances, i.e., rare abnormal snippets in the abnormal videos, is largely biased by the dominant negative instances, especially when the abnormal events are subtle anomalies that exhibit only small differences compared with normal events. This issue is exacerbated in many methods that ignore important video temporal dependencies. To address this issue, …

Go to article

Constrained Contrastive Distribution Learning For Unsupervised Anomaly Detection And Localisation In Medical Images, Yu Tian, Guansong Pang, Fengbei Liu, Yuanhong Chen, Seon Ho Shin, Johan W. Verjans, Rajvinder Singh Oct 2021

Constrained Contrastive Distribution Learning For Unsupervised Anomaly Detection And Localisation In Medical Images, Yu Tian, Guansong Pang, Fengbei Liu, Yuanhong Chen, Seon Ho Shin, Johan W. Verjans, Rajvinder Singh

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main advantages over its fully supervised counterpart. Firstly, it is able to directly leverage large datasets available from health screening programs that contain mostly normal image samples, avoiding the costly manual labelling of abnormal samples and the subsequent issues involved in training with extremely class-imbalanced data. Further, UAD approaches can potentially detect and localise any type of lesions that deviate from the normal patterns. One significant challenge faced …

Go to article

Disentangling Hate In Online Memes, Ka Wei, Roy Lee, Rui Cao, Ziqing Fan, Jing Jiang, Wen Haw Chong Oct 2021

Disentangling Hate In Online Memes, Ka Wei, Roy Lee, Rui Cao, Ziqing Fan, Jing Jiang, Wen Haw Chong

Research Collection School Of Computing and Information Systems

Hateful and offensive content detection has been extensively explored in a single modality such as text. However, such toxic information could also be communicated via multimodal content such as online memes. Therefore, detecting multimodal hateful content has recently garnered much attention in academic and industry research communities. This paper aims to contribute to this emerging research topic by proposing DisMultiHate, which is a novel framework that performed the classification of multimodal hateful content. Specifically, DisMultiHate is designed to disentangle target entities in multimodal memes to improve the hateful content classification and explainability. We conduct extensive experiments on two publicly available …

Go to article

Artificial Intelligence And Work: Two Perspectives, Steven Miller, Thomas H. Davenport Sep 2021

Artificial Intelligence And Work: Two Perspectives, Steven Miller, Thomas H. Davenport

Research Collection School Of Computing and Information Systems

One of the most important issues in contemporary societies is the impact of intelligent technologies on human work. For an empirical perspective on the issue, we recently completed 30 case studies of people collaborating with AI-enabled smart machines. Twenty-four were from North America, mostly in the US. Six were from Southeast Asia, mostly in Singapore. We compare some of our observations to one of the broadest academic examinations of the issue. In particular, we focus on our case study observations with regard to key findings from the MIT Task Force on the Work of the Future report.

Go to article

Characterization And Automatic Updates Of Deprecated Machine-Learning Api Usages, Stefanus Agus Haryono, Thung Ferdian, David Lo, Julia Lawall, Lingxiao Jiang Sep 2021

Characterization And Automatic Updates Of Deprecated Machine-Learning Api Usages, Stefanus Agus Haryono, Thung Ferdian, David Lo, Julia Lawall, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Due to the rise of AI applications, machine learning (ML) libraries, often written in Python, have become far more accessible. ML libraries tend to be updated periodically, which may deprecate existing APIs, making it necessary for application developers to update their usages. In this paper, we build a tool to automate deprecated API usage updates. We first present an empirical study to better understand how updates of deprecated ML API usages in Python can be done. The study involves a dataset of 112 deprecated APIs from Scikit-Learn, TensorFlow, and PyTorch. Guided by the findings of our empirical study, we propose …

Go to article

Learning And Evaluating Chinese Idiom Embeddings, Minghuan Tan, Jing Jiang Sep 2021

Learning And Evaluating Chinese Idiom Embeddings, Minghuan Tan, Jing Jiang

Research Collection School Of Computing and Information Systems

We study the task of learning and evaluating Chinese idiom embeddings. We first construct a new evaluation dataset that contains idiom synonyms and antonyms. Observing that existing Chinese word embedding methods may not be suitable for learning idiom embeddings, we further present a BERT-based method that directly learns embedding vectors for individual idioms. We empirically compare representative existing methods and our method. We find that our method substantially outperforms existing methods on the evaluation dataset we have constructed.

Go to article

Dynamic Heterogeneous Graph Embedding Via Heterogeneous Hawkes Process, Yugang Ji, Tianrui Jia, Yuan Fang, Chuan Shi Sep 2021

Dynamic Heterogeneous Graph Embedding Via Heterogeneous Hawkes Process, Yugang Ji, Tianrui Jia, Yuan Fang, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph embedding, aiming to learn low-dimensional representations of nodes while preserving valuable structure information, has played a key role in graph analysis and inference. However, most existing methods deal with static homogeneous topologies, while graphs in real-world scenarios are gradually generated with different-typed temporal events, containing abundant semantics and dynamics. Limited work has been done for embedding dynamic heterogeneous graphs since it is very challenging to model the complete formation process of heterogeneous events. In this paper, we propose a novel Heterogeneous Hawkes Process based dynamic Graph Embedding (HPGE) to handle this problem. HPGE effectively integrates the Hawkes process into …

Go to article

Orthogonal Inductive Matrix Completion, Antoine Ledent, Rrodrigo Alves, Marius Kloft Sep 2021

Orthogonal Inductive Matrix Completion, Antoine Ledent, Rrodrigo Alves, Marius Kloft

Research Collection School Of Computing and Information Systems

We propose orthogonal inductive matrix completion (OMIC), an interpretable approach to matrix completion based on a sum of multiple orthonormal side information terms, together with nuclear-norm regularization. The approach allows us to inject prior knowledge about the singular vectors of the ground-truth matrix. We optimize the approach by a provably converging algorithm, which optimizes all components of the model simultaneously. We study the generalization capabilities of our method in both the distribution-free setting and in the case where the sampling distribution admits uniform marginals, yielding learning guarantees that improve with the quality of the injected knowledge in both cases. As …

Go to article

A Learning And Optimization Framework For Collaborative Urban Delivery Problems With Alliances, Jingfeng Yang, Hoong Chuin Lau Sep 2021

A Learning And Optimization Framework For Collaborative Urban Delivery Problems With Alliances, Jingfeng Yang, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

The emergence of e-Commerce imposes a tremendous strain on urban logistics which in turn raises concerns on environmental sustainability if not performed efficiently. While large logistics service providers (LSPs) can perform fulfillment sustainably as they operate extensive logistic networks, last-mile logistics are typically performed by small LSPs who need to form alliances to reduce delivery costs and improve efficiency, and to compete with large players. In this paper, we consider a multi-alliance multi-depot pickup and delivery problem with time windows (MAD-PDPTW) and formulate it as a mixed-integer programming (MIP) model. To cope with large-scale problem instances, we propose a two-stage …

Go to article

Learning And Exploiting Shaped Reward Models For Large Scale Multiagent Rl, Arambam James Singh, Akshat Kumar, Hoong Chuin Lau Aug 2021

Learning And Exploiting Shaped Reward Models For Large Scale Multiagent Rl, Arambam James Singh, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Many real world systems involve interaction among large number of agents to achieve a common goal, for example, air traffic control. Several model-free RL algorithms have been proposed for such settings. A key limitation is that the empirical reward signal in model-free case is not very effective in addressing the multiagent credit assignment problem, which determines an agent's contribution to the team's success. This results in lower solution quality and high sample complexity. To address this, we contribute (a) an approach to learn a differentiable reward model for both continuous and discrete action setting by exploiting the collective nature of …

Go to article

Learning To Assign: Towards Fair Task Assignment In Large-Scale Ride Hailing, Dingyuan Shi, Yongxin Tong, Zimu Zhou, Bingchen Song, Weifeng Lv, Qiang Yang Aug 2021

Learning To Assign: Towards Fair Task Assignment In Large-Scale Ride Hailing, Dingyuan Shi, Yongxin Tong, Zimu Zhou, Bingchen Song, Weifeng Lv, Qiang Yang

Research Collection School Of Computing and Information Systems

Ride hailing is a widespread shared mobility application where the central issue is to assign taxi requests to drivers with various objectives. Despite extensive research on task assignment in ride hailing, the fairness of earnings among drivers is largely neglected. Pioneer studies on fair task assignment in ride hailing are ineffective and inefficient due to their myopic optimization perspective and timeconsuming assignment techniques. In this work, we propose LAF, an effective and efficient task assignment scheme that optimizes both utility and fairness. We adopt reinforcement learning to make assignments in a holistic manner and propose a set of acceleration techniques …

Go to article

Biasrv: Uncovering Biased Sentiment Predictions At Runtime, Zhou Yang, Muhammad Hilmi Asyrofi, David Lo Aug 2021

Biasrv: Uncovering Biased Sentiment Predictions At Runtime, Zhou Yang, Muhammad Hilmi Asyrofi, David Lo

Research Collection School Of Computing and Information Systems

Sentiment analysis (SA) systems, though widely applied in many domains, have been demonstrated to produce biased results. Some research works have been done in automatically generating test cases to reveal unfairness in SA systems, but the community still lacks tools that can monitor and uncover biased predictions at runtime. This paper fills this gap by proposing BiasRV, the first tool to raise an alarm when a deployed SA system makes a biased prediction on a given input text. To implement this feature, BiasRV dynamically extracts a template from an input text and from the template generates gender-discriminatory mutants (semanticallyequivalent texts …

Go to article

Learn To Intervene: An Adaptive Learning Policy For Restless Bandits In Application To Preventive Healthcare, Arpita Biswas, Gaurav Aggarwal, Pradeep Varakantham, Milind Tambe Aug 2021

Learn To Intervene: An Adaptive Learning Policy For Restless Bandits In Application To Preventive Healthcare, Arpita Biswas, Gaurav Aggarwal, Pradeep Varakantham, Milind Tambe

Research Collection School Of Computing and Information Systems

In many public health settings, it is important for patients to adhere to health programs, such as taking medications and periodic health checks. Unfortunately, beneficiaries may gradually disengage from such programs, which is detrimental to their health. A concrete example of gradual disengagement has been observed by an organization that carries out a free automated call-based program for spreading preventive care information among pregnant women. Many women stop picking up calls after being enrolled for a few months. To avoid such disengagements, it is important to provide timely interventions. Such interventions are often expensive and can be provided to only …

Go to article

Crossasr++: A Modular Differential Testing Framework For Automatic Speech Recognition, Muhammad Hilmi Asyrofi, Zhou Yang, David Lo Aug 2021

Crossasr++: A Modular Differential Testing Framework For Automatic Speech Recognition, Muhammad Hilmi Asyrofi, Zhou Yang, David Lo

Research Collection School Of Computing and Information Systems

Developers need to perform adequate testing to ensure the quality of Automatic Speech Recognition (ASR) systems. However, manually collecting required test cases is tedious and time-consuming. Our recent work proposes CrossASR, a differential testing method for ASR systems. This method first utilizes Text-to-Speech (TTS) to generate audios from texts automatically and then feed these audios into different ASR systems for cross-referencing to uncover failed test cases. It also leverages a failure estimator to find failing test cases more efficiently. Such a method is inherently self-improvable: the performance can increase by leveraging more advanced TTS and ASR systems. So, in this …

Go to article

Node-Wise Localization Of Graph Neural Networks, Zemin Liu, Yuan Fang, Chenghao Liu, Steven C.H. Hoi Aug 2021

Node-Wise Localization Of Graph Neural Networks, Zemin Liu, Yuan Fang, Chenghao Liu, Steven C.H. Hoi

Research Collection School Of Computing and Information Systems

Graph neural networks (GNNs) emerge as a powerful family of representation learning models on graphs. To derive node representations, they utilize a global model that recursively aggregates information from the neighboring nodes. However, different nodes reside at different parts of the graph in different local contexts, making their distributions vary across the graph. Ideally, how a node receives its neighborhood information should be a function of its local context, to diverge from the global GNN model shared by all nodes. To utilize node locality without overfitting, we propose a node-wise localization of GNNs by accounting for both global and local …

Go to article

Learning Interpretable Concept Groups In Cnns, Saurabh Varshneya, Antoine Ledent, Rob Vandermeulen, Yunwen Lei, Matthias Enders, Damian Borth, Marius Kloft Aug 2021

Learning Interpretable Concept Groups In Cnns, Saurabh Varshneya, Antoine Ledent, Rob Vandermeulen, Yunwen Lei, Matthias Enders, Damian Borth, Marius Kloft

Research Collection School Of Computing and Information Systems

We propose a novel training methodology---Concept Group Learning (CGL)---that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy that forces filters in the same group to be active in similar image regions for a given layer. We additionally use a regularizer to encourage a sparse weighting of the concept groups in each layer so that a few concept groups can have greater importance than others. We quantitatively evaluate CGL's model interpretability using standard interpretability evaluation …

Go to article

First Prev Next Last