arXiv subjects

Qiang Yang

Publications and source records attributed to Qiang Yang.

At least 163 records · Page 9Linked to original sources

arXiv2021

Generalised quasilinear approximations of turbulent channel flow: Part 2. Spanwise scale interactions

Continuing from Part 1 (Hernández \emph{et al.}, \emph{arXiv:2108.12395}, 2021), a generalized quasilinear (GQL) approximation is studied in turbulent channel flow using a flow decomposition defined with spanwise Fourier modes: the flow is decomposed into a set of low-wavenumber spanwise Fourier modes and the rest high-wavenumber modes. This decomposition leads to the nonlinear low-wavenumber group that supports the self-sustaining process within the given integral length scales, whereas the linearised high-wavenumber group is not able to do so, unlike the GQL models in Part 1 which place a minimal mathematical description for the self-sustaining process across all integral scales. Despite the important physical difference, it is shown that the GQL models in this study share some similarities with those in Part 1: i.e. the reduced multi-scale behaviour and anisotropic turbulent fluctuations. Furthermore, despite not being able to support the self-sustaining process in the high-wavenumber group, the GQL models in the present study are found to reproduce some key statistical features in the high-wavenumber group solely through the `scattering' mechanism proposed by previous studies. Finally, using the nature of the GQL approximation, a set of numerical experiments suppressing certain triadic nonlinear interactions are further carried out. This unveils some key roles played by the certain types of triadic interactions including energy cascade and inverse energy transfer in the near-wall region. In particular, the inhibition of inverse energy transfer in the spanwise direction leads to suppression of the near-wall positive turbulent transport at large scales.

physics.flu-dyn↗

arXiv2021

SportsSum2.0: Generating High-Quality Sports News from Live Text Commentary

Sports game summarization aims to generate news articles from live text commentaries. A recent state-of-the-art work, SportsSum, not only constructs a large benchmark dataset, but also proposes a two-step framework. Despite its great contributions, the work has three main drawbacks: 1) the noise existed in SportsSum dataset degrades the summarization performance; 2) the neglect of lexical overlap between news and commentaries results in low-quality pseudo-labeling algorithm; 3) the usage of directly concatenating rewritten sentences to form news limits its practicability. In this paper, we publish a new benchmark dataset SportsSum2.0, together with a modified summarization framework. In particular, to obtain a clean dataset, we employ crowd workers to manually clean the original dataset. Moreover, the degree of lexical overlap is incorporated into the generation of pseudo labels. Further, we introduce a reranker-enhanced summarizer to take into account the fluency and expressiveness of the summarized news. Extensive experiments show that our model outperforms the state-of-the-art baseline.

cs.CL↗

arXiv2021

Federated Deep Learning with Bayesian Privacy

Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. For Federated Learning of Deep Neural Network with billions of model parameters, existing privacy-preserving solutions are unsatisfactory. Homomorphic encryption (HE) based methods provide secure privacy protections but suffer from extremely high computational and communication overheads rendering it almost useless in practice . Deep learning with Differential Privacy (DP) was implemented as a practical learning algorithm at a manageable cost in complexity. However, DP is vulnerable to aggressive Bayesian restoration attacks as disclosed in the literature and demonstrated in experimental results of this work. To address the aforementioned perplexity, we propose a novel Bayesian Privacy (BP) framework which enables Bayesian restoration attacks to be formulated as the probability of reconstructing private data from observed public information. Specifically, the proposed BP framework accurately quantifies privacy loss by Kullback-Leibler (KL) Divergence between the prior distribution about the privacy data and the posterior distribution of restoration private data conditioning on exposed information}. To our best knowledge, this Bayesian Privacy analysis is the first to provides theoretical justification of secure privacy-preserving capabilities against Bayesian restoration attacks. As a concrete use case, we demonstrate that a novel federated deep learning method using private passport layers is able to simultaneously achieve high model performance, privacy-preserving capability and low computational complexity. Theoretical analysis is in accordance with empirical measurements of information leakage extensively experimented with a variety of DNN networks on image classification MNIST, CIFAR10, and CIFAR100 datasets.

cs.LG↗

arXiv2021

Graph Random Neural Network for Semi-Supervised Learning on Graphs

We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, non-robustness, and weak-generalization when labeled nodes are scarce. In this paper, we propose a simple yet effective framework -- GRAPH RANDOM NEURAL NETWORKS (GRAND) -- to address these issues. In GRAND, we first design a random propagation strategy to perform graph data augmentation. Then we leverage consistency regularization to optimize the prediction consistency of unlabeled nodes across different data augmentations. Extensive experiments on graph benchmark datasets suggest that GRAND significantly outperforms state-of-the-art GNN baselines on semi-supervised node classification. Finally, we show that GRAND mitigates the issues of over-smoothing and non-robustness, exhibiting better generalization behavior than existing GNNs. The source code of GRAND is publicly available at https://github.com/Grand20/grand.

cs.LG↗

arXiv2021

QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction

We study the problem of query attribute value extraction, which aims to identify named entities from user queries as diverse surface form attribute values and afterward transform them into formally canonical forms. Such a problem consists of two phases: {named entity recognition (NER)} and {attribute value normalization (AVN)}. However, existing works only focus on the NER phase but neglect equally important AVN. To bridge this gap, this paper proposes a unified query attribute value extraction system in e-commerce search named QUEACO, which involves both two phases. Moreover, by leveraging large-scale weakly-labeled behavior data, we further improve the extraction performance with less supervision cost. Specifically, for the NER phase, QUEACO adopts a novel teacher-student network, where a teacher network that is trained on the strongly-labeled data generates pseudo-labels to refine the weakly-labeled data for training a student network. Meanwhile, the teacher network can be dynamically adapted by the feedback of the student's performance on strongly-labeled data to maximally denoise the noisy supervisions from the weak labels. For the AVN phase, we also leverage the weakly-labeled query-to-attribute behavior data to normalize surface form attribute values from queries into canonical forms from products. Extensive experiments on a real-world large-scale E-commerce dataset demonstrate the effectiveness of QUEACO.

cs.CL↗

arXiv2021

Protect, Show, Attend and Tell: Empowering Image Captioning Models with Ownership Protection

By and large, existing Intellectual Property (IP) protection on deep neural networks typically i) focus on image classification task only, and ii) follow a standard digital watermarking framework that was conventionally used to protect the ownership of multimedia and video content. This paper demonstrates that the current digital watermarking framework is insufficient to protect image captioning tasks that are often regarded as one of the frontiers AI problems. As a remedy, this paper studies and proposes two different embedding schemes in the hidden memory state of a recurrent neural network to protect the image captioning model. From empirical points, we prove that a forged key will yield an unusable image captioning model, defeating the purpose of infringement. To the best of our knowledge, this work is the first to propose ownership protection on image captioning task. Also, extensive experiments show that the proposed method does not compromise the original image captioning performance on all common captioning metrics on Flickr30k and MS-COCO datasets, and at the same time it is able to withstand both removal and ambiguity attacks. Code is available at https://github.com/jianhanlim/ipr-imagecaptioning

cs.CV↗

arXiv2021

Generalised quasilinear approximations of turbulent channel flow: Part 1. Streamwise nonlinear energy transfer

A generalised quasilinear (GQL) approximation (Marston \emph{et al.}, \emph{Phys. Rev. Lett.}, vol. 116, 104502, 2016) is applied to turbulent channel flow at $Re_τ\simeq 1700$ ($Re_τ$ is the friction Reynolds number), with emphasis on the energy transfer in the streamwise wavenumber space. The flow is decomposed into low and high streamwise wavenumber groups, the former of which is solved by considering the full nonlinear equations whereas the latter is obtained from the linearised equations around the former. The performance of the GQL approximation is subsequently compared with that of a QL model (Thomas \emph{et al.}, \emph{Phys. Fluids.}, vol. 26, no. 10, 105112, 2014), in which the low-wavenumber group only contains zero streamwise wavenumber. It is found that the QL model exhibits a considerably reduced multi-scale behaviour at the given moderately high Reynolds number. This is improved significantly by the GQL approximation which incorporates only a few more streamwise Fourier modes into the low-wavenumber group, and it reasonably well recovers the distance-from-the-wall scaling in the turbulence statistics and spectra. Finally, it is proposed that the energy transfer from the low to the high-wavenumber group in the GQL approximation, referred to as the `scattering' mechanism, depends on the neutrally stable leading Lyapunov spectrum of the linearised equations for the high wavenumber group. In particular, it is shown that if the threshold wavenumber distinguishing the two groups is sufficiently high, the scattering mechanism can completely be absent due to the linear nature of the equations for the high-wavenumber group.

physics.flu-dyn↗

arXiv2021

Data science and AI in FinTech: An overview

Financial technology (FinTech) has been playing an increasingly critical role in driving modern economies, society, technology, and many other areas. Smart FinTech is the new-generation FinTech, largely inspired and empowered by data science and new-generation AI and (DSAI) techniques. Smart FinTech synthesizes broad DSAI and transforms finance and economies to drive intelligent, automated, whole-of-business and personalized economic and financial businesses, services and systems. The research on data science and AI in FinTech involves many latest progress made in smart FinTech for BankingTech, TradeTech, LendTech, InsurTech, WealthTech, PayTech, RiskTech, cryptocurrencies, and blockchain, and the DSAI techniques including complex system methods, quantitative methods, intelligent interactions, recognition and responses, data analytics, deep learning, federated learning, privacy-preserving processing, augmentation, optimization, and system intelligence enhancement. Here, we present a highly dense research overview of smart financial businesses and their challenges, the smart FinTech ecosystem, the DSAI techniques to enable smart FinTech, and some research directions of smart FinTech futures to the DSAI communities.

q-fin.GN↗

arXiv2021

SecureBoost: A Lossless Federated Learning Framework

The protection of user privacy is an important concern in machine learning, as evidenced by the rolling out of the General Data Protection Regulation (GDPR) in the European Union (EU) in May 2018. The GDPR is designed to give users more control over their personal data, which motivates us to explore machine learning frameworks for data sharing that do not violate user privacy. To meet this goal, in this paper, we propose a novel lossless privacy-preserving tree-boosting system known as SecureBoost in the setting of federated learning. SecureBoost first conducts entity alignment under a privacy-preserving protocol and then constructs boosting trees across multiple parties with a carefully designed encryption strategy. This federated learning system allows the learning process to be jointly conducted over multiple parties with common user samples but different feature sets, which corresponds to a vertically partitioned data set. An advantage of SecureBoost is that it provides the same level of accuracy as the non-privacy-preserving approach while at the same time, reveals no information of each private data provider. We show that the SecureBoost framework is as accurate as other non-federated gradient tree-boosting algorithms that require centralized data and thus it is highly scalable and practical for industrial applications such as credit risk analysis. To this end, we discuss information leakage during the protocol execution and propose ways to provably reduce it.

cs.LG↗

arXiv2021

A Survey on Multi-Task Learning

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach as well as discussing the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, we review online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works in this paper. Finally, we present theoretical analyses and discuss several future directions for MTL.

cs.LG↗

arXiv2021

Ternary Hashing

This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the state-of-the-art binary hashing counterparts. Two kinds of axiomatic ternary logic, Kleene logic and Łukasiewicz logic are adopted to calculate the Ternary Hamming Distance (THD) for both the learning/encoding and testing/querying phases. Our work demonstrates that, with an efficient implementation of ternary logic on standard binary machines, the proposed ternary hashing is compared favorably to the binary hashing methods with consistent improvements of retrieval mean average precision (mAP) ranging from 1\% to 5.9\% as shown in CIFAR10, NUS-WIDE and ImageNet100 datasets.

cs.AI↗

arXiv2021

Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

cs.LG↗

arXiv2021

Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack

Ever since Machine Learning as a Service (MLaaS) emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties. To the best of our knowledge, one of the prominent deep learning models - Generative Adversarial Networks (GANs) which has been widely used to create photorealistic image are totally unprotected despite the existence of pioneering IPR protection methodology for Convolutional Neural Networks (CNNs). This paper therefore presents a complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs. Empirically, we show that the proposed method does not compromise the original GANs performance (i.e. image generation, image super-resolution, style transfer), and at the same time, it is able to withstand both removal and ambiguity attacks against embedded watermarks.

cs.CR↗

arXiv2021

Self-supervised Cross-silo Federated Neural Architecture Search

Federated Learning (FL) provides both model performance and data privacy for machine learning tasks where samples or features are distributed among different parties. In the training process of FL, no party has a global view of data distributions or model architectures of other parties. Thus the manually-designed architectures may not be optimal. In the past, Neural Architecture Search (NAS) has been applied to FL to address this critical issue. However, existing Federated NAS approaches require prohibitive communication and computation effort, as well as the availability of high-quality labels. In this work, we present Self-supervised Vertical Federated Neural Architecture Search (SS-VFNAS) for automating FL where participants hold feature-partitioned data, a common cross-silo scenario called Vertical Federated Learning (VFL). In the proposed framework, each party first conducts NAS using self-supervised approach to find a local optimal architecture with its own data. Then, parties collaboratively improve the local optimal architecture in a VFL framework with supervision. We demonstrate experimentally that our approach has superior performance, communication efficiency and privacy compared to Federated NAS and is capable of generating high-performance and highly-transferable heterogeneous architectures even with insufficient overlapping samples, providing automation for those parties without deep learning expertise.

cs.LG↗

arXiv2021

A Game-theoretic Approach Towards Collaborative Coded Computation Offloading

Coded distributed computing (CDC) has emerged as a promising approach because it enables computation tasks to be carried out in a distributed manner while mitigating straggler effects, which often account for the long overall completion times. Specifically, by using polynomial codes, computed results from only a subset of edge servers can be used to reconstruct the final result. However, incentive issues have not been studied systematically for the edge servers to complete the CDC tasks. In this paper, we propose a tractable two-level game-theoretic approach to incentivize the edge servers to complete the CDC tasks. Specifically, in the lower level, a hedonic coalition formation game is formulated where the edge servers share their resources within their coalitions. By forming coalitions, the edge servers have more Central Processing Unit (CPU) power to complete the computation tasks. In the upper level, given the CPU power of the coalitions of edge servers, an all-pay auction is designed to incentivize the edge servers to participate in the CDC tasks. In the all-pay auction, the bids of the edge servers are represented by the allocation of their CPU power to the CDC tasks. The all-pay auction is designed to maximize the utility of the cloud server by determining the allocation of rewards to the winners. Simulation results show that the edge servers are incentivized to allocate more CPU power when multiple rewards are offered, i.e., there are multiple winners, instead of rewarding only the edge server with the largest CPU power allocation. Besides, the utility of the cloud server is maximized when it offers multiple homogeneous rewards, instead of heterogeneous rewards.

cs.GT↗

arXiv2021

TrNews: Heterogeneous User-Interest Transfer Learning for News Recommendation

We investigate how to solve the cross-corpus news recommendation for unseen users in the future. This is a problem where traditional content-based recommendation techniques often fail. Luckily, in real-world recommendation services, some publisher (e.g., Daily news) may have accumulated a large corpus with lots of consumers which can be used for a newly deployed publisher (e.g., Political news). To take advantage of the existing corpus, we propose a transfer learning model (dubbed as TrNews) for news recommendation to transfer the knowledge from a source corpus to a target corpus. To tackle the heterogeneity of different user interests and of different word distributions across corpora, we design a translator-based transfer-learning strategy to learn a representation mapping between source and target corpora. The learned translator can be used to generate representations for unseen users in the future. We show through experiments on real-world datasets that TrNews is better than various baselines in terms of four metrics. We also show that our translator is effective among existing transfer strategies.

cs.IR↗

arXiv2021

Real-World Image Datasets for Federated Learning

Federated learning is a new machine learning paradigm which allows data parties to build machine learning models collaboratively while keeping their data secure and private. While research efforts on federated learning have been growing tremendously in the past two years, most existing works still depend on pre-existing public datasets and artificial partitions to simulate data federations due to the lack of high-quality labeled data generated from real-world edge applications. Consequently, advances on benchmark and model evaluations for federated learning have been lagging behind. In this paper, we introduce a real-world image dataset. The dataset contains more than 900 images generated from 26 street cameras and 7 object categories annotated with detailed bounding box. The data distribution is non-IID and unbalanced, reflecting the characteristic real-world federated learning scenarios. Based on this dataset, we implemented two mainstream object detection algorithms (YOLO and Faster R-CNN) and provided an extensive benchmark on model performance, efficiency, and communication in a federated learning setting. Both the dataset and algorithms are made publicly available.

cs.CV↗

arXiv2020

Probing the $L_μ-L_τ$ gauge boson at electron colliders

We investigate the minimal $U(1)_{L_μ-L_τ}$ model with extra heavy vector-like leptons or charged scalars. By studying the kinetic mixing between $U(1)_{L_μ-L_τ}$ gauge boson $Z^\prime$ and standard model photon, which is absent at tree level and will arise at one loop level due to $μ$, $τ$ and new heavy charged leptons or scalars, the interesting behavior is shown. It can provide possibility for visible signatures of new heavy particles. We propose to search for $Z^\prime$ at electron collider experiments, such as Belle II, BESIII and future Super Tau Charm Factory (STCF), using the monophoton final state. The parameter space of $Z^\prime$ is probed, and scanned by its gauge coupling constant $g_{Z^\prime}$ and mass $m_{Z^\prime}$. We find that electron colliders have sensitivity to the previously unexplored parameter space for $Z^\prime$ with MeV-GeV mass. Future STCF experiments with $\sqrt s=2-7$ GeV can exclude the anomalous muon magnetic moment favored area when $m_{Z^\prime}<5$ GeV with the luminosity of 30 ab$^{-1}$. For $m_{Z^\prime} < 2m_μ$, $g_{Z^\prime}$ can be down to $4.2\times 10^{-5}$ at 2 GeV STCF.

hep-ph↗