arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,171 records · Page 65Linked to original sources

arXiv2022

Neighbor Enhanced Graph Convolutional Networks for Node Classification and Recommendation

The recently proposed Graph Convolutional Networks (GCNs) have achieved significantly superior performance on various graph-related tasks, such as node classification and recommendation. However, currently researches on GCN models usually recursively aggregate the information from all the neighbors or randomly sampled neighbor subsets, without explicitly identifying whether the aggregated neighbors provide useful information during the graph convolution. In this paper, we theoretically analyze the affection of the neighbor quality over GCN models' performance and propose the Neighbor Enhanced Graph Convolutional Network (NEGCN) framework to boost the performance of existing GCN models. Our contribution is three-fold. First, we at the first time propose the concept of neighbor quality for both node classification and recommendation tasks in a general theoretical framework. Specifically, for node classification, we propose three propositions to theoretically analyze how the neighbor quality affects the node classification performance of GCN models. Second, based on the three proposed propositions, we introduce the graph refinement process including specially designed neighbor evaluation methods to increase the neighbor quality so as to boost both the node classification and recommendation tasks. Third, we conduct extensive node classification and recommendation experiments on several benchmark datasets. The experimental results verify that our proposed NEGCN framework can significantly enhance the performance for various typical GCN models on both node classification and recommendation tasks.

cs.LG↗

arXiv2022

Likelihood Scores for Sparse Signal and Change-Point Detection

We consider here the identification of change-points on large-scale data streams. The objective is to find the most efficient way of combining information across data stream so that detection is possible under the smallest detectable change magnitude. The challenge comes from the sparsity of change-points when only a small fraction of data streams undergo change at any point in time. The most successful approach to the sparsity issue so far has been the application of hard thresholding such that only local scores from data streams exhibiting significant changes are considered and added. However the identification of an optimal threshold is a difficult one. In particular it is unlikely that the same threshold is optimal for different levels of sparsity. We propose here a sparse likelihood score for identifying a sparse signal. The score is a likelihood ratio for testing between the null hypothesis of no change against an alternative hypothesis in which the change-points or signals are barely detectable. By the Neyman-Pearson Lemma this score has maximum detection power at the given alternative. The outcome is that we have a scoring of data streams that is successful in detecting at the boundary of the detectable region of signals and change-points. The likelihood score can be seen as a soft thresholding approach to sparse signal and change-point detection in which local scores that indicate small changes are down-weighted much more than local scores indicating large changes. We are able to show second-order optimality of the sparsity likelihood score in the sense of achieving successful detection at the minimum detectable order of change magnitude as well as at the minimum detection asymptotic constant with respect this order of change.

math.ST↗

arXiv2022

A Fast and Efficient Change-point Detection Framework based on Approximate $k$-Nearest Neighbor Graphs

Change-point analysis is thriving in this big data era to address problems arising in many fields where massive data sequences are collected to study complicated phenomena over time. It plays an important role in processing these data by segmenting a long sequence into homogeneous parts for follow-up studies. The task requires the method to be able to process large datasets quickly and deal with various types of changes for high-dimensional data. We propose a new approach making use of approximate $k$-nearest neighbor information from the observations, and derive an analytic formula to control the type I error. The time complexity of our proposed method is $O\left(dn(\log n+k \log d)+nk^2\right)$ for an $n$-length sequence of $d$-dimensional data. The test statistic we consider incorporates a useful pattern for moderate- to high- dimensional data so that the proposed method could detect various types of changes in the sequence. The new approach is also asymptotic distribution free, facilitating its usage for a broader community. We apply our method to fMRI datasets and Neuropixels datasets to illustrate its effectiveness.

stat.ME↗

arXiv2022

RHONN Modelling-enabled Nonlinear Predictive Control for Lateral Dynamics Stabilization of An In-wheel Motor Driven Vehicle

Featuring the fast response and flexibility in control allocation, an electric vehicle with in-wheel motors is a good platform for implementing advanced vehicle dynamics control. Among many active safety functions of an in-wheel motor driven vehicle (IMDV), lateral stability control is a key technology, which can be realized through torque vectoring. To further advance the lateral stabilization performance of the IMDV, in this paper a novel data-driven nonlinear model predictive control (NMPC) is proposed based the recurrent high-order neural network (RHONN) modelling method. First, the new RHONN model is developed to represent vehicle's nonlinear dynamic behaviors. Different from the conventional physics-based modelling method, the RHONN model only needs data and forms high-order polynomials. Based on the RHONN model, the steady-state responses of vehicle's yaw rate and sideslip angle are iteratively optimized and set as the control objectives for low-level controller, aiming to improve the system robustness. Besides, a nonlinear model predictive controller is designed based on the RHONN, which is expected to improve the prediction accuracy during the receding horizon control. Further, a constrained optimization problem is formulated to derive the required yaw moment for vehicle lateral dynamics stabilization. Finally, the performance of the developed RHONN-based nonlinear MPC is validated on an IMDV in the CarSim/Simulink simulation environment. The validation results show that the developed approach outperforms the conventional method, and further improves the stable margin of the system. It is able to enhance the lateral stabilization performance of the IMDV under various driving scenarios, demonstrating the feasibility and effectiveness of the proposed approach.

eess.SY↗

arXiv2022

Chiral Phonon Activated Spin Seebeck Effect

Efficient generation of spin polarization is the central focus of spintronics. In magnetic materials, spin currents can arise from heat currents by the conventional spin Seebeck effect. Recently, chiral phonons with definite handedness and angular momenta have also produced profound impacts on multiple research fields. In this paper, starting with nonequilibrium distribution of chiral phonons under temperature gradient, we find a new spin selectivity effect - chiral phonon activated spin Seebeck (CPASS) effect, in chiral materials without magnetic order nor spin-orbit coupling. With both phonon-drag and band transport contributions, the CPASS coefficients are computed based on the Boltzmann transport theory. The spin accumulations by the CPASS effect quadratically increase with temperature gradient, and vary with the chemical potential modulation, thus enabling highly efficient and tunable spin generation. The CPASS effect provides a promising explanation on the chiral-induced spin selectivity effect and opportunities for designing advanced spintronic devices based on nonmagnetic chiral materials.

cond-mat.mes-hall↗

arXiv2022

Deep Semi-supervised Metric Learning with Dual Alignment for Cervical Cancer Cell Detection

Deep learning has achieved unprecedented success in various object detection tasks with huge amounts of labeled data. However, obtaining large-scale annotations for medical images is extremely challenging due to the high demand of labour and expertise. In this paper, we propose a novel deep semi-supervised metric learning method to effectively leverage both labeled and unlabeled data for cervical cancer cell detection. Specifically, our model learns a metric space and conducts dual alignment of semantic features on both the proposal level and the prototype levels. On the proposal level, we align the unlabeled data with class proxies derived from the labeled data. We further align the prototypes of the labeled and unlabeled data to alleviate the influence of possibly noisy pseudo labels generated at the proposal alignment stage. Moreover, we adopt a memory bank to store the labeled prototypes, which significantly enrich the metric learning information from larger batches. Extensive experiments show our proposed method outperforms other state-of-the-art semi-supervised approaches consistently, demonstrating the efficacy of our proposed deep semi-supervised metric learning with dual alignment.

eess.IV↗

arXiv2022

Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal

Existing unsupervised person re-identification (ReID) methods focus on adapting a model trained on a source domain to a fixed target domain. However, an adapted ReID model usually only works well on a certain target domain, but can hardly memorize the source domain knowledge and generalize to upcoming unseen data. In this paper, we propose unsupervised lifelong person ReID, which focuses on continuously conducting unsupervised domain adaptation on new domains without forgetting the knowledge learnt from old domains. To tackle unsupervised lifelong ReID, we conduct a contrastive rehearsal on a small number of stored old samples while sequentially adapting to new domains. We further set an image-to-image similarity constraint between old and new models to regularize the model updates in a way that suits old knowledge. We sequentially train our model on several large-scale datasets in an unsupervised manner and test it on all seen domains as well as several unseen domains to validate the generalizability of our method. Our proposed unsupervised lifelong method achieves strong generalizability, which significantly outperforms previous lifelong methods on both seen and unseen domains. Code will be made available at https://github.com/chenhao2345/UCR.

cs.CV↗

arXiv2022

The pole counting rule and XYZ states

The pole counting rule is a powerful and model-independent method to distinguish a confining state from a hadronic molecule. It has been applied to the explorations of $X(6900)$, $X_1(2900)$ as well as $Z_c(3900)$, $X(3872)$, $X(4660)$, etc.. For $X(6900)$, both a confining state and a molecular state are not excluded, because lacking of enough data. For $X_1(2900)$, the analysis shows that it should be a $\bar{D}_1 K$ molecule, with $J^P=1^-$ and an iso-singlet interpretation is much more favorable. Finally, it is noted that almost all XYZ particles with exotic quantum numbers can be interpreted as hadronic molecules. The $X(3872)$ is, however, more like a charmonium.

hep-ph↗

arXiv2022

Space Exploration Architecture and Design Framework for Commercialization

The trend of space commercialization is changing the decision-making process for future space exploration architectures, and there is a growing need for a new decision-making framework that explicitly considers the interactions between the mission coordinator (i.e., government) and the commercial players. In response to this challenge, this paper develops a framework for space exploration and logistics decision making that considers the incentive mechanism to stimulate commercial participation in future space infrastructure development and deployment. By extending the state-of-the-art space logistics design formulations from the game-theoretic perspective, the relationship between the mission coordinator and commercial players is first analyzed, and then the formulation for the optimal architecture design and incentive mechanism in three different scenarios is derived. To demonstrate and evaluate the effectiveness of the proposed framework, a case study on lunar habitat infrastructure design and deployment is conducted. Results show how total mission demands and in-situ resource utilization system performances after deployment may impact the cooperation among stakeholders. As an outcome of this study, an incentive-based decision-making framework that can benefit both the mission coordinator and the commercial players from commercialization is derived, leading to a mutually beneficial space exploration between the government and the industry.

math.OC↗

arXiv2022

Hierarchical Reinforcement Learning Framework for Stochastic Spaceflight Campaign Design

This paper develops a hierarchical reinforcement learning architecture for multimission spaceflight campaign design under uncertainty, including vehicle design, infrastructure deployment planning, and space transportation scheduling. This problem involves a high-dimensional design space and is challenging especially with uncertainty present. To tackle this challenge, the developed framework has a hierarchical structure with reinforcement learning and network-based mixed-integer linear programming (MILP), where the former optimizes campaign-level decisions (e.g., design of the vehicle used throughout the campaign, destination demand assigned to each mission in the campaign), whereas the latter optimizes the detailed mission-level decisions (e.g., when to launch what from where to where). The framework is applied to a set of human lunar exploration campaign scenarios with uncertain in situ resource utilization performance as a case study. The main value of this work is its integration of the rapidly growing reinforcement learning research and the existing MILP-based space logistics methods through a hierarchical framework to handle the otherwise intractable complexity of space mission design under uncertainty. This unique framework is expected to be a critical steppingstone for the emerging research direction of artificial intelligence for space mission design.

cs.LG↗

arXiv2022

Deep Learning for Computational Cytology: A Survey

Computational cytology is a critical, rapid-developing, yet challenging topic in the field of medical image computing which analyzes the digitized cytology image by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) algorithms have made significant progress in medical image analysis, leading to the boosting publications of cytological studies. To investigate the advanced methods and comprehensive applications, we survey more than 120 publications of DL-based cytology image analysis in this article. We first introduce various deep learning methods, including fully supervised, weakly supervised, unsupervised, and transfer learning. Then, we systematically summarize the public datasets, evaluation metrics, versatile cytology image analysis applications including classification, detection, segmentation, and other related tasks. Finally, we discuss current challenges and potential research directions of computational cytology.

eess.IV↗

arXiv2022

Celestial Blocks and Transverse Spin in the Three-Point Energy Correlator

Quantitative theoretical techniques for understanding the substructure of jets at the LHC enable new insights into the dynamics of QCD, and novel approaches to search for new physics. Recently, there has been a program to reformulate jet substructure in terms of correlation functions, $\langle \mathcal{E}(\vec n_1) \mathcal{E}(\vec n_2) \cdots \mathcal{E}(\vec n_k) \rangle$, of light-ray operators, $\mathcal{E}(\vec n)$, allowing the application of techniques developed in the study of Conformal Field Theories (CFTs). In this paper we further develop these techniques in the particular context of the three-point correlator $\langle \mathcal{E}(\vec n_1) \mathcal{E}(\vec n_2) \mathcal{E}(\vec n_3) \rangle$, using recently computed perturbative data in both QCD and $\mathcal{N}=4$ sYM. We derive the celestial blocks appearing in the light-ray operator product expansion (OPE) of the three-point correlator, and use the Lorentzian inversion formula to extract the spectrum of light-ray operators appearing in the expansion, showing, in particular, that the OPE data is analytic in transverse spin. Throughout our presentation, we highlight the relation between the OPE approach, and more standard splitting function based approaches of perturbative QCD, emphasizing the utility of the OPE approach for incorporating symmetries in jet substructure calculations. We hope that our presentation introduces a number of new techniques to the jet substructure community, and also illustrates the phenomenological relevance of the study of light-ray operators in the OPE limit to the CFT community.

hep-ph↗

arXiv2022

Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning

Machine learning (ML) is a key technique for big-data-driven modelling and analysis of massive Internet of Things (IoT) based intelligent and ubiquitous computing. For fast-increasing applications and data amounts, distributed learning is a promising emerging paradigm since it is often impractical or inefficient to share/aggregate data to a centralized location from distinct ones. This paper studies the problem of training an ML model over decentralized systems, where data are distributed over many user devices and the learning algorithm run on-device, with the aim of relaxing the burden at a central entity/server. Although gossip-based approaches have been used for this purpose in different use cases, they suffer from high communication costs, especially when the number of devices is large. To mitigate this, incremental-based methods are proposed. We first introduce incremental block-coordinate descent (I-BCD) for the decentralized ML, which can reduce communication costs at the expense of running time. To accelerate the convergence speed, an asynchronous parallel incremental BCD (API-BCD) method is proposed, where multiple devices/agents are active in an asynchronous fashion. We derive convergence properties for the proposed methods. Simulation results also show that our API-BCD method outperforms state of the art in terms of running time and communication costs.

cs.LG↗

arXiv2022

Category-Association Based Similarity Matching for Novel Object Pick-and-Place Task

Robotic pick-and-place has been researched for a long time to cope with uncertainty of novel objects and changeable environments. Past works mainly focus on learning-based methods to achieve high precision. However, they have difficulty being generalized for the limitation of specified training models. To break through this drawback of learning-based approaches, we introduce a new perspective of similarity matching between novel objects and a known database based on category-association to achieve pick-and-place tasks with high accuracy and stabilization. We calculate the category name similarity using word embedding to quantify the semantic similarity between the categories of known models and the target real-world objects. With a similar model identified by a similarity prediction function, we preplan a series of robust grasps and imitate them to plan new grasps on the real-world target object. We also propose a distance-based method to infer the in-hand posture of objects and adjust small rotations to achieve stable placements under uncertainty. Through a real-world robotic pick-and-place experiment with a dozen of in-category and out-of-category novel objects, our method achieved an average success rate of 90.6% and 75.9% respectively, validating the capacity of generalization to diverse objects.

cs.RO↗

arXiv2022

Instance and Panoptic Segmentation Using Conditional Convolutions

We propose a simple yet effective framework for instance and panoptic segmentation, termed CondInst (conditional convolutions for instance and panoptic segmentation). In the literature, top-performing instance segmentation methods typically follow the paradigm of Mask R-CNN and rely on ROI operations (typically ROIAlign) to attend to each instance. In contrast, we propose to attend to the instances with dynamic conditional convolutions. Instead of using instance-wise ROIs as inputs to the instance mask head of fixed weights, we design dynamic instance-aware mask heads, conditioned on the instances to be predicted. CondInst enjoys three advantages: 1.) Instance and panoptic segmentation are unified into a fully convolutional network, eliminating the need for ROI cropping and feature alignment. 2.) The elimination of the ROI cropping also significantly improves the output instance mask resolution. 3.) Due to the much improved capacity of dynamically-generated conditional convolutions, the mask head can be very compact (e.g., 3 conv. layers, each having only 8 channels), leading to significantly faster inference time per instance and making the overall inference time almost constant, irrelevant to the number of instances. We demonstrate a simpler method that can achieve improved accuracy and inference speed on both instance and panoptic segmentation tasks. On the COCO dataset, we outperform a few state-of-the-art methods. We hope that CondInst can be a strong baseline for instance and panoptic segmentation. Code is available at: https://git.io/AdelaiDet

cs.CV↗

arXiv2022

Ubiquitous Coexisting Electron-Mode Couplings in High Temperature Cuprate Superconductors

In conventional superconductors, the electron-phonon coupling plays a dominant role in pairing the electrons and generating superconductivity. In high temperature cuprate superconductors, the existence of the electron coupling with phonons and other boson modes and its role in producing high temperature superconductivity remain unclear. The evidence of the electron-boson coupling mainly comes from the angle-resolved photoemission (ARPES) observations of the ~70meV nodal dispersion kink and the ~40meV antinodal kink. However, the reported results are sporadic and the nature of the involved bosons are still under debate. Here we report new findings of ubiquitous two coexisting electron-mode couplings in cuprate superconductors. By taking ultra-high resolution laser-based ARPES measurements, combined with the improved second derivative analysis method, we discovered that the electrons are coupled simultaneously with two sharp phonon modes with energies of ~70meV and ~40meV in different superconductors with different doping levels, over the entire momentum space and at different temperatures above and below the superconducting transition temperature. The observed electron-phonon couplings are unusual because the associated energy scales do not exhibit an obvious change across the superconducting transition. We further find that the well-known "peak-dip-hump" structure, which has long been considered as a hallmark of superconductivity, is also omnipresent and consists of finer structures that originates from electron coupling with two sharp phonon modes. These comprehensive results provide a unified picture to reconcile all the reported observations and pinpoint the origin of the electron-mode couplings in cuprate superconductors. They provide key information to understand the role of the electron-phonon coupling in generating high temperature superconductivity.

cond-mat.supr-con↗

arXiv2022

Semantic decoupled representation learning for remote sensing image change detection

Contemporary transfer learning-based methods to alleviate the data insufficiency in change detection (CD) are mainly based on ImageNet pre-training. Self-supervised learning (SSL) has recently been introduced to remote sensing (RS) for learning in-domain representations. Here, we propose a semantic decoupled representation learning for RS image CD. Typically, the object of interest (e.g., building) is relatively small compared to the vast background. Different from existing methods expressing an image into one representation vector that may be dominated by irrelevant land-covers, we disentangle representations of different semantic regions by leveraging the semantic mask. We additionally force the model to distinguish different semantic representations, which benefits the recognition of objects of interest in the downstream CD task. We construct a dataset of bitemporal images with semantic masks in an effortless manner for pre-training. Experiments on two CD datasets show our model outperforms ImageNet pre-training, in-domain supervised pre-training, and several recent SSL methods.

cs.CV↗

arXiv2022

S2Looking: A Satellite Side-Looking Dataset for Building Change Detection

Building-change detection underpins many important applications, especially in the military and crisis-management domains. Recent methods used for change detection have shifted towards deep learning, which depends on the quality of its training data. The assembly of large-scale annotated satellite imagery datasets is therefore essential for global building-change surveillance. Existing datasets almost exclusively offer near-nadir viewing angles. This limits the range of changes that can be detected. By offering larger observation ranges, the scroll imaging mode of optical satellites presents an opportunity to overcome this restriction. This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles. The dataset consists of 5000 bitemporal image pairs of rural areas and more than 65,920 annotated instances of changes throughout the world. The dataset can be used to train deep-learning-based change-detection algorithms. It expands upon existing datasets by providing (1) larger viewing angles; (2) large illumination variances; and (3) the added complexity of rural images. To facilitate {the} use of the dataset, a benchmark task has been established, and preliminary tests suggest that deep-learning algorithms find the dataset significantly more challenging than the closest-competing near-nadir dataset, LEVIR-CD+. S2Looking may therefore promote important advances in existing building-change-detection algorithms. The dataset is available at https://github.com/S2Looking/.

cs.CV↗