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

Computer Sciences Commons™

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

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 2731 - 2760 of 8479

Full-Text Articles in Computer Sciences

Privacy-Preserving Proof Of Storage For The Pay-As-You-Go Business Model, Tong Wu, Guomin Yang, Yi Mu, Fuchun Guo, Robert H. Deng Jul 2021

Privacy-Preserving Proof Of Storage For The Pay-As-You-Go Business Model, Tong Wu, Guomin Yang, Yi Mu, Fuchun Guo, Robert H. Deng

Research Collection School Of Computing and Information Systems

Proof of Storage (PoS) enables a cloud storage provider to prove that a client's data is intact. However, existing PoS protocols are not designed for the pay-as-you-go business model in which payment is made based on both storage volume and duration. In this paper, we propose two PoS protocols suitable for the pay-as-you-go storage business model. The first is a time encapsulated Proof of Retrievability (PoR) protocol that ensures retrievability of the original file upon successful auditing by a client. Considering the large size of outsourced data, we then extend the protocol to a privacy-preserving public auditing protocol which allows …

Go to article

Order-Agnostic Cross Entropy For Non-Autoregressive Machine Translation, Cunxiao Du, Zhaopeng Tu, Jing Jiang Jul 2021

Order-Agnostic Cross Entropy For Non-Autoregressive Machine Translation, Cunxiao Du, Zhaopeng Tu, Jing Jiang

Research Collection School Of Computing and Information Systems

We propose a new training objective named orderagnostic cross entropy (OAXE) for fully nonautoregressive translation (NAT) models. OAXE improves the standard cross-entropy loss to ameliorate the effect of word reordering, which is a common source of the critical multimodality problem in NAT. Concretely, OAXE removes the penalty for word order errors, and computes the cross entropy loss based on the best possible alignment between model predictions and target tokens. Since the log loss is very sensitive to invalid references, we leverage cross entropy initialization and loss truncation to ensure the model focuses on a good part of the search space. …

Go to article

A Differentially Private Task Planning Framework For Spatial Crowdsourcing, Qian Tao, Yongxin Tong, Shuyuan Li, Yuxiang Zeng, Zimu Zhou, Ke Xu Jul 2021

A Differentially Private Task Planning Framework For Spatial Crowdsourcing, Qian Tao, Yongxin Tong, Shuyuan Li, Yuxiang Zeng, Zimu Zhou, Ke Xu

Research Collection School Of Computing and Information Systems

Spatial crowdsourcing has stimulated various new applications such as taxi calling and food delivery. A key enabler for these spatial crowdsourcing based applications is to plan routes for crowd workers to execute tasks given diverse requirements of workers and the spatial crowdsourcing platform. Despite extensive studies on task planning in spatial crowdsourcing, few have accounted for the location privacy of tasks, which may be misused by an untrustworthy platform. In this paper, we explore efficient task planning for workers while protecting the locations of tasks. Specifically, we define the Privacy-Preserving Task Planning (PPTP) problem, which aims at both total revenue …

Go to article

Self-Supervised Contrastive Learning For Code Retrieval And Summarization Via Semantic-Preserving Transformations, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang Jul 2021

Self-Supervised Contrastive Learning For Code Retrieval And Summarization Via Semantic-Preserving Transformations, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

We propose Corder, a self-supervised contrastive learning framework for source code model. Corder is designed to alleviate the need of labeled data for code retrieval and code summarization tasks. The pre-trained model of Corder can be used in two ways: (1) it can produce vector representation of code which can be applied to code retrieval tasks that do not have labeled data; (2) it can be used in a fine-tuning process for tasks that might still require label data such as code summarization. The key innovation is that we train the source code model by asking it to recognize similar …

Go to article

Optimization Planning For 3d Convnets, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei Jul 2021

Optimization Planning For 3d Convnets, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal "path" to automate the entire training. In this paper, we decompose the path into a series of training …

Go to article

A Coprocessor-Based Introspection Framework Via Intel Management Engine, Lei Zhou, Fengwei Zhang, Jidong Xiao, Kevin Leach, Westley Weimer, Xuhua Ding, Guojun Wang Jul 2021

A Coprocessor-Based Introspection Framework Via Intel Management Engine, Lei Zhou, Fengwei Zhang, Jidong Xiao, Kevin Leach, Westley Weimer, Xuhua Ding, Guojun Wang

Research Collection School Of Computing and Information Systems

During the past decade, virtualization-based (e.g., virtual machine introspection) and hardware-assisted approaches (e.g., x86 SMM and ARM TrustZone) have been used to defend against low-level malware such as rootkits. However, these approaches either require a large Trusted Computing Base (TCB) or they must share CPU time with the operating system, disrupting normal execution. In this article, we propose an introspection framework called NIGHTHAWK that transparently checks system integrity and monitor the runtime state of target system. NIGHTHAWK leverages the Intel Management Engine (IME), a co-processor that runs in isolation from the main CPU. By using the IME, our approach has …

Go to article

Dehumor: Visual Analytics For Decomposing Humor, Xingbo Wang, Yao Ming, Tongshuang Wu, Haipeng Zeng, Yong Wang, Huamin Qu Jul 2021

Dehumor: Visual Analytics For Decomposing Humor, Xingbo Wang, Yao Ming, Tongshuang Wu, Haipeng Zeng, Yong Wang, Huamin Qu

Research Collection School Of Computing and Information Systems

Despite being a critical communication skill, grasping humor is challenginga successful use of humor requires a mixture of both engaging content build-up and an appropriate vocal delivery (e.g., pause). Prior studies on computational humor emphasize the textual and audio features immediately next to the punchline, yet overlooking longer-term context setup. Moreover, the theories are usually too abstract for understanding each concrete humor snippet. To fill in the gap, we develop DeHumor, a visual analytical system for analyzing humorous behaviors in public speaking. To intuitively reveal the building blocks of each concrete example, DeHumor decomposes each humorous video into multimodal features …

Go to article

Claim: Curriculum Learning Policy For Influence Maximization In Unknown Social Networks, Dexun Li, Meghna Lowalekar, Pradeep Varakantham Jul 2021

Claim: Curriculum Learning Policy For Influence Maximization In Unknown Social Networks, Dexun Li, Meghna Lowalekar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Influence maximization is the problem of finding a small subset of nodes in a network that can maximize the diffusion of information. Recently, it has also found application in HIV prevention, substance abuse prevention, micro-finance adoption, etc., where the goal is to identify the set of peer leaders in a real-world physical social network who can disseminate information to a large group of people. Unlike online social networks, real-world networks are not completely known, and collecting information about the network is costly as it involves surveying multiple people. In this paper, we focus on this problem of network discovery for …

Go to article

A Mean-Field Markov Decision Process Model For Spatial-Temporal Subsidies In Ride-Sourcing Markets, Zheng Zhu, Jintao Ke, Hai Wang Jul 2021

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 …

Go to article

Integrated Framework For Developing Instructional Videos For Foundational Computing Courses, Kyong Jin Shim, Gottipati Swapna, Yi Meng Lau Jul 2021

Integrated Framework For Developing Instructional Videos For Foundational Computing Courses, Kyong Jin Shim, Gottipati Swapna, Yi Meng Lau

Research Collection School Of Computing and Information Systems

Instructional videos are widely used in higher education due to their effectiveness and flexibility of personalized learning features. Computing courses usually focuses on programming, user interface design, server connectivity, data storage, and architecture, among others. The design of instructional videos varies in not only the course content but also the style of content creation. We propose an integrated framework, Computing Videos Design Framework (CVDF), for designing and developing instructional videos for computing courses. CVDF combines the cognitive skills from Bloom’s taxonomy, video design principles, and course learning outcomes for designing different types of instructional videos. We apply the framework to …

Go to article

Meta-Inductive Node Classification Across Graphs, Zhihao Wen, Yuan Fang, Zemin Liu Jul 2021

Meta-Inductive Node Classification Across Graphs, Zhihao Wen, Yuan Fang, Zemin Liu

Research Collection School Of Computing and Information Systems

Semi-supervised node classification on graphs is an important research problem, with many real-world applications in information retrieval such as content classification on a social network and query intent classification on an e-commerce query graph. While traditional approaches are largely transductive, recent graph neural networks (GNNs) integrate node features with network structures, thus enabling inductive node classification models that can be applied to new nodes or even new graphs in the same feature space. However, inter-graph differences still exist across graphs within the same domain. Thus, training just one global model (e.g., a state-of-the-art GNN) to handle all new graphs, whilst …

Go to article

Rnnrepair: Automatic Rnn Repair Via Model-Based Analysis, Xiaofei Xie, Wenbo Guo, Lei Ma, Wei Le, Jian Wang, Lingjun Zhou, Yang Liu, Xinyu Xing Jul 2021

Rnnrepair: Automatic Rnn Repair Via Model-Based Analysis, Xiaofei Xie, Wenbo Guo, Lei Ma, Wei Le, Jian Wang, Lingjun Zhou, Yang Liu, Xinyu Xing

Research Collection School Of Computing and Information Systems

Deep neural networks are vulnerable to adversarial attacks. Due to their black-box nature, it is rather challenging to interpret and properly repair these incorrect behaviors. This paper focuses on interpreting and repairing the incorrect behaviors of Recurrent Neural Networks (RNNs). We propose a lightweight model-based approach (RNNRepair) to help understand and repair incorrect behaviors of an RNN. Specifically, we build an influence model to characterize the stateful and statistical behaviors of an RNN over all the training data and to perform the influence analysis for the errors. Compared with the existing techniques on influence function, our method can efficiently estimate …

Go to article

Vibransee: Enabling Simultaneous Visible Light Communication And Sensing, Ila Nitin Gokarn, Archan Misra Jul 2021

Vibransee: Enabling Simultaneous Visible Light Communication And Sensing, Ila Nitin Gokarn, Archan Misra

Research Collection School Of Computing and Information Systems

Driven by the ubiquitous proliferation of low-cost LED luminaires, visible light communication (VLC) has been established as a high-speed communications technology based on the high-frequency modulation of an optical source. In parallel, Visible Light Sensing (VLS) has recently demonstrated how vision-based at-a-distance sensing of mechanical vibrations (e.g., of factory equipment) can be performed using high frequency optical strobing. However, to date, exemplars of VLC and VLS have been explored in isolation, without consideration of their mutual dependencies. In this work, we explore whether and how high-throughput VLC and high-coverage VLS can be simultaneously supported. We first demonstrate the existence of …

Go to article

Paying Attention To Video Object Pattern Understanding, Wenguan Wang, Jianbing Shen, Xiankai Lu, Steven C. H. Hoi, Haibin Ling Jul 2021

Paying Attention To Video Object Pattern Understanding, Wenguan Wang, Jianbing Shen, Xiankai Lu, Steven C. H. Hoi, Haibin Ling

Research Collection School Of Computing and Information Systems

This paper conducts a systematic study on the role of visual attention in video object pattern understanding. By elaborately annotating three popular video segmentation datasets (DAVIS) with dynamic eye-tracking data in the unsupervised video object segmentation (UVOS) setting. For the first time, we quantitatively verified the high consistency of visual attention behavior among human observers, and found strong correlation between human attention and explicit primary object judgments during dynamic, task-driven viewing. Such novel observations provide an in-depth insight of the underlying rationale behind video object pattens. Inspired by these findings, we decouple UVOS into two sub-tasks: UVOS-driven Dynamic Visual Attention …

Go to article

Efficient White-Box Fairness Testing Through Gradient Search, Lingfeng Zhang, Yueling Zhang, Min Zhang Jul 2021

Efficient White-Box Fairness Testing Through Gradient Search, Lingfeng Zhang, Yueling Zhang, Min Zhang

Research Collection School Of Computing and Information Systems

Deep learning (DL) systems are increasingly deployed for autonomous decision-making in a wide range of applications. Apart from the robustness and safety, fairness is also an important property that a well-designed DL system should have. To evaluate and improve individual fairness of a model, systematic test case generation for identifying individual discriminatory instances in the input space is essential. In this paper, we propose a framework EIDIG for efficiently discovering individual fairness violation. Our technique combines a global generation phase for rapidly generating a set of diverse discriminatory seeds with a local generation phase for generating as many individual discriminatory …

Go to article

Oesense: Employing Occlusion Effect For In-Ear Human Sensing, Dong Ma, Andrea Ferlini, Cecilia Mascolo Jul 2021

Oesense: Employing Occlusion Effect For In-Ear Human Sensing, Dong Ma, Andrea Ferlini, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Smart earbuds are recognized as a new wearable platform for personal-scale human motion sensing. However, due to the interference from head movement or background noise, commonly-used modalities (e.g. accelerometer and microphone) fail to reliably detect both intense and light motions. To obviate this, we propose OESense, an acoustic-based in-ear system for general human motion sensing. The core idea behind OESense is the joint use of the occlusion effect (i.e., the enhancement of low-frequency components of bone-conducted sounds in an occluded ear canal) and inward-facing microphone, which naturally boosts the sensing signal and suppresses external interference. We prototype OESense as an …

Go to article

Bias Field Poses A Threat To Dnn-Based X-Ray Recognition, Bingyu Tian, Qing Guo, Felix Juefei-Xu, Wen Le Chan, Yupeng Cheng, Xiaohong Li, Xiaofei Xie, Shengchao Qin Jul 2021

Bias Field Poses A Threat To Dnn-Based X-Ray Recognition, Bingyu Tian, Qing Guo, Felix Juefei-Xu, Wen Le Chan, Yupeng Cheng, Xiaohong Li, Xiaofei Xie, Shengchao Qin

Research Collection School Of Computing and Information Systems

Chest X-ray plays a key role in screening and diagnosis of many lung diseases including the COVID-19. Many works construct deep neural networks (DNNs) for chest X-ray images to realize automated and efficient diagnosis of lung diseases. However, bias field caused by the improper medical image acquisition process widely exists in the chest X-ray images while the robustness of DNNs to the bias field is rarely explored, posing a threat to the X-ray-based automated diagnosis system. In this paper, we study this problem based on the adversarial attack and propose a brand new attack, i.e., adversarial bias field attack where …

Go to article

An Efficient Transformer-Based Model For Vietnamese Punctuation Prediction, Hieu Tran, Cuong V. Dinh, Hong Quang Pham, Binh T. Nguyen Jul 2021

An Efficient Transformer-Based Model For Vietnamese Punctuation Prediction, Hieu Tran, Cuong V. Dinh, Hong Quang Pham, Binh T. Nguyen

Research Collection School Of Computing and Information Systems

In both formal and informal texts, missing punctuation marks make the texts confusing and challenging to read. This paper aims to conduct exhaustive experiments to investigate the benefits of the pre-trained Transformer-based models on two Vietnamese punctuation datasets. The experimental results show our models can achieve encouraging results, and adding Bi-LSTM or/and CRF layers on top of the proposed models can also boost model performance. Finally, our best model can significantly bypass state-of-the-art approaches on both the novel and news datasets for the Vietnamese language. It can gain the corresponding performance up to 21.45%21.45% and 18.27%18.27% in the overall F1-scores.

Go to article

Stealing Deep Reinforcement Learning Models For Fun And Profit, Kangjie Chen, Shangwei Guo, Tianwei Zhang, Xiaofei Xie, Yang Liu Jul 2021

Stealing Deep Reinforcement Learning Models For Fun And Profit, Kangjie Chen, Shangwei Guo, Tianwei Zhang, Xiaofei Xie, Yang Liu

Research Collection School Of Computing and Information Systems

This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only from its interaction with the environment. Model extraction attacks against supervised Deep Learning models have been widely studied. However, those techniques cannot be applied to the reinforcement learning scenario due to DRL models' high complexity, stochasticity and limited observable information. We propose a novel methodology to overcome the above challenges. The key insight of our approach is that the process of DRL model extraction is equivalent to imitation learning, a well-established solution to learn …

Go to article

Recent Advances In Network-Based Methods For Disease Gene Prediction, Sezin Kircali Ata, Min Wu, Yuan Fang, Ou-Yang Le, Chee Keong Kwoh, Xiao-Li Li Jul 2021

Recent Advances In Network-Based Methods For Disease Gene Prediction, Sezin Kircali Ata, Min Wu, Yuan Fang, Ou-Yang Le, Chee Keong Kwoh, Xiao-Li Li

Research Collection School Of Computing and Information Systems

Disease-gene association through Genome-wide association study (GWAS) is an arduous task for researchers. Investigating single nucleotide polymorphisms (SNPs) that correlate with specific diseases needs statistical analysis of associations. Considering the huge number of possible mutations, in addition to its high cost, another important drawback of GWAS analysis is the large number of false-positives. Thus, researchers search for more evidence to cross-check their results through different sources. To provide the researchers with alternative and complementary low-cost disease-gene association evidence, computational approaches come into play. Since molecular networks are able to capture complex interplay among molecules in diseases, they become one of …

Go to article

Exploring Cross-Modality Utilization In Recommender Systems, Quoc Tuan Truong, Aghiles Salah, Thanh-Binh Tran, Jingyao Guo, Hady W. Lauw Jul 2021

Exploring Cross-Modality Utilization In Recommender Systems, Quoc Tuan Truong, Aghiles Salah, Thanh-Binh Tran, Jingyao Guo, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Multimodal recommender systems alleviate the sparsity of historical user-item interactions. They are commonly catalogued based on the type of auxiliary data (modality) they leverage, such as preference data plus user-network (social), user/item texts (textual), or item images (visual) respectively. One consequence of this categorization is the tendency for virtual walls to arise between modalities. For instance, a study involving images would compare to only baselines ostensibly designed for images. However, a closer look at existing models' statistical assumptions about any one modality would reveal that many could work just as well with other modalities. Therefore, we pursue a systematic investigation …

Go to article

An Adaptive Large Neighborhood Search For The Green Mixed Fleet Vehicle Routing Problem With Realistic Energy Consumption And Partial Recharges, Vincent F. Yu, Panca Jodiawan, Aldy Gunawan Jul 2021

An Adaptive Large Neighborhood Search For The Green Mixed Fleet Vehicle Routing Problem With Realistic Energy Consumption And Partial Recharges, Vincent F. Yu, Panca Jodiawan, Aldy Gunawan

Research Collection School Of Computing and Information Systems

This study addresses a variant of the Electric Vehicle Routing Problem with Mixed Fleet, named as the Green Mixed Fleet Vehicle Routing Problem with Realistic Energy Consumption and Partial Recharges. This problem contains three important characteristics — realistic energy consumption, partial recharging policy, and carbon emissions. An adaptive Large Neighborhood Search heuristic is developed for the problem. Experimental results show that the proposed ALNS finds optimal solutions for most small-scale benchmark instances in a significantly faster computational time compared to the performance of CPLEX solver. Moreover, it obtains high quality solutions for all medium- and large-scale instances under a reasonable …

Go to article

The Multi-Vehicle Cycle Inventory Routing Problem: Formulation And A Metaheuristic Approach, Vincent F. Yu, Audrey Tedja Widjaja, Aldy Gunawan, Pieter Vansteenwegen Jul 2021

The Multi-Vehicle Cycle Inventory Routing Problem: Formulation And A Metaheuristic Approach, Vincent F. Yu, Audrey Tedja Widjaja, Aldy Gunawan, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

This paper presents a new variant of the Multi-Vehicle Cyclic Inventory Routing Problem (MV-CIRP) which aims to determine a subset of customers to be visited, the appropriate number of vehicles used, and the corresponding cycle time and route sequence, such that the total cost (e.g. transportation, inventory, and rewards) is minimized. The MV-CIRP is formulated as a mixed-integer nonlinear programming model. We propose a Simulated Annealing (SA) based algorithm to solve the problem. SA is first tested on the available benchmark Single-Vehicle CIRP (SV-CIRP) instances and compared to the state-of-the-art algorithms. SA is then tested on the benchmark MV-CIRP instances …

Go to article

On The Generalizability Of Neural Program Models With Respect To Semantic-Preserving Program Transformations, Md Rafiqul Islam Rabin, Nghi D. Q. Bui, Ke Wang, Yijun Yu, Lingxiao Jiang Jul 2021

On The Generalizability Of Neural Program Models With Respect To Semantic-Preserving Program Transformations, Md Rafiqul Islam Rabin, Nghi D. Q. Bui, Ke Wang, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Context: With the prevalence of publicly available source code repositories to train deep neural network models, neural program models can do well in source code analysis tasks such as predicting method names in given programs that cannot be easily done by traditional program analysis techniques. Although such neural program models have been tested on various existing datasets, the extent to which they generalize to unforeseen source code is largely unknown. Objective: Since it is very challenging to test neural program models on all unforeseen programs, in this paper, we propose to evaluate the generalizability of neural program models with respect …

Go to article

Make It Easy: An Effective End-To-End Entity Alignment Framework, Congcong Ge, Xiaoze Liu, Lu Chen Chen, Baihua Zheng, Yunjun Gao Jul 2021

Make It Easy: An Effective End-To-End Entity Alignment Framework, Congcong Ge, Xiaoze Liu, Lu Chen Chen, Baihua Zheng, Yunjun Gao

Research Collection School Of Computing and Information Systems

Entity alignment (EA) is a prerequisite for enlarging the coverage of a unified knowledge graph. Previous EA approaches either restrain the performance due to inadequate information utilization or need labor-intensive pre-processing to get external or reliable information to perform the EA task. This paper proposes EASY, an effective end-to-end EA framework, which is able to (i) remove the labor-intensive pre-processing by fully discovering the name information provided by the entities themselves; and (ii) jointly fuse the features captured by the names of entities and the structural information of the graph to improve the EA results. Specifically, EASY first introduces NEAP, …

Go to article

Attack As Defense: Characterizing Adversarial Examples Using Robustness, Zhe Zhao, Guangke Chen, Jingyi Wang, Yiwei Yang, Fu Song, Jun Sun Jul 2021

Attack As Defense: Characterizing Adversarial Examples Using Robustness, Zhe Zhao, Guangke Chen, Jingyi Wang, Yiwei Yang, Fu Song, Jun Sun

Research Collection School Of Computing and Information Systems

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have been proposed to improve robustness of deep learning software, many of them are ineffective against adaptive attacks. In this work, we propose a novel characterization to distinguish adversarial examples from benign ones based on the observation that adversarial examples are significantly less robust than benign ones. As existing robustness measurement does not scale to large networks, we propose a novel defense framework, named attack …

Go to article

Frameaxis: Characterizing Microframe Bias And Intensity With Word Embedding, Haewoon Kwak, Jisun An, Elise Jing Jing, Yong-Yeol Ahn Jul 2021

Frameaxis: Characterizing Microframe Bias And Intensity With Word Embedding, Haewoon Kwak, Jisun An, Elise Jing Jing, Yong-Yeol Ahn

Research Collection School Of Computing and Information Systems

Framing is a process of emphasizing a certain aspect of an issue over the others, nudging readers or listeners towards different positions on the issue even without making a biased argument. Here, we propose FrameAxis, a method for characterizing documents by identifying the most relevant semantic axes (“microframes”) that are overrepresented in the text using word embedding. Our unsupervised approach can be readily applied to large datasets because it does not require manual annotations. It can also provide nuanced insights by considering a rich set of semantic axes. FrameAxis is designed to quantitatively tease out two important dimensions of how …

Go to article

How Important Is The Train-Validation Split In Meta-Learning?, Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, D. Jason Lee, Sham Kakade, Huan Wang, Caiming Xiong Jul 2021

How Important Is The Train-Validation Split In Meta-Learning?, Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, D. Jason Lee, Sham Kakade, Huan Wang, Caiming Xiong

Research Collection School Of Computing and Information Systems

Meta-learning aims to perform fast adaptation on a new task through learning a “prior” from multiple existing tasks. A common practice in meta-learning is to perform a train-validation split (train-val method) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split. Despite its prevalence, the importance of the train-validation split is not well understood either in theory or in practice, particularly in comparison to the more direct train-train method, which uses all the pertask data for both training and evaluation. We provide a detailed theoretical study on whether …

Go to article

Task Similarity Aware Meta Learning: Theory-Inspired Improvement On Maml, Pan Zhou, Yingtian Zpu, Xiaotong Yuan, Jiashi Feng, Caiming Xiong, Steven C. H. Hoi Jul 2021

Task Similarity Aware Meta Learning: Theory-Inspired Improvement On Maml, Pan Zhou, Yingtian Zpu, Xiaotong Yuan, Jiashi Feng, Caiming Xiong, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Few-shot learning ability is heavily desired for machine intelligence. By meta-learning a model initialization from training tasks with fast adaptation ability to new tasks, model-agnostic meta-learning (MAML) has achieved remarkable success in a number of few-shot learning applications. However, theoretical understandings on the learning ability of MAML remain absent yet, hindering developing new and more advanced meta learning methods in a principled way. In this work, we solve this problem by theoretically justifying the fast adaptation capability of MAML when applied to new tasks. Specifically, we prove that the learnt meta-initialization can benefit the fast adaptation to new tasks with …

Go to article

Unified Conversational Recommendation Policy Learning Via Graph-Based Reinforcement Learning, Yang Deng, Yaliang Li, Fei Sun, Bolin Ding, Wai Lam Jul 2021

Unified Conversational Recommendation Policy Learning Via Graph-Based Reinforcement Learning, Yang Deng, Yaliang Li, Fei Sun, Bolin Ding, Wai Lam

Research Collection School Of Computing and Information Systems

Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to learn conversational recommendation policies to decide what attributes to ask, which items to recommend, and when to ask or recommend, at each conversation turn. However, existing methods mainly target at solving one or two of these three decision-making problems in CRS with separated conversation and recommendation components, which restrict the scalability and generality of CRS and fall short of preserving a stable training procedure. In the light of these challenges, we propose …

Go to article

First Prev Next Last