arXiv subjects

Xiao Yang

Publications and source records attributed to Xiao Yang.

At least 235 records · Page 13Linked to original sources

arXiv2020

Incentive Mechanism Design for ROI-constrained Auto-bidding

Auto-bidding plays an important role in online advertising and has become a crucial tool for advertisers and advertising platforms to meet their performance objectives and optimize the efficiency of ad delivery. Advertisers employing auto-bidding only need to express high-level goals and constraints, and leave the bid optimization problem to the advertising platforms. As auto-bidding has obviously changed the bidding language and the way advertisers participate in the ad auction, fundamental investigation into mechanism design for auto-bidding environment should be made to study the interaction of auto-bidding with advertisers. In this paper, we formulate the general problem of incentive mechanism design for ROI-constrained auto-bidding, and carry out analysis of strategy-proof requirements for the revenue-maximizing and profit-maximizing advertisers. In addition, we provide a mechanism framework and a practical solution to guarantee the incentive property for different types of advertisers.

cs.GT↗

arXiv2020

Boosting Adversarial Training with Hypersphere Embedding

Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models. In this work, we advocate incorporating the hypersphere embedding (HE) mechanism into the AT procedure by regularizing the features onto compact manifolds, which constitutes a lightweight yet effective module to blend in the strength of representation learning. Our extensive analyses reveal that AT and HE are well coupled to benefit the robustness of the adversarially trained models from several aspects. We validate the effectiveness and adaptability of HE by embedding it into the popular AT frameworks including PGD-AT, ALP, and TRADES, as well as the FreeAT and FastAT strategies. In the experiments, we evaluate our methods under a wide range of adversarial attacks on the CIFAR-10 and ImageNet datasets, which verifies that integrating HE can consistently enhance the model robustness for each AT framework with little extra computation.

cs.LG↗

arXiv2020

Qlib: An AI-oriented Quantitative Investment Platform

Quantitative investment aims to maximize the return and minimize the risk in a sequential trading period over a set of financial instruments. Recently, inspired by rapid development and great potential of AI technologies in generating remarkable innovation in quantitative investment, there has been increasing adoption of AI-driven workflow for quantitative research and practical investment. In the meantime of enriching the quantitative investment methodology, AI technologies have raised new challenges to the quantitative investment system. Particularly, the new learning paradigms for quantitative investment call for an infrastructure upgrade to accommodate the renovated workflow; moreover, the data-driven nature of AI technologies indeed indicates a requirement of the infrastructure with more powerful performance; additionally, there exist some unique challenges for applying AI technologies to solve different tasks in the financial scenarios. To address these challenges and bridge the gap between AI technologies and quantitative investment, we design and develop Qlib that aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment.

q-fin.GN↗

arXiv2020

Automatic Detection and Correction Algorithms for Magnetic Saturation in the SMFT/HSOS longitudinal Magnetograms

longitudinal magnetic field often suffers the saturation effect in strong magnetic field region when the measurement performs in a single-wavelength point and linear calibration is adopted. In this study, we develop a method that can judge the threshold of saturation in Stokes $V/I$ observed by the Solar Magnetic Field Telescope (SMFT) and correct for it automatically. The procedure is that first perform the second-order polynomial fit to the Stokes $V/I$ \textit{vs} $I/I_{m}$ ($I_{m}$ is the maximum value of Stokes $I$) curve to estimate the threshold of saturation, then reconstruct Stokes $V/I$ in strong field region to correct for saturation. The algorithm is proved to be effective by comparing with the magnetograms obtained by the Helioseismic and Magnetic Imager (HMI). The accurate rate of detection and correction for saturation is $\sim$99.4\% and $\sim$88\% respectively among 175 active regions. The advantages and disadvantages of the algorithm are discussed.

astro-ph.SR↗

arXiv2020

Design and Interpretation of Universal Adversarial Patches in Face Detection

We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of adversarial examples in terms of improving the success rate as an attacker, in this work we show an interpretation of such patches that can prevent the state-of-the-art face detectors from detecting the real faces. We investigate a phenomenon: patches designed to suppress real face detection appear face-like. This phenomenon holds generally across different initialization, locations, scales of patches, backbones, and state-of-the-art face detection frameworks. We propose new optimization-based approaches to automatic design of universal adversarial patches for varying goals of the attack, including scenarios in which true positives are suppressed without introducing false positives. Our proposed algorithms perform well on real-world datasets, deceiving state-of-the-art face detectors in terms of multiple precision/recall metrics and transferability.

cs.CV↗

arXiv2020

A New Comprehensive Data Set of Solar Filaments of 100 yr Interval. I

Filaments are very common physical phenomena on the Sun and are often taken as important proxies of solar magnetic activities. The study of filaments has become a hot topic in the space weather research. For a more comprehensive understanding of filaments, especially for an understanding of solar activities of multiple solar cycles, it is necessary to perform a combined multifeature analysis by constructing a data set of multiple solar cycle data. To achieve this goal, we constructed a centennial data set that covers the H$α$ data from five observatories around the world. During the data set construction, we encountered varieties of problems, such as data fusion, accurate determination of the solar edge, classifying data by quality, dynamic threshold, and so on, which arose mainly due to multiple sources and a large time span of data. But fortunately, these problems were well solved. The data set includes seven types of data products and eight types of feature parameters with which we can implement the functions of data searching and statistical analyses. It has the characteristics of better continuity and highly complementary to space observation data, especially in the wavelengths not covered by space observations, and covers many solar cycles (including more than 60 yr of high-cadence data). We expect that this new comprehensive data set as well as the tools will help researchers to significantly speed up their search for features or events of interest, for either statistical or case study purposes, and possibly help them get a better and more comprehensive understanding of solar filament mechanisms.

astro-ph.SR↗

arXiv2020

Organized Self-Emulsification toward Structural Color

The formation of water-in-oil-in-water (W/O/W) double emulsions can be well-controlled through an organized self-emulsification mechanism in the presence of rigid bottlebrush amphiphilic block copolymers. Nanoscale water droplets with well-controlled diameters form ordered spatial arrangements within the micron-scale oil droplets. Upon solvent evaporation, solid microspheres with hexagonal close packed nanopore arrays are obtained resulting in bright structural colors. The reflected color is precisely tunable across the whole visible light range through tailoring contour length of the bottlebrush molecule. In-situ observation of the W/O interface using confocal laser scanning microscopy provides insights into the mechanism of the organized self-emulsification. This work provides a powerful strategy for the fabrication of structural colored materials in an easy and scalable manner.

physics.app-ph↗

arXiv2020

Propagating Slow Sausage Waves in a Sunspot Observed by the New Vacuum Solar Telescope

A sunspot is an ideal waveguide for a variety of magnetohydrodynamic waves, which carry a significant amount of energy to the upper atmosphere and could be used as a tool to probe magnetic and thermal structure of a sunspot. In this study, we used the New Vacuum Solar Telescope and took high-resolution image sequences simultaneously in both TiO (7058$\pm$10 Å) and H$_α$ (6562$\pm$2.5 Å) bandpasses. We extracted the area and total emission intensity variations of sunspot umbra and analyzed the signals with synchrosqueezing transform. We found that the area and emission intensity varied with both three and five minute periodicity. Moreover, the area and intensity oscillated in phase with each other, this fact hold in both TiO and H$_α$ data. We interpret this oscillatory signal as propagating slow sausage wave. The propagation speed is estimated at about 8 km$\cdot$s$^{-1}$. We infer that this sunspot's umbra could have temperature as low as 2800--3500 K.

astro-ph.SR↗

arXiv2020

A Non-Linear Magnetic Field Calibration Method for Filter-Based Magnetographs by Multilayer Perceptron

For filter-based magnetographs, the linear calibration method under the weak-field assumption is usually adopted; this leads to magnetic saturation effect in the regions with strong magnetic field. This article explores a new method to overcome the above disadvantage using a multilayer perceptron network, which we call MagMLP, based on a back-propagation algorithm with one input layer, five hidden layers, and one output layer. We use the data from the \textit{Spectropolarimeter} (SP) on board \textit{Hinode} to simulate single-wavelength observations for the model training, and take into account the influence of the Doppler velocity field and the filling factor. The training results show that the linear fitting coefficient (LFC) of the transverse field reaches above 0.91, and that of the longitudinal field is above 0.98. The generalization of the models is good because the corresponding LFCs are above 0.9 for the test subsets. Compared with the linear calibration method, the MagMLP is much more effective on dealing with the magnetic saturation effect. Analyzing an active region, the results of the linear calibration present an evident magnetic saturation effect in the umbra regions; the corresponding systematic error reaches values greater than 1000 G in most areas, or even exceeds 2000 G at some pixels. However, the results of MagMLP at these locations are very close to the inversion results, and the systematic errors are basically within 300 G. In addition, we find that there are many "bright spots" and "dark spots" on the inclination angle images from the inversion results of \textit{Hinode}/SP with values of 180 and 0 degrees, respectively, where the inversion is not reliable and does not produce a good result; the MagMLP handles these points well.

astro-ph.IM↗

arXiv2019

Benchmarking Adversarial Robustness

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance to perform correct and complete evaluations of the adversarial attack and defense algorithms. In this paper, we establish a comprehensive, rigorous, and coherent benchmark to evaluate adversarial robustness on image classification tasks. After briefly reviewing plenty of representative attack and defense methods, we perform large-scale experiments with two robustness curves as the fair-minded evaluation criteria to fully understand the performance of these methods. Based on the evaluation results, we draw several important findings and provide insights for future research.

cs.CV↗

arXiv2019

Smoothness of Severi Varieties

We aim at giving a rigorous proof of the state-ments on the smoothness and the dimension of Severi varieties wherethere are gaps in the proofs in some standard literature. The method isa mixture of algebraic and analytic methods.

math.AG↗

arXiv2019

Leveraging User Engagement Signals For Entity Labeling in a Virtual Assistant

Personal assistant AI systems such as Siri, Cortana, and Alexa have become widely used as a means to accomplish tasks through natural language commands. However, components in these systems generally rely on supervised machine learning algorithms that require large amounts of hand-annotated training data, which is expensive and time consuming to collect. The ability to incorporate unsupervised, weakly supervised, or distantly supervised data holds significant promise in overcoming this bottleneck. In this paper, we describe a framework that leverages user engagement signals (user behaviors that demonstrate a positive or negative response to content) to automatically create granular entity labels for training data augmentation. Strategies such as multi-task learning and validation using an external knowledge base are employed to incorporate the engagement annotated data and to boost the model's accuracy on a sequence labeling task. Our results show that learning from data automatically labeled by user engagement signals achieves significant accuracy gains in a production deep learning system, when measured on both the sequence labeling task as well as on user facing results produced by the system end-to-end. We believe this is the first use of user engagement signals to help generate training data for a sequence labeling task on a large scale, and can be applied in practical settings to speed up new feature deployment when little human annotated data is available.

cs.LG↗

arXiv2019

Solar Filament Recognition Based on Deep Learning

The paper presents a reliable method using deep learning to recognize solar filaments in H-alpha full-disk solar images automatically. This method cannot only identify filaments accurately but also minimize the effects of noise points of the solar images. Firstly, a raw filament dataset is set up, consisting of tens of thousands of images required for deep learning. Secondly, an automated method for solar filament identification is developed using the U-Net deep convolutional network. To test the performance of the method, a dataset with 60 pairs of manually corrected H-alpha images is employed. These images are obtained from the Big Bear Solar Observatory/Full-Disk H-alpha Patrol Telescope (BBSO/FDHA) in 2013. Cross-validation indicates that the method can efficiently identify filaments in full-disk H-alpha images.

astro-ph.IM↗

arXiv2019

Intelligent Recognition of Time Stamp Characters in Solar Scanned Images from Film

Prior to the availability of digital cameras, the solar observational images are typically recorded on films, and the information such as date and time were stamped in the same frames on film. It is significant to extract the time stamp information on the film so that the researchers can efficiently use the image data. This paper introduces an intelligent method for extracting time stamp information, namely, the Convolutional Neural Network (CNN), which is an algorithm in deep learning of multilayer neural network structures and can identify time stamp character in the scanned solar images. We carry out the time stamp decoding for the digitized data from the National Solar Observatory from 1963 to 2003. The experimental results show that the method is accurate and quick for this application. We finish the time stamp information extraction for more than 7 million images with the accuracy of 98\%.

astro-ph.SR↗

arXiv2019

AiAds: Automated and Intelligent Advertising System for Sponsored Search

Sponsored search has more than 20 years of history, and it has been proven to be a successful business model for online advertising. Based on the pay-per-click pricing model and the keyword targeting technology, the sponsored system runs online auctions to determine the allocations and prices of search advertisements. In the traditional setting, advertisers should manually create lots of ad creatives and bid on some relevant keywords to target their audience. Due to the huge amount of search traffic and a wide variety of ad creations, the limits of manual optimizations from advertisers become the main bottleneck for improving the efficiency of this market. Moreover, as many emerging advertising forms and supplies are growing, it's crucial for sponsored search platform to pay more attention to the ROI metrics of ads for getting the marketing budgets of advertisers. In this paper, we present the AiAds system developed at Baidu, which use machine learning techniques to build an automated and intelligent advertising system. By designing and implementing the automated bidding strategy, the intelligent targeting and the intelligent creation models, the AiAds system can transform the manual optimizations into multiple automated tasks and optimize these tasks in advanced methods. AiAds is a brand-new architecture of sponsored search system which changes the bidding language and allocation mechanism, breaks the limit of keyword targeting with end-to-end ad retrieval framework and provides global optimization of ad creation. This system can increase the advertiser's campaign performance, the user experience and the revenue of the advertising platform simultaneously and significantly. We present the overall architecture and modeling techniques for each module of the system and share our lessons learned in solving several key challenges.

cs.LG↗

arXiv2019

Standard Magnetic Field Production at Huairou Solar Observing Station

The regular solar observations are operated at Huairou Solar Observing Station (HSOS) since 1987, which make the construction of long-term magnetic field datasets available to understand solar magnetic field and cycles. There exist some inconveniences for solar physicist to use these data, because the data storage medium and format at HSOS experienced some changes. Additionally, the processes of magnetic field calibration are not easy to deal with for who are not familiar with these data. Here shows that the magnetic field of HSOS are further processed toward international standards, in order to explore HSOS observations data for scientific research.

astro-ph.SR↗

arXiv2018

TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade

We study the problem of extracting text instance contour information from images and use it to assist scene text detection. We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be effectively used to extract instance-level text contour from natural images. (2) The extracted contour information can be used for better scene text detection. We propose two ways for learning the contour task together with the scene text detection: (1) as an auxiliary task and (2) as multi-task cascade. Extensive experiments with different benchmark datasets demonstrate that both designs improve the performance of a state-of-the-art scene text detector and that a multi-task cascade design achieves the best performance.

cs.CV↗

arXiv2018

Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching

Community-based question answering (CQA) websites represent an important source of information. As a result, the problem of matching the most valuable answers to their corresponding questions has become an increasingly popular research topic. We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue. We employ a generative model to iteratively sample a subset of challenging negative samples to fool our classification model. Both models are alternatively optimized using REINFORCE algorithm. The proposed method is completely different from previous ones, where negative samples in training set are directly used or uniformly down-sampled. Further, we propose using Multi-scale Matching which explicitly inspects the correlation between words and ngrams of different levels of granularity. We evaluate the proposed method on SemEval 2016 and SemEval 2017 datasets and achieves state-of-the-art or similar performance.

cs.CL↗