arXiv subjects

Chi Zhang

Publications and source records attributed to Chi Zhang.

At least 685 records · Page 38Linked to original sources

arXiv2021

One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction

Traditional industrial recommenders are usually trained on a single business domain and then serve for this domain. However, in large commercial platforms, it is often the case that the recommenders need to make click-through rate (CTR) predictions for multiple business domains. Different domains have overlapping user groups and items. Thus, there exist commonalities. Since the specific user groups have disparity and the user behaviors may change in various business domains, there also have distinctions. The distinctions result in domain-specific data distributions, making it hard for a single shared model to work well on all domains. To learn an effective and efficient CTR model to handle multiple domains simultaneously, we present Star Topology Adaptive Recommender (STAR). Concretely, STAR has the star topology, which consists of the shared centered parameters and domain-specific parameters. The shared parameters are applied to learn commonalities of all domains, and the domain-specific parameters capture domain distinction for more refined prediction. Given requests from different business domains, STAR can adapt its parameters conditioned on the domain characteristics. The experimental result from production data validates the superiority of the proposed STAR model. Since 2020, STAR has been deployed in the display advertising system of Alibaba, obtaining averaging 8.0% improvement on CTR and 6.0% on RPM (Revenue Per Mille).

cs.IR↗

arXiv2021

Quantum key distribution over 658 km fiber with distributed vibration sensing

Twin-field quantum key distribution (TF-QKD) promises ultra-long secure key distribution which surpasses the rate distance limit and can reduce the number of the trusted nodes in long-haul quantum network. Tremendous efforts have been made towards implementation of TF-QKD, among which, the secure key with finite size analysis can distribute more than 500 km in the lab and in the field. Here, we demonstrate the sending-or-not-sending TF-QKD experimentally, achieving a secure key distribution with finite size analysis over 658 km ultra-low-loss optical fiber, improve the secure distance record by around 100 km. Meanwhile, in a TF-QKD system, any phase fluctuation due to temperature variation and ambient variation during the channel must be recorded and compensated, and all these phase information can then be utilized to sense the channel vibration perturbations. With our QKD system, we recovered the external vibrational perturbations on the fiber generated by an artificial vibroseis and successfully located the perturbation position with a resolution better than 1 km. Our results not only set a new distance record of QKD, but also demonstrate that the redundant information of TF-QKD can be used for remote sensing of the channel vibration, which can find applications in earthquake detection and landslide monitoring besides secure communication.

quant-ph↗

arXiv2021

Centers of Multilinear Forms and Applications

In this paper we study the center algebras of multilinear forms. It is shown that the center of a nondegenerate multilinear form is a finite dimensional commutative algebra and can be effectively applied to its direct sum decompositions. As an application of the algebraic structure of centers, we also show that almost all multilinear forms are absolutely indecomposable. The theory of centers can be extended to multilinear maps and be applied to their symmetric equivalence. Moreover, with a help of the results of symmetric equivalence, we are able to provide a linear algebraic proof of a well known Torelli type result which says that two complex homogeneous polynomials with the same Jacobian ideal are linearly equivalent.

math.RA↗

arXiv2021

On Centers and Direct Sum Decompositions of Higher Degree Forms

Higher degree forms are homogeneous polynomials of degree $d > 2,$ or equivalently symmetric $d$-linear spaces. This paper is mainly concerned about the algebraic structure of the centers of higher degree forms with applications specifically to direct sum decompositions, namely expressing higher degree forms as sums of forms in disjoint sets of variables. We show that the center algebra of almost every form is the ground field, consequently almost all higher degree forms are absolutely indecomposable. If a higher degree form is decomposable, then we provide simple criteria and algorithms for direct sum decompositions by its center algebra. It is shown that the direct sum decomposition problem can be boiled down to some standard tasks of linear algebra, in particular the computations of eigenvalues and eigenvectors. We also apply the structure results of center algebras to provide a complete answer to the classical problem of whether a higher degree form can be reconstructed from its Jacobian ideal.

math.RA↗

arXiv2021

A multi-order smoothed particle hydrodynamics method for cardiac electromechanics with the Purkinje network

In previous work, Zhang et al. (2021) \cite{zhang2021integrative} developed an integrated smoothed particle hydrodynamics (SPH) method to simulate the principle aspects of cardiac function, including electrophysiology, passive and active mechanical response of the myocardium. As the inclusion of the Purkinje network in electrocardiology is recognized as fundamental to accurately describing the electrical activation in the right and left ventricles, in this paper, we present a multi-order SPH method to handle the electrical propagation through the Purkinje system and in the myocardium with monodomain/monodomain coupling strategy. We first propose an efficient algorithm for network generation on arbitrarily complex surface by exploiting level-set geometry representation and cell-linked list neighbor search algorithm. Then, a reduced-order SPH method is developed to solve the one-dimensional monodomain equation to characterize the fast electrical activation through the Purkinje network. Finally, a multi-order coupling paradigm is introduced to capture the coupled nature of potential propagation arising from the interaction between the network and the myocardium. A set of numerical examples are studied to assess the computational performance, accuracy and versatility of the proposed methods. In particular, numerical study performed in realistic left ventricle demonstrates that the present method features all the physiological issues that characterize a heartbeat simulation, including the initiation of the signal in the Purkinje network and the systolic and diastolic phases. As expected, the results underlie the importance of using physiologically realistic Purkinje network for modeling cardiac functions.

cs.CE↗

arXiv2021

Generalised and efficient wall boundary condition treatment in GPU-accelerated smoothed particle hydrodynamics

This paper presents a generalised and efficient wall boundary treatment in the smoothed particle hydrodynamics (SPH) method for 3-D complex and arbitrary geometries with single- and multi-phase flows to be executed on graphics processing units (GPUs). Using a force balance between the wall and fluid particles with a novel penalty method, a pressure boundary condition is applied on the wall dummy particles which effectively prevents non-physical particle penetration into the wall boundaries also in highly violent impacts and multi-phase flows with high density ratios. A new density reinitialisation scheme is also presented to enhance the accuracy. The proposed method is very simple in comparison with previous wall boundary formulations on GPUs that enforces no additional memory caching and thus is ideally suited for heterogeneous architectures of GPUs. The method is validated in various test cases involving violent single- and multi-phase flows in arbitrary geometries and demonstrates very good robustness, accuracy and performance. The new wall boundary condition treatment is able to improve the high accuracy of its previous version \citep{ADAMI2012wall} also in complex 3-D and multi-phase problems, while it is efficiently executable on GPUs with single precision floating points arithmetic which makes it suitable for a wide range of GPUs, including consumer graphic cards. Therefore, the method is a reliable solution for the long-lasting challenge of the wall boundary condition in the SPH method for a broad range of natural and industrial applications.

physics.comp-ph↗

arXiv2021

Plant-Protein-Enabled Biodegradable Triboelectric Nanogenerator for Sustainable Agriculture

As the use of triboelectric nanogenerators (TENGs) increases, the generation of related electronic waste has been a major challenge. Therefore, the development of environmentally friendly, biodegradable, and low-cost TENGs must be prioritized. Having discovered that plant proteins, by-products of grain processing, possess excellent triboelectric properties, we explore these properties by evaluating the protein structure. The proteins are recycled to fabricate triboelectric layers, and the triboelectric series according to electrical properties is determined for the first time. Using a special structure design, we construct a plant-protein-enabled biodegradable TENG by integrating a polylactic acid film, which is used as a new type of mulch film to construct a growth-promoting system that generates space electric fields for agriculture. Thus, from the plant protein to the crop, a sustainable recycling loop is implemented. Using bean seedlings as a model to confirm the feasibility of the mulch film, we further use it in the cultivation of greenhouse vegetables. Experimental results demonstrate the applicability of the proposed plant-protein-enabled biodegradable TENG in sustainable agriculture.

physics.app-ph↗

arXiv2021

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train the student. A popular model smoothing method is the Temporal Moving Average (TMA), which continuously averages the teacher parameters with the up-to-date student parameters. In this paper, we propose "Spatial Ensemble", a novel model smoothing mechanism in parallel with TMA. Spatial Ensemble randomly picks up a small fragment of the student model to directly replace the corresponding fragment of the teacher model. Consequentially, it stitches different fragments of historical student models into a unity, yielding the "Spatial Ensemble" effect. Spatial Ensemble obtains comparable student-teacher learning performance by itself and demonstrates valuable complementarity with temporal moving average. Their integration, named Spatial-Temporal Smoothing, brings general (sometimes significant) improvement to the student-teacher learning framework on a variety of state-of-the-art methods. For example, based on the self-supervised method BYOL, it yields +0.9% top-1 accuracy improvement on ImageNet, while based on the semi-supervised approach FixMatch, it increases the top-1 accuracy by around +6% on CIFAR-10 when only few training labels are available. Codes and models are available at: https://github.com/tengteng95/Spatial_Ensemble.

cs.CV↗

arXiv2021

Effectiveness of Optimization Algorithms in Deep Image Classification

Adam is applied widely to train neural networks. Different kinds of Adam methods with different features pop out. Recently two new adam optimizers, AdaBelief and Padam are introduced among the community. We analyze these two adam optimizers and compare them with other conventional optimizers (Adam, SGD + Momentum) in the scenario of image classification. We evaluate the performance of these optimization algorithms on AlexNet and simplified versions of VGGNet, ResNet using the EMNIST dataset. (Benchmark algorithm is available at \hyperref[https://github.com/chuiyunjun/projectCSC413]{https://github.com/chuiyunjun/projectCSC413}).

cs.CV↗

arXiv2021

BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning

Online interactions with the environment to collect data samples for training a Reinforcement Learning (RL) agent is not always feasible due to economic and safety concerns. The goal of Offline Reinforcement Learning is to address this problem by learning effective policies using previously collected datasets. Standard off-policy RL algorithms are prone to overestimations of the values of out-of-distribution (less explored) actions and are hence unsuitable for Offline RL. Behavior regularization, which constraints the learned policy within the support set of the dataset, has been proposed to tackle the limitations of standard off-policy algorithms. In this paper, we improve the behavior regularized offline reinforcement learning and propose BRAC+. First, we propose quantification of the out-of-distribution actions and conduct comparisons between using Kullback-Leibler divergence versus using Maximum Mean Discrepancy as the regularization protocol. We propose an analytical upper bound on the KL divergence as the behavior regularizer to reduce variance associated with sample based estimations. Second, we mathematically show that the learned Q values can diverge even using behavior regularized policy update under mild assumptions. This leads to large overestimations of the Q values and performance deterioration of the learned policy. To mitigate this issue, we add a gradient penalty term to the policy evaluation objective. By doing so, the Q values are guaranteed to converge. On challenging offline RL benchmarks, BRAC+ outperforms the baseline behavior regularized approaches by 40%~87% and the state-of-the-art approach by 6%.

cs.LG↗

arXiv2021

The Three-loop MHV Octagon from $\bar{Q}$ equations

The $\bar{Q}$ equations, rooted in the dual superconformal anomalies, are a powerful tool for computing amplitudes in planar $\mathcal{N}=4$ supersymmetric Yang-Mills theory. By using the $\bar{Q}$ equations, we compute the symbol of the first MHV amplitude with algebraic letters -- the three-loop 8-point amplitude (or the octagon remainder function) -- in this theory. The symbol alphabet for this amplitude consists of 204 independent rational letters and shares the same 18 algebraic letters with the two-loop 8-point NMHV amplitude.

hep-th↗

arXiv2021

Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence

In this paper, we propose a Spatial Robust Mixture Regression model to investigate the relationship between a response variable and a set of explanatory variables over the spatial domain, assuming that the relationships may exhibit complex spatially dynamic patterns that cannot be captured by constant regression coefficients. Our method integrates the robust finite mixture Gaussian regression model with spatial constraints, to simultaneously handle the spatial nonstationarity, local homogeneity, and outlier contaminations. Compared with existing spatial regression models, our proposed model assumes the existence a few distinct regression models that are estimated based on observations that exhibit similar response-predictor relationships. As such, the proposed model not only accounts for nonstationarity in the spatial trend, but also clusters observations into a few distinct and homogenous groups. This provides an advantage on interpretation with a few stationary sub-processes identified that capture the predominant relationships between response and predictor variables. Moreover, the proposed method incorporates robust procedures to handle contaminations from both regression outliers and spatial outliers. By doing so, we robustly segment the spatial domain into distinct local regions with similar regression coefficients, and sporadic locations that are purely outliers. Rigorous statistical hypothesis testing procedure has been designed to test the significance of such segmentation. Experimental results on many synthetic and real-world datasets demonstrate the robustness, accuracy, and effectiveness of our proposed method, compared with other robust finite mixture regression, spatial regression and spatial segmentation methods.

stat.ME↗

arXiv2021

Adaptive Reliability Analysis for Multi-fidelity Models using a Collective Learning Strategy

In many fields of science and engineering, models with different fidelities are available. Physical experiments or detailed simulations that accurately capture the behavior of the system are regarded as high-fidelity models with low model uncertainty, however, they are expensive to run. On the other hand, simplified physical experiments or numerical models are seen as low-fidelity models that are cheaper to evaluate. Although low-fidelity models are often not suitable for direct use in reliability analysis due to their low accuracy, they can offer information about the trend of the high-fidelity model thus providing the opportunity to explore the design space at a low cost. This study presents a new approach called adaptive multi-fidelity Gaussian process for reliability analysis (AMGPRA). Contrary to selecting training points and information sources in two separate stages as done in state-of-the-art mfEGRA method, the proposed approach finds the optimal training point and information source simultaneously using the novel collective learning function (CLF). CLF is able to assess the global impact of a candidate training point from an information source and it accommodates any learning function that satisfies a certain profile. In this context, CLF provides a new direction for quantifying the impact of new training points and can be easily extended with new learning functions to adapt to different reliability problems. The performance of the proposed method is demonstrated by three mathematical examples and one engineering problem concerning the wind reliability of transmission towers. It is shown that the proposed method achieves similar or higher accuracy with reduced computational costs compared to state-of-the-art single and multi-fidelity methods. A key application of AMGPRA is high-fidelity fragility modeling using complex and costly physics-based computational models.

cs.LG↗

arXiv2021

Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning

Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at different few-shot learning scenarios. It is therefore tricky to decide which learning strategies to use under different task conditions. Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs. The goal of our work is to search for good parameter adaptation policies that are applied to different stages in the network for few-shot classification. We present a search space that covers many popular few-shot learning algorithms in the literature and develop a differentiable searching and decoding algorithm based on meta-learning that supports gradient-based optimization. We demonstrate the effectiveness of our searching-based method on multiple benchmark datasets. Extensive experiments show that our approach significantly outperforms baselines and demonstrates performance advantages over many state-of-the-art methods. Code and models will be made publicly available.

cs.CV↗

arXiv2021

GeneAnnotator: A Semi-automatic Annotation Tool for Visual Scene Graph

In this manuscript, we introduce a semi-automatic scene graph annotation tool for images, the GeneAnnotator. This software allows human annotators to describe the existing relationships between participators in the visual scene in the form of directed graphs, hence enabling the learning and reasoning on visual relationships, e.g., image captioning, VQA and scene graph generation, etc. The annotations for certain image datasets could either be merged in a single VG150 data-format file to support most existing models for scene graph learning or transformed into a separated annotation file for each single image to build customized datasets. Moreover, GeneAnnotator provides a rule-based relationship recommending algorithm to reduce the heavy annotation workload. With GeneAnnotator, we propose Traffic Genome, a comprehensive scene graph dataset with 1000 diverse traffic images, which in return validates the effectiveness of the proposed software for scene graph annotation. The project source code, with usage examples and sample data is available at https://github.com/Milomilo0320/A-Semi-automatic-Annotation-Software-for-Scene-Graph, under the Apache open-source license.

cs.CV↗

arXiv2021

Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Development

This paper introduces a human-in-the-loop (HITL) data annotation pipeline to generate high-quality, large-scale speech datasets. The pipeline combines human and machine advantages to more quickly, accurately, and cost-effectively annotate datasets with machine pre-labeling and fully manual auditing. Quality control mechanisms such as blind testing, behavior monitoring, and data validation have been adopted in the annotation pipeline to mitigate potential bias introduced by machine-generated labels. Our A/B testing and pilot results demonstrated the HITL pipeline can improve annotation speed and capacity by at least 80% and quality is comparable to or higher than manual double pass annotation. We are leveraging this scalable pipeline to create and continuously grow ultra-high volume off-the-shelf (UHV-OTS) speech corpora for multiple languages, with the capability to expand to 10,000+ hours per language annually. Customized datasets can be produced from the UHV-OTS corpora using dynamic packaging. UHV-OTS is a long-term Appen project to support commercial and academic research data needs in speech processing. Appen will donate a number of free speech datasets from the UHV-OTS each year to support academic and open source community research under the CC-BY-SA license. We are also releasing the code of the data pre-processing and pre-tagging pipeline under the Apache 2.0 license to allow reproduction of the results reported in the paper.

eess.AS↗

arXiv2021

Calibrating Class Activation Maps for Long-Tailed Visual Recognition

Real-world visual recognition problems often exhibit long-tailed distributions, where the amount of data for learning in different categories shows significant imbalance. Standard classification models learned on such data distribution often make biased predictions towards the head classes while generalizing poorly to the tail classes. In this paper, we present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map Calibration (CAMC) module to improve the learning and prediction of network classifiers, by enforcing network prediction based on important image regions. The proposed CAMC module highlights the correlated image regions across data and reinforces the representations in these areas to obtain a better global representation for classification. Furthermore, we investigate the use of normalized classifiers for representation learning in long-tailed problems. Our empirical study demonstrates that by simply scaling the outputs of the classifier with an appropriate scalar, we can effectively improve the classification accuracy on tail classes without losing the accuracy of head classes. We conduct extensive experiments to validate the effectiveness of our design and we set new state-of-the-art performance on five benchmarks, including ImageNet-LT, Places-LT, iNaturalist 2018, CIFAR10-LT, and CIFAR100-LT.

cs.CV↗

arXiv2021

Binocular Mutual Learning for Improving Few-shot Classification

Most of the few-shot learning methods learn to transfer knowledge from datasets with abundant labeled data (i.e., the base set). From the perspective of class space on base set, existing methods either focus on utilizing all classes under a global view by normal pretraining, or pay more attention to adopt an episodic manner to train meta-tasks within few classes in a local view. However, the interaction of the two views is rarely explored. As the two views capture complementary information, we naturally think of the compatibility of them for achieving further performance gains. Inspired by the mutual learning paradigm and binocular parallax, we propose a unified framework, namely Binocular Mutual Learning (BML), which achieves the compatibility of the global view and the local view through both intra-view and cross-view modeling. Concretely, the global view learns in the whole class space to capture rich inter-class relationships. Meanwhile, the local view learns in the local class space within each episode, focusing on matching positive pairs correctly. In addition, cross-view mutual interaction further promotes the collaborative learning and the implicit exploration of useful knowledge from each other. During meta-test, binocular embeddings are aggregated together to support decision-making, which greatly improve the accuracy of classification. Extensive experiments conducted on multiple benchmarks including cross-domain validation confirm the effectiveness of our method.

cs.CV↗