Searcharxiv⌕ Search

arXiv subjects

Zhi Qiao

Publications and source records attributed to Zhi Qiao.

34 records · Page 2Linked to original sources
arXiv2021

SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection

Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection. Due to the lack of ground truth labels, practitioners often have to build a large number of unsupervised, heterogeneous models (i.e., different algorithms with varying hyperparameters) for further combination and analysis, rather than relying on a single model. How to accelerate the training and scoring on new-coming samples by outlyingness (referred as prediction throughout the paper) with a large number of unsupervised, heterogeneous OD models? In this study, we propose a modular acceleration system, called SUOD, to address it. The proposed system focuses on three complementary acceleration aspects (data reduction for high-dimensional data, approximation for costly models, and taskload imbalance optimization for distributed environment), while maintaining performance accuracy. Extensive experiments on more than 20 benchmark datasets demonstrate SUOD's effectiveness in heterogeneous OD acceleration, along with a real-world deployment case on fraudulent claim analysis at IQVIA, a leading healthcare firm. We open-source SUOD for reproducibility and accessibility.

cs.LG↗
arXiv2021

PyHealth: A Python Library for Health Predictive Models

Despite the explosion of interest in healthcare AI research, the reproducibility and benchmarking of those research works are often limited due to the lack of standard benchmark datasets and diverse evaluation metrics. To address this reproducibility challenge, we develop PyHealth, an open-source Python toolbox for developing various predictive models on healthcare data. PyHealth consists of data preprocessing module, predictive modeling module, and evaluation module. The target users of PyHealth are both computer science researchers and healthcare data scientists. With PyHealth, they can conduct complex machine learning pipelines on healthcare datasets with fewer than ten lines of code. The data preprocessing module enables the transformation of complex healthcare datasets such as longitudinal electronic health records, medical images, continuous signals (e.g., electrocardiogram), and clinical notes into machine learning friendly formats. The predictive modeling module provides more than 30 machine learning models, including established ensemble trees and deep neural network-based approaches, via a unified but extendable API designed for both researchers and practitioners. The evaluation module provides various evaluation strategies (e.g., cross-validation and train-validation-test split) and predictive model metrics. With robustness and scalability in mind, best practices such as unit testing, continuous integration, code coverage, and interactive examples are introduced in the library's development. PyHealth can be installed through the Python Package Index (PyPI) or https://github.com/yzhao062/PyHealth .

cs.LG↗
arXiv2020

FLANNEL: Focal Loss Based Neural Network Ensemble for COVID-19 Detection

To test the possibility of differentiating chest x-ray images of COVID-19 against other pneumonia and healthy patients using deep neural networks. We construct the X-ray imaging data from two publicly available sources, which include 5508 chest x-ray images across 2874 patients with four classes: normal, bacterial pneumonia, non-COVID-19 viral pneumonia, and COVID-19. To identify COVID-19, we propose a Focal Loss Based Neural Ensemble Network (FLANNEL), a flexible module to ensemble several convolutional neural network (CNN) models and fuse with a focal loss for accurate COVID-19 detection on class imbalance data. FLANNEL consistently outperforms baseline models on COVID-19 identification task in all metrics. Compared with the best baseline, FLANNEL shows a higher macro-F1 score with 6% relative increase on Covid-19 identification task where it achieves 0.7833(0.07) in Precision, 0.8609(0.03) in Recall, and 0.8168(0.03) F1 score.

eess.IV↗
arXiv2020

Gaussian Constrained Attention Network for Scene Text Recognition

Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we argue that the existing attention mechanism faces the problem of attention diffusion, in which the model may not focus on a certain character area. In this paper, we propose Gaussian Constrained Attention Network to deal with this problem. It is a 2D attention-based method integrated with a novel Gaussian Constrained Refinement Module, which predicts an additional Gaussian mask to refine the attention weights. Different from adopting an additional supervision on the attention weights simply, our proposed method introduces an explicit refinement. In this way, the attention weights will be more concentrated and the attention-based recognition network achieves better performance. The proposed Gaussian Constrained Refinement Module is flexible and can be applied to existing attention-based methods directly. The experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. Our code has been available at https://github.com/Pay20Y/GCAN.

cs.CV↗
arXiv2020

SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition

Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape. Nevertheless, they still face lots of challenges like image blur, uneven illumination, and incomplete characters. We argue that most encoder-decoder methods are based on local visual features without explicit global semantic information. In this work, we propose a semantics enhanced encoder-decoder framework to robustly recognize low-quality scene texts. The semantic information is used both in the encoder module for supervision and in the decoder module for initializing. In particular, the state-of-the art ASTER method is integrated into the proposed framework as an exemplar. Extensive experiments demonstrate that the proposed framework is more robust for low-quality text images, and achieves state-of-the-art results on several benchmark datasets.

cs.CV↗
arXiv2020

Combining GHOST and Casper

We present "Gasper," a proof-of-stake-based consensus protocol, which is an idealized version of the proposed Ethereum 2.0 beacon chain. The protocol combines Casper FFG, a finality tool, with LMD GHOST, a fork-choice rule. We prove safety, plausible liveness, and probabilistic liveness under different sets of assumptions.

cs.CR↗
arXiv2019

Shape-Aware Organ Segmentation by Predicting Signed Distance Maps

In this work, we propose to resolve the issue existing in current deep learning based organ segmentation systems that they often produce results that do not capture the overall shape of the target organ and often lack smoothness. Since there is a rigorous mapping between the Signed Distance Map (SDM) calculated from object boundary contours and the binary segmentation map, we exploit the feasibility of learning the SDM directly from medical scans. By converting the segmentation task into predicting an SDM, we show that our proposed method retains superior segmentation performance and has better smoothness and continuity in shape. To leverage the complementary information in traditional segmentation training, we introduce an approximated Heaviside function to train the model by predicting SDMs and segmentation maps simultaneously. We validate our proposed models by conducting extensive experiments on a hippocampus segmentation dataset and the public MICCAI 2015 Head and Neck Auto Segmentation Challenge dataset with multiple organs. While our carefully designed backbone 3D segmentation network improves the Dice coefficient by more than 5% compared to current state-of-the-arts, the proposed model with SDM learning produces smoother segmentation results with smaller Hausdorff distance and average surface distance, thus proving the effectiveness of our method.

cs.CV↗
arXiv2019

On the Cheeger constant for distance-regular graphs

The Cheeger constant of a graph is the smallest possible ratio between the size of a subgraph and the size of its boundary. It is well known that this constant must be at least $\frac{λ_1}{2}$, where $λ_1$ is the smallest positive eigenvalue of the Laplacian matrix. The subject of this paper is a conjecture of the authors that for distance-regular graphs the Cheeger constant is at most $λ_1$. In particular, we prove the conjecture for the known infinite families of distance-regular graphs, distance-regular graphs of diameter 2 (the strongly regular graphs), several classes of imprimitive distance-regular graphs, and most distance-regular graphs with small valency.

math.CO↗
arXiv2019

Non-bipartite distance-regular graphs with a small smallest eigenvalue

In 2017, Qiao and Koolen showed that for any fixed integer $D\geq 3$, there are only finitely many such graphs with $θ_{\min}\leq -αk$, where $0<α<1$ is any fixed number. In this paper, we will study non-bipartite distance-regular graphs with relatively small $θ_{\min}$ compared with $k$. In particular, we will show that if $θ_{\min}$ is relatively close to $-k$, then the odd girth $g$ must be large. Also we will classify the non-bipartite distance-regular graphs with $θ_{\min} \leq \frac{D-1}{D}$ for $D =4,5$.

math.CO↗
arXiv2017

A new characterization of the dual polar graphs

In this paper we give a new characterization of the dual polar graphs, extending the work of Brouwer and Wilbrink on regular near polygons. Also as a consequence of our characterization we confirm a conjecture of the authors on non-bipartite distance-regular graphs with smallest eigenvalue at most $-k/2$, where $k$ is the valency of the distance-regular graph, in case of $c_2 \geq3$ and $a_1 =1$.

math.CO↗
arXiv2016

A note on graphs with exactly two main eigenvalues

In this note, we consider connected graphs with exactly two main eigenvalues. We will give several constructions for them, and as a consequence we show a family of those graphs with an unbounded number of distinct valencies.

math.CO↗
arXiv2016

Temporally modulated phase retrieval method for weak temporal phase measurement of laser pulses

The measurement of weak temporal phase for picosecond and nanosecond laser pulses is important but quite difficult. We propose a simple iterative algorithm, which is based on a temporally movable phase modulation process, to retrieve the weak temporal phase of laser pulses. This unambiguous method can achieve a high accuracy and simultaneously measure the weak temporal phase and temporal profile of pulses, which are almost transform-limited. Detailed analysis shows that this iterative method has valuable potential applications in the characterization of pulses with weak temporal phase.

physics.optics↗
arXiv2015

Light tails and the Hermitian dual polar graphs

Juriśič et al. conjectured that if a distance-regular graph $Γ$ with diameter $D$ at least three has a light tail, then one of the following holds: 1.$a_1 =0$; 2.$Γ$ is an antipodal cover of diameter three; 3.$Γ$ is tight; 4.$Γ$ is the halved $2D+1$-cube; 5.$Γ$ is a Hermitian dual polar graph $^2A_{2D-1}(r)$ where $r$ is a prime power. In this note, we will consider the case when the light tail corresponds to the eigenvalue $-\frac{k}{a_1 +1}$. Our main result is: Theorem Let $Γ$ be a non-bipartite distance-regular graph with valency $k \geq 3$ , diameter $D \geq 3$ and distinct eigenvalues $θ_0 > θ_1 > \cdots > θ_D$. Suppose that $Γ$ is $2$-bounded with smallest eigenvalue $θ_D = -\frac{k}{a_1 +1}$. If the minimal idempotent $E_D$, corresponding to eigenvalue $θ_D$, is a light tail, then $Γ$ is the dual polar graph $^2A_{2D-1}(r)$, where $r$ is a prime power. As a consequence of this result we will also show: Theorem Let $Γ$ be a distance-regular graph with valency $k \geq 3$, diameter $D \geq 2$, $a_1 =1$ and $θ_0 > θ_1 > \cdots > θ_D$. If $c_2 \geq5$ and $θ_D = -k/2$, then $c_2 =5$ and $Γ$ is the dual polar graph $^2A_{2D-1}(2)$.

math.CO↗
arXiv2015

2-walk-regular dihedrants from group-divisible designs

In this note, we construct bipartite 2-walk-regular graphs with exactly 6 distinct eigenvalues as incidence graphs of group-divisible designs with the dual property. For many of them, we show that they are 2-arc-transitive dihedrants. We note that many of these graphs are not described in Du et al. [7, Theorem1.2], in which they classify the connected 2-arc transitive dihedrants.

math.CO↗
arXiv2014

Predicting market instability: New dynamics between volume and volatility

Econophysics and econometrics agree that there is a correlation between volume and volatility in a time series. Using empirical data and their distributions, we further investigate this correlation and discover new ways that volatility and volume interact, particularly when the levels of both are high. We find that the distribution of the volume-conditional volatility is well fit by a power-law function with an exponential cutoff. We find that the volume-conditional volatility distribution scales with volume, and collapses these distributions to a single curve. We exploit the characteristics of the volume-volatility scatter plot to find a strong correlation between logarithmic volume and a quantity we define as local maximum volatility (LMV), which indicates the largest volatility observed in a given range of trading volumes. This finding supports our empirical analysis showing that volume is an excellent predictor of the maximum value of volatility for both same-day and near-future time periods. We also use a joint conditional probability that includes both volatility and volume to demonstrate that invoking both allows us to better predict the largest next-day volatility than invoking either one alone.

q-fin.ST↗