Xin Chen, Yawen Duan, Zewei Chen, Hang Xu, Zihao Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li
Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They also lack efficient mechanisms to reuse knowledge when confronting multiple tasks. These challenges preclude their applicability, and motivate our proposal of CATCH, a novel Context-bAsed meTa reinforcement learning (RL) algorithm for transferrable arChitecture searcH. The combination of meta-learning and RL allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces. CATCH utilizes a probabilistic encoder to encode task properties into latent context variables, which then guide CATCH's controller to quickly "catch" top-performing networks. The contexts also assist a network evaluator in filtering inferior candidates and speed up learning. Extensive experiments demonstrate CATCH's universality and search efficiency over many other widely-recognized algorithms. It is also capable of handling cross-domain architecture search as competitive networks on ImageNet, COCO, and Cityscapes are identified. This is the first work to our knowledge that proposes an efficient transferrable NAS solution while maintaining robustness across various settings.
Xin Chen, Yucheng Ouyang, Xin Chen, Zhenchuan Chen, Rongfen Lin, Xingyu Gao, Lifang Wang, Fang Li, Yin Liu, Honghui Shang, Haifeng Song
Molecular dynamics simulations have emerged as a potent tool for investigating the physical properties and kinetic behaviors of materials at the atomic scale, particularly in extreme conditions. Ab initio accuracy is now achievable with machine learning based interatomic potentials. With recent advancements in high-performance computing, highly accurate and large-scale simulations become feasible. This study introduces TensorMD, a new machine learning interatomic potential (MLIP) model that integrates physical principles and tensor diagrams. The tensor formalism provides a more efficient computation and greater flexibility for use with other scientific codes. Additionally, we proposed several portable optimization strategies and developed a highly optimized version for the new Sunway supercomputer. Our optimized TensorMD can achieve unprecedented performance on the new Sunway, enabling simulations of up to 52 billion atoms with a time-to-solution of 31 ps/step/atom, setting new records for HPC + AI + MD.
Xin Chen, Yue Xu, Yongcheng Wu, Yu-Ping Kuang, Qing Wang, Hang Chen, Shih-Chieh Hsu, Zhen Hu, Congqiao Li
A generic heavy Higgs has both dim-4 and effective dim-6 interactions with the Standard Model (SM) particles. The former has been the focus of LHC searches in all major Higgs production channels, just as the SM one, but with negative results so far. If the heavy Higgs is connected with Beyond Standard Model (BSM) physics at a few TeV scale, its dim-6 operators will play a very important role - they significantly enhance the Higgs momentum, and reduce the SM background in a special phase space corner to a level such that a heavy Higgs emerges, which is not possible with dim-4 operators only. We focus on the associated VH production channel, where the effect of dim-6 operators is the largest and the SM background is the lowest. Main search regions for this type of signal are identified, and substructure variables of boosted jets are employed to enhance the signal from backgrounds. The parameter space of these operators are scanned over, and expected exclusion regions with 300 fb$^{-1}$ and 3 ab$^{-1}$ LHC data are shown, if no BSM is present. The strategy given in this paper will shed light on a heavy Higgs which may be otherwise hiding in the present and future LHC data.
Xin Chen, Changhong Zhao, Na Li
With the increasing penetration of renewable energy resources, power systems face new challenges in balancing power supply and demand and maintaining the nominal frequency. This paper studies load control to handle these challenges. In particular, a fully distributed automatic load control (ALC) algorithm, which only needs local measurement and local communication, is proposed. We prove that the load control algorithm globally converges to an optimal operating point which minimizes the total disutility of users, restores the nominal frequency and the scheduled tie-line power flows, and respects the load capacity limits and the thermal constraints of transmission lines. It is further shown that the asymptotic convergence still holds even when inaccurate system parameters are used in the control algorithm. In addition, the global exponential convergence of the reduced ALC algorithm without considering the capacity limits is proved and leveraged to study the dynamical tracking performance and robustness of the algorithm. Lastly, the effectiveness, optimality, and robustness of the proposed algorithm are demonstrated via numerical simulations.
Xin Chen, Anqi Pang, Yang Wei, Lan Xui, Jingyi Yu
In this paper, we present TightCap, a data-driven scheme to capture both the human shape and dressed garments accurately with only a single 3D human scan, which enables numerous applications such as virtual try-on, biometrics and body evaluation. To break the severe variations of the human poses and garments, we propose to model the clothing tightness - the displacements from the garments to the human shape implicitly in the global UV texturing domain. To this end, we utilize an enhanced statistical human template and an effective multi-stage alignment scheme to map the 3D scan into a hybrid 2D geometry image. Based on this 2D representation, we propose a novel framework to predicted clothing tightness via a novel tightness formulation, as well as an effective optimization scheme to further reconstruct multi-layer human shape and garments under various clothing categories and human postures. We further propose a new clothing tightness dataset (CTD) of human scans with a large variety of clothing styles, poses and corresponding ground-truth human shapes to stimulate further research. Extensive experiments demonstrate the effectiveness of our TightCap to achieve high-quality human shape and dressed garments reconstruction, as well as the further applications for clothing segmentation, retargeting and animation.
Xin Chen, Raquel Esteban-Puyuelo, Linyang Li, Biplab Sanyal
Structural phase transitions between semiconductors and topological insulators have rich applications in nanoelectronics but are rarely found in two-dimensional (2D) materials. In this work, by combining ab initio computations and evolutionary structure search, we investigate two stable 2D forms of gold(I) telluride (Au$_{2}$Te) with square symmetry, noted as s(I)- and s(II)-Au$_{2}$Te. s(II)-Au$_{2}$Te is the global minimum structure and is a room-temperature topological insulator. s(I)-Au$_{2}$Te is a direct-gap semiconductor with high carrier mobilities and unusual in-plane negative Poisson's ratio. Both s(I) and s(II) phases have ultra-low Young's modulus, implying high flexibility. By applying a small tensile strain, s(II)-Au$_{2}$Te can be transformed into s(I)-Au$_{2}$Te. Hence, a structural phase transition from a room-temperature topological insulator to an auxetic semiconductor is found in the 2D forms of Au$_{2}$Te, which enables potential applications in phase-change electronic devices. Moreover, we elucidate the mechanism of the phase transition with the help of phonon spectra and group theory analysis.
Xin Chen, Qi Zhao, Xinyang Liu
With the fast development of Deep Learning techniques, Named Entity Recognition (NER) is becoming more and more important in the information extraction task. The greatest difficulty that the NER task faces is to keep the detectability even when types of NE and documents are unfamiliar. Realizing that the specificity information may contain potential meanings of a word and generate semantic-related features for word embedding, we develop a distribution-aware word embedding and implement three different methods to make use of the distribution information in a NER framework. And the result shows that the performance of NER will be improved if the word specificity is incorporated into existing NER methods.
Yuwen Qin, Ningbo Cai, Chen Gao, Yadong Zhang, Yonghong Cheng, Xin Chen
The precise estimate of remaining useful life (RUL) is vital for the prognostic analysis and predictive maintenance that can significantly reduce failure rate and maintenance costs. The degradation-related features extracted from the sensor streaming data with neural networks can dramatically improve the accuracy of the RUL prediction. The Temporal deep degradation network (TDDN) model is proposed to make the RUL prediction with the degradation-related features given by the one-dimensional convolutional neural network (1D CNN) feature extraction and attention mechanism. 1D CNN is used to extract the temporal features from the streaming sensor data. Temporal features have monotonic degradation trends from the fluctuating raw sensor streaming data. Attention mechanism can improve the RUL prediction performance by capturing the fault characteristics and the degradation development with the attention weights. The performance of the TDDN model is evaluated on the public C-MAPSS dataset and compared with the existing methods. The results show that the TDDN model can achieve the best RUL prediction accuracy in complex conditions compared to current machine learning models. The degradation-related features extracted from the high-dimension sensor streaming data demonstrate the clear degradation trajectories and degradation stages that enable TDDN to predict the turbofan-engine RUL accurately and efficiently.
Xin Chen, Yuwen Qin, Weidong Zhao, Qiming Yang, Ningbo Cai, Kai Wu
Accurate state-of-health (SOH) estimation is critical to guarantee the safety, efficiency and reliability of battery-powered applications. Most SOH estimation methods focus on the 0-100\% full state-of-charge (SOC) range that has similar distributions. However, the batteries in real-world applications usually work in the partial SOC range under shallow-cycle conditions and follow different degradation profiles with no labeled data available, thus making SOH estimation challenging. To estimate shallow-cycle battery SOH, a novel unsupervised deep transfer learning method is proposed to bridge different domains using self-attention distillation module and multi-kernel maximum mean discrepancy technique. The proposed method automatically extracts domain-variant features from charge curves to transfer knowledge from the large-scale labeled full cycles to the unlabeled shallow cycles. The CALCE and SNL battery datasets are employed to verify the effectiveness of the proposed method to estimate the battery SOH for different SOC ranges, temperatures, and discharge rates. The proposed method achieves a root-mean-square error within 2\% and outperforms other transfer learning methods for different SOC ranges. When applied to batteries with different operating conditions and from different manufacturers, the proposed method still exhibits superior SOH estimation performance. The proposed method is the first attempt at accurately estimating battery SOH under shallow-cycle conditions without needing a full-cycle characteristic test.
David Lindner, Xin Chen, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
We propose Convex Constraint Learning for Reinforcement Learning (CoCoRL), a novel approach for inferring shared constraints in a Constrained Markov Decision Process (CMDP) from a set of safe demonstrations with possibly different reward functions. While previous work is limited to demonstrations with known rewards or fully known environment dynamics, CoCoRL can learn constraints from demonstrations with different unknown rewards without knowledge of the environment dynamics. CoCoRL constructs a convex safe set based on demonstrations, which provably guarantees safety even for potentially sub-optimal (but safe) demonstrations. For near-optimal demonstrations, CoCoRL converges to the true safe set with no policy regret. We evaluate CoCoRL in gridworld environments and a driving simulation with multiple constraints. CoCoRL learns constraints that lead to safe driving behavior. Importantly, we can safely transfer the learned constraints to different tasks and environments. In contrast, alternative methods based on Inverse Reinforcement Learning (IRL) often exhibit poor performance and learn unsafe policies.
Xin Chen
May 17, 2013·quant-ph·PDF Quantum path interferences or resonances in multilevel dissipative quantum systems play an important and intriguing role in the transport processes of nanoscale systems. Many previous minimalistic models used to describe the quantum path interference driven by incoherent fields are based on the approximations including the second order perturbation for the weak coupling limit, the ad-hoc choices of two-time correlation functions and $\it{etc}$. On the other hand, the similar model to study the non-adiabatic molecular electronic excitation have been extensively developed and many efficient quantum molecular dynamics simulation schemes, such as the Ehrenfest scheme, have been proposed. In this paper, I aim to propose an unified model, extend the Ehrenfest scheme to study the interactions of system-light and system-phonon simultaneously and gain insight into and principles of the roles of quantum path interferences in the realistic molecular systems. I discuss how to derive the time-dependent stochastic Schr$\ddot{o}$dinger equation from the Ehrenfest scheme as a foundation to discuss the detailed balance for the weak coupling limit and therefore the quantum correction in the Ehrenfest scheme. Different from the master equation technique, the Ehrenfest scheme doesn't need any specific assumptions about spectral densities and two time correlation functions. With simple open two-level and three-level quantum systems, I show the effect of the quantum path interference on the steady state populations. Currently I only focus on the role of the phonon thermal reservoir. The electromagnetic field (solar light) will be modeled as a thermal reservoir and discussed in detail in the future paper.
Xin Chen, Yu Zhu, Hua Zhou, Liang Diao, Dongyan Wang
In this paper, we introduce a new and challenging large-scale food image dataset called "ChineseFoodNet", which aims to automatically recognizing pictured Chinese dishes. Most of the existing food image datasets collected food images either from recipe pictures or selfie. In our dataset, images of each food category of our dataset consists of not only web recipe and menu pictures but photos taken from real dishes, recipe and menu as well. ChineseFoodNet contains over 180,000 food photos of 208 categories, with each category covering a large variations in presentations of same Chinese food. We present our efforts to build this large-scale image dataset, including food category selection, data collection, and data clean and label, in particular how to use machine learning methods to reduce manual labeling work that is an expensive process. We share a detailed benchmark of several state-of-the-art deep convolutional neural networks (CNNs) on ChineseFoodNet. We further propose a novel two-step data fusion approach referred as "TastyNet", which combines prediction results from different CNNs with voting method. Our proposed approach achieves top-1 accuracies of 81.43% on the validation set and 81.55% on the test set, respectively. The latest dataset is public available for research and can be achieved at https://sites.google.com/view/chinesefoodnet.
Long Huo, Xin Chen, Kaiwen Li, Fengying Cai, Jürgen Kurths
El Niño-Southern Oscillation (ENSO) exhibits significant impacts on the frequency of extreme weather events and its socio-economic implications prevail on a global scale. However, a fundamental gap still exists in understanding the relationship between the ENSO and weather-related power outages in the continental United States. Through 24-year (2000-2023) composite and statistical analysis, our study reveals that higher power outage numbers (PONs) are observed from the developing winter to the decaying summer of La Niña phases. In particular, during the decaying spring, high La Niña intensity favors the occurrences of power outage over the west coast and east of the United States, by modulating the frequency of extreme precipitations and heatwaves. Furthermore, projected increasing heatwaves from the Coupled Model Intercomparison Project Phase 6 (CMIP6) indicate that spring-time PONs over the eastern United States occur about 11 times higher for the mid-term future (2041-2060) and almost 26 times higher for the long-term future (2081-2100), compared with 2000-2023. Our study provides a strong recommendation for building a more climate-resilient power system.
Yadong Zhang, Chenye Zou, Xin Chen
Battery discharge capacity forecasting is critically essential for the applications of lithium-ion batteries. The capacity degeneration can be treated as the memory of the initial battery state of charge from the data point of view. The streaming sensor data collected by battery management systems (BMS) reflect the usable battery capacity degradation rates under various operational working conditions. The battery capacity in different cycles can be measured with the temporal patterns extracted from the streaming sensor data based on the attention mechanism. The attention-based similarity regarding the first cycle can describe the battery capacity degradation in the following cycles. The deep degradation network (DDN) is developed with the attention mechanism to measure similarity and predict battery capacity. The DDN model can extract the degeneration-related temporal patterns from the streaming sensor data and perform the battery capacity prediction efficiently online in real-time. Based on the MIT-Stanford open-access battery aging dataset, the root-mean-square error of the capacity estimation is 1.3 mAh. The mean absolute percentage error of the proposed DDN model is 0.06{\%}. The DDN model also performance well in the Oxford Battery Degradation Dataset with dynamic load profiles. Therefore, the high accuracy and strong robustness of the proposed algorithm are verified.
Xin Chen, Wenbin Lu, Shu Yang, Dipankar Bandyopadhyay
While the classic off-policy evaluation (OPE) literature commonly assumes decision time points to be evenly spaced for simplicity, in many real-world scenarios, such as those involving user-initiated visits, decisions are made at irregularly-spaced and potentially outcome-dependent time points. For a more principled evaluation of the dynamic policies, this paper constructs a novel OPE framework, which concerns not only the state-action process but also an observation process dictating the time points at which decisions are made. The framework is closely connected to the Markov decision process in computer science and with the renewal process in the statistical literature. Within the framework, two distinct value functions, derived from cumulative reward and integrated reward respectively, are considered, and statistical inference for each value function is developed under revised Markov and time-homogeneous assumptions. The validity of the proposed method is further supported by theoretical results, simulation studies, and a real-world application from electronic health records (EHR) evaluating periodontal disease treatments.
Xin Chen, Jorge I. Poveda, Na Li
This paper introduces a class of model-free feedback methods for solving generic constrained optimization problems where the specific mathematical forms of the objective and constraint functions are not available. The proposed methods, termed Projected Zeroth-Order (P-ZO) dynamics, incorporate projection maps into a class of continuous-time model-free dynamics that make use of periodic dithering for the purpose of gradient learning. In particular, the proposed P-ZO algorithms can be interpreted as new extremum-seeking algorithms that autonomously drive an unknown system toward a neighborhood of the set of solutions of an optimization problem using only output feedback, while systematically guaranteeing that the input trajectories remain in a feasible set for all times. In this way, the P-ZO algorithms can properly handle hard and asymptotical constraints in model-free optimization problems without using penalty terms or barrier functions. Moreover, the proposed dynamics have suitable robustness properties with respect to small bounded additive disturbances on the states and dynamics, a property that is fundamental for practical real-world implementations. Additional tracking results for time-varying and switching cost functions are also derived under stronger convexity and smoothness assumptions and using tools from hybrid dynamical systems. Numerical examples are presented throughout the paper to illustrate the above results.
Xin Chen, Andy Sun, Wenbo Shi, Na Li
To facilitate effective decarbonization of the electric power sector, this paper introduces the generic Carbon-aware Optimal Power Flow (C-OPF) method for power system decision-making that considers demand-side carbon accounting and emission management. Built upon the classic optimal power flow (OPF) model, the C-OPF method incorporates carbon emission flow equations and constraints, as well as carbon-related objectives, to jointly optimize power flow and carbon flow. In particular, this paper establishes the feasibility and solution uniqueness of the carbon emission flow equations, and proposes modeling and linearization techniques to address the issues of undetermined power flow directions and bilinear terms in the C-OPF model. Additionally, two novel carbon emission models, together with the carbon accounting schemes, for energy storage systems are developed and integrated into the C-OPF model. Numerical simulations demonstrate the characteristics and effectiveness of the C-OPF method, in comparison with OPF solutions.
Xin Chen
Sep 28, 2025·quant-ph·PDF Nonlinear optics underpins quantum photonics by enabling the generation and control of quantum states of light. We present new applications of optical resonators as mode selectors in nonlinear processes. First, we show that cavity-enhanced spontaneous parametric down-conversion can generate spectrally uncorrelated photon pairs with improved decorrelation and wavelength flexibility. Second, we demonstrate that a cavity-assisted sum-frequency generation process realizes a quantum pulse gate with high-resolution temporal-mode selectivity and precise spectral control. Our theoretical framework provides a general methodology for analyzing cavity-enhanced nonlinear processes and highlights the versatility of optical resonators as powerful tools for engineering quantum light.
Xin Chen, Zhibin Ye
Feb 28, 2025·quant-ph·PDF Quantum illumination leverages entanglement to surpass classical target detection, even in high-noise environments. Remarkably, its quantum advantage persists despite entanglement degradation caused by environmental decoherence. A central challenge lies in designing optimal receivers to exploit this advantage, with the correlation-to-displacement conversion module emerging as a promising candidate. However, the practical implementation of the conversion module faces technical hurdles, primarily due to the vast number of modes involved. In this work, we address these challenges by proposing a frequency-mode entangled source with matched photon numbers, a heterodyne detection scheme for the returned signals across vast modes, and a cavity-enhanced quantum pulse gate for programmable mode processing. This integrated framework paves the way for the realization of practical quantum illumination systems.
Xin Chen, Yunhai Wang, Huaiwei Bao, Kecheng Lu, Jaemin Jo, Chi-Wing Fu, Jean-Daniel Fekete
We present a novel visualization-driven illumination model for density plots, a new technique to enhance density plots by effectively revealing the detailed structures in high- and medium-density regions and outliers in low-density regions, while avoiding artifacts in the density field's colors. When visualizing large and dense discrete point samples, scatterplots and dot density maps often suffer from overplotting, and density plots are commonly employed to provide aggregated views while revealing underlying structures. Yet, in such density plots, existing illumination models may produce color distortion and hide details in low-density regions, making it challenging to look up density values, compare them, and find outliers. The key novelty in this work includes (i) a visualization-driven illumination model that inherently supports density-plot-specific analysis tasks and (ii) a new image composition technique to reduce the interference between the image shading and the color-encoded density values. To demonstrate the effectiveness of our technique, we conducted a quantitative study, an empirical evaluation of our technique in a controlled study, and two case studies, exploring twelve datasets with up to two million data point samples.