Searcharxiv⌕ Search

arXiv subjects

Zhen Huang

Publications and source records attributed to Zhen Huang.

At least 145 records · Page 8Linked to original sources
arXiv2022

Efficient Frozen Gaussian Sampling Algorithms for Nonadiabatic Quantum Dynamics at Metal Surfaces

In this article, we propose a Frozen Gaussian Sampling (FGS) algorithm for simulating nonadiabatic quantum dynamics at metal surfaces with a continuous spectrum. This method consists of a Monte-Carlo algorithm for sampling the initial wave packets on the phase space and a surface-hopping type stochastic time propagation scheme for the wave packets. We prove that to reach a certain accuracy threshold, the sample size required is independent of both the semiclassical parameter $\varepsilon$ and the number of metal orbitals $N$, which makes it one of the most promising methods to study the nonadiabatic dynamics. The algorithm and its convergence properties are also validated numerically. Furthermore, we carry out numerical experiments including exploring the nuclei dynamics, electron transfer and finite-temperature effects, and demonstrate that our method captures the physics which can not be captured by classical surface hopping trajectories.

physics.comp-ph↗
arXiv2022

Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization

Cloth-Changing person re-identification (CC-ReID) aims at matching the same person across different locations over a long-duration, e.g., over days, and therefore inevitably meets challenge of changing clothing. In this paper, we focus on handling well the CC-ReID problem under a more challenging setting, i.e., just from a single image, which enables high-efficiency and latency-free pedestrian identify for real-time surveillance applications. Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID. GI-ReID adopts a two-stream architecture that consists of a image ReID-Stream and an auxiliary gait recognition stream (Gait-Stream). The Gait-Stream, that is discarded in the inference for high computational efficiency, acts as a regulator to encourage the ReID-Stream to capture cloth-invariant biometric motion features during the training. To get temporal continuous motion cues from a single image, we design a Gait Sequence Prediction (GSP) module for Gait-Stream to enrich gait information. Finally, a high-level semantics consistency over two streams is enforced for effective knowledge regularization. Experiments on multiple image-based Cloth-Changing ReID benchmarks, e.g., LTCC, PRCC, Real28, and VC-Clothes, demonstrate that GI-ReID performs favorably against the state-of-the-arts. Codes are available at https://github.com/jinx-USTC/GI-ReID.

cs.CV↗
arXiv2022

SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples

Unsupervised sentence embedding aims to obtain the most appropriate embedding for a sentence to reflect its semantic. Contrastive learning has been attracting developing attention. For a sentence, current models utilize diverse data augmentation methods to generate positive samples, while consider other independent sentences as negative samples. Then they adopt InfoNCE loss to pull the embeddings of positive pairs gathered, and push those of negative pairs scattered. Although these models have made great progress on sentence embedding, we argue that they may suffer from feature suppression. The models fail to distinguish and decouple textual similarity and semantic similarity. And they may overestimate the semantic similarity of any pairs with similar textual regardless of the actual semantic difference between them. This is because positive pairs in unsupervised contrastive learning come with similar and even the same textual through data augmentation. To alleviate feature suppression, we propose contrastive learning for unsupervised sentence embedding with soft negative samples (SNCSE). Soft negative samples share highly similar textual but have surely and apparently different semantic with the original samples. Specifically, we take the negation of original sentences as soft negative samples, and propose Bidirectional Margin Loss (BML) to introduce them into traditional contrastive learning framework, which merely involves positive and negative samples. Our experimental results show that SNCSE can obtain state-of-the-art performance on semantic textual similarity (STS) task with average Spearman's correlation coefficient of 78.97% on BERTbase and 79.23% on RoBERTabase. Besides, we adopt rank-based error analysis method to detect the weakness of SNCSE for future study.

cs.CL↗
arXiv2021

Reversible modulation of metal-insulator transition in VO2 via chemically-induced oxygen migration

Metal-insulator transitions (MIT),an intriguing correlated phenomenon induced by the subtle competition of the electrons' repulsive Coulomb interaction and kinetic energy, is of great potential use for electronic applications due to the dramatic change in resistivity. Here, we demonstrate a reversible control of MIT in VO2 films via oxygen stoichiometry engineering. By facilely depositing and dissolving a water-soluble yet oxygen-active Sr3Al2O6 capping layer atop the VO2 at room temperature, oxygen ions can reversibly migrate between VO2 and Sr3Al2O6, resulting in a gradual suppression and a complete recovery of MIT in VO2. The migration of the oxygen ions is evidenced in a combination of transport measurement, structural characterization and first-principles calculations. This approach of chemically-induced oxygen migration using a water-dissolvable adjacent layer could be useful for advanced electronic and iontronic devices and studying oxygen stoichiometry effects on the MIT.

cond-mat.mtrl-sci↗
arXiv2021

Exploring Retraining-Free Speech Recognition for Intra-sentential Code-Switching

In this paper, we present our initial efforts for building a code-switching (CS) speech recognition system leveraging existing acoustic models (AMs) and language models (LMs), i.e., no training required, and specifically targeting intra-sentential switching. To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised. Specifically, we have designed an automatic approach to obtain high quality pronunciation of foreign language (FL) words in the native language (NL) phoneme set using existing acoustic phone decoders and an LSTM-based grapheme-to-phoneme (G2P) model. Improved accented pronunciations have thus been obtained by learning foreign pronunciations directly from data. Furthermore, a code-switching LM was deployed by converting the original NL LM into a CS LM using translated word pairs and borrowing statistics for the NL LM. Experimental evidence clearly demonstrates that our approach better deals with accented foreign pronunciations than techniques based on human labeling. Moreover, our best system achieves a 55.5% relative word error rate reduction from 34.4%, obtained with a conventional monolingual ASR system, to 15.3% on an intra-sentential CS task without harming the monolingual recognition accuracy.

eess.AS↗
arXiv2021

Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition

Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely used for this task due to their powerful capability to model graph data. The topology of the adjacency graph is a key factor for modeling the correlations of the input skeletons. Thus, previous methods mainly focus on the design/learning of the graph topology. But once the topology is learned, only a single-scale feature and one transformation exist in each layer of the networks. Many insights, such as multi-scale information and multiple sets of transformations, that have been proven to be very effective in convolutional neural networks (CNNs), have not been investigated in GCNs. The reason is that, due to the gap between graph-structured skeleton data and conventional image/video data, it is very challenging to embed these insights into GCNs. To overcome this gap, we reinvent the split-transform-merge strategy in GCNs for skeleton sequence processing. Specifically, we design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths. Extensive experiments demonstrate that our network outperforms state-of-the-art methods by a significant margin with only 1/5 of the parameters and 1/10 of the FLOPs. Code is available at https://github.com/yellowtownhz/STIGCN.

cs.CV↗
arXiv2021

Next Waves in Veridical Network Embedding

Embedding nodes of a large network into a metric (e.g., Euclidean) space has become an area of active research in statistical machine learning, which has found applications in natural and social sciences. Generally, a representation of a network object is learned in a Euclidean geometry and is then used for subsequent tasks regarding the nodes and/or edges of the network, such as community detection, node classification and link prediction. Network embedding algorithms have been proposed in multiple disciplines, often with domain-specific notations and details. In addition, different measures and tools have been adopted to evaluate and compare the methods proposed under different settings, often dependent of the downstream tasks. As a result, it is challenging to study these algorithms in the literature systematically. Motivated by the recently proposed Veridical Data Science (VDS) framework, we propose a framework for network embedding algorithms and discuss how the principles of predictability, computability and stability apply in this context. The utilization of this framework in network embedding holds the potential to motivate and point to new directions for future research.

stat.ML↗
arXiv2021

Revisiting Knowledge Distillation: An Inheritance and Exploration Framework

Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged information on similarities/consistency between the class distributions or intermediate feature representations of the teacher model and the student model. However, directly pushing the student model to mimic the probabilities/features of the teacher model to a large extent limits the student model in learning undiscovered knowledge/features. In this paper, we propose a novel inheritance and exploration knowledge distillation framework (IE-KD), in which a student model is split into two parts - inheritance and exploration. The inheritance part is learned with a similarity loss to transfer the existing learned knowledge from the teacher model to the student model, while the exploration part is encouraged to learn representations different from the inherited ones with a dis-similarity loss. Our IE-KD framework is generic and can be easily combined with existing distillation or mutual learning methods for training deep neural networks. Extensive experiments demonstrate that these two parts can jointly push the student model to learn more diversified and effective representations, and our IE-KD can be a general technique to improve the student network to achieve SOTA performance. Furthermore, by applying our IE-KD to the training of two networks, the performance of both can be improved w.r.t. deep mutual learning. The code and models of IE-KD will be make publicly available at https://github.com/yellowtownhz/IE-KD.

cs.LG↗
arXiv2020

Kernel Partial Correlation Coefficient -- a Measure of Conditional Dependence

In this paper we propose and study a class of simple, nonparametric, yet interpretable measures of conditional dependence between two random variables $Y$ and $Z$ given a third variable $X$, all taking values in general topological spaces. The population version of any of these measures captures the strength of conditional dependence and it is 0 if and only if $Y$ and $Z$ are conditionally independent given $X$, and 1 if and only if $Y$ is a measurable function of $Z$ and $X$. Thus, our measure -- which we call kernel partial correlation (KPC) coefficient -- can be thought of as a nonparametric generalization of the partial correlation coefficient that possesses the above properties when $(X,Y,Z)$ is jointly normal. We describe two consistent methods of estimating KPC. Our first method utilizes the general framework of geometric graphs, including $K$-nearest neighbor graphs and minimum spanning trees. A sub-class of these estimators can be computed in near linear time and converges at a rate that automatically adapts to the intrinsic dimension(s) of the underlying distribution(s). Our second strategy involves direct estimation of conditional mean embeddings using cross-covariance operators in the reproducing kernel Hilbert spaces. Using these empirical measures we develop forward stepwise (high-dimensional) nonlinear variable selection algorithms. We show that our algorithm, using the graph-based estimator, yields a provably consistent model-free variable selection procedure, even in the high-dimensional regime when the number of covariates grows exponentially with the sample size, under suitable sparsity assumptions. Extensive simulation and real-data examples illustrate the superior performance of our methods compared to existing procedures. The recent conditional dependence measure proposed by Azadkia and Chatterjee (2019) can be viewed as a special case of our general framework.

stat.ME↗
arXiv2020

Phase diagram and superconducting dome of infinite-layer $\mathrm{Nd_{1-x}Sr_{x}NiO_{2}}$ thin films

Infinite-layer Nd1-xSrxNiO2 thin films with Sr doping level x from 0.08 to 0.3 were synthesized and investigated. We found a superconducting dome to be between 0.12 and 0.235 which is accompanied by a weakly insulating behaviour in both underdoped and overdoped regimes. The dome is akin to that in the electron-doped 214-type and infinite-layer cuprate superconductors. For x higher than 0.18, the normal state Hall coefficient ($R_{H}$) changes the sign from negative to positive as the temperature decreases. The temperature of the sign changes monotonically decreases with decreasing x from the overdoped side and approaches the superconducting dome at the mid-point, suggesting a reconstruction of the Fermi surface as the dopant concentration changes across the center of the dome.

cond-mat.supr-con↗
arXiv2020

Topological Hall Effect and Skyrmion-like Bubbles at a Charge-transfer Interface

Exploring exotic interface magnetism due to charge transfer and strong spin-orbit coupling has profound application in future development of spintronic memory. Here, the emergence, tuning and interpretation of hump-shape Hall Effect from a CaMnO3/CaIrO3/CaMnO3 trilayer structure are studied in detail. The hump signal can be recognized as Topological Hall Effect suggesting the presence of Skyrmion-like magnetic bubbles; but the debated alternative interpretation where the signal being an artefact between two cancelling Anomalous Hall Effect loops is also discussed. Firstly, by tilting the magnetic field direction, the evolution of Hall signal suggests transformation of the bubbles topology into a more trivial kind. Secondly, by varying the thickness of CaMnO3, the optimal thicknesses for the hump signal emergence are found, suggesting a tuning of charge transfer fraction. Using high-resolution transmission electron microscopy, a stacking fault is also identified, which distinguishes the top and bottom CaMnO3/CaIrO3 interfaces in terms of charge transfer fraction and possible interfacial Dzyaloshinskii-Moriya Interaction. Finally, a spin-transfer torque experiment revealed a low threshold current density of ~10^9 A/m^2 for initiating the motion of bubbles. This discovery opens a possible route for integrating Skyrmions with antiferromagnetic spintronics.

cond-mat.mes-hall↗
arXiv2020

Characteristic Lengths of Interlayer Charge-Transfer in Correlated Oxide Heterostructures

Using interlayer interaction to control functional heterostructures with atomic-scale designs has become one of the most effective interface-engineering strategies nowadays. Here, we demonstrate the effect of a crystalline LaFeO3 buffer layer on amorphous and crystalline LaAlO3/SrTiO3 heterostructures. The LaFeO3 buffer layer acts as an energetically favored electron acceptor in both LaAlO3/SrTiO3 systems, resulting in modulation of interfacial carrier density and hence metal-to-insulator transition. For amorphous and crystalline LaAlO3/SrTiO3 heterostructures, the metal-to-insulator transition is found when the LaFeO3 layer thickness crosses 3 and 6 unit cells, respectively. Such different critical LaFeO3 thicknesses are explained in terms of distinct characteristic lengths of the redox-reaction-mediated and polar-catastrophe-dominated charge transfer, controlled by the interfacial atomic contact and Thomas-Fermi screening effect, respectively. Our results not only shed light on the complex interlayer charge transfer across oxide heterostructures but also provides a new route to precisely tailor the charge-transfer process at a functional interface.

cond-mat.mtrl-sci↗
arXiv2020

SNDCNN: Self-normalizing deep CNNs with scaled exponential linear units for speech recognition

Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN). Inspired by Self- Normalizing Neural Networks, we propose the self-normalizing deep CNN (SNDCNN) based acoustic model topology, by removing the SC/BN and replacing the typical RELU activations with scaled exponential linear unit (SELU) in ResNet-50. SELU activations make the network self-normalizing and remove the need for both shortcut connections and batch normalization. Compared to ResNet- 50, we can achieve the same or lower (up to 4.5% relative) word error rate (WER) while boosting both training and inference speed by 60%-80%. We also explore other model inference optimization schemes to further reduce latency for production use.

cs.LG↗
arXiv2019

Language Model-Driven Unsupervised Neural Machine Translation

Unsupervised neural machine translation(NMT) is associated with noise and errors in synthetic data when executing vanilla back-translations. Here, we explicitly exploits language model(LM) to drive construction of an unsupervised NMT system. This features two steps. First, we initialize NMT models using synthetic data generated via temporary statistical machine translation(SMT). Second, unlike vanilla back-translation, we formulate a weight function, that scores synthetic data at each step of subsequent iterative training; this allows unsupervised training to an improved outcome. We present the detailed mathematical construction of our method. Experimental WMT2014 English-French, and WMT2016 English-German and English-Russian translation tasks revealed that our method outperforms the best prior systems by more than 3 BLEU points.

cs.CL↗
arXiv2019

SubCharacter Chinese-English Neural Machine Translation with Wubi encoding

Neural machine translation (NMT) is one of the best methods for understanding the differences in semantic rules between two languages. Especially for Indo-European languages, subword-level models have achieved impressive results. However, when the translation task involves Chinese, semantic granularity remains at the word and character level, so there is still need more fine-grained translation model of Chinese. In this paper, we introduce a simple and effective method for Chinese translation at the sub-character level. Our approach uses the Wubi method to translate Chinese into English; byte-pair encoding (BPE) is then applied. Our method for Chinese-English translation eliminates the need for a complicated word segmentation algorithm during preprocessing. Furthermore, our method allows for sub-character-level neural translation based on recurrent neural network (RNN) architecture, without preprocessing. The empirical results show that for Chinese-English translation tasks, our sub-character-level model has a comparable BLEU score to the subword model, despite having a much smaller vocabulary. Additionally, the small vocabulary is highly advantageous for NMT model compression.

cs.CL↗
arXiv2019

A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning

Rapid progress has been made in the field of reading comprehension and question answering, where several systems have achieved human parity in some simplified settings. However, the performance of these models degrades significantly when they are applied to more realistic scenarios, such as answers involve various types, multiple text strings are correct answers, or discrete reasoning abilities are required. In this paper, we introduce the Multi-Type Multi-Span Network (MTMSN), a neural reading comprehension model that combines a multi-type answer predictor designed to support various answer types (e.g., span, count, negation, and arithmetic expression) with a multi-span extraction method for dynamically producing one or multiple text spans. In addition, an arithmetic expression reranking mechanism is proposed to rank expression candidates for further confirming the prediction. Experiments show that our model achieves 79.9 F1 on the DROP hidden test set, creating new state-of-the-art results. Source code\footnote{\url{https://github.com/huminghao16/MTMSN}} is released to facilitate future work.

cs.CL↗
arXiv2019

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is inefficient since the input is re-encoded within each module, and is unable to leverage upstream components to help downstream training. In this work, we present RE$^3$QA, a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer. Unlike previous pipelined approaches, RE$^3$QA shares contextualized text representation across different components, and is carefully designed to use high-quality upstream outputs (e.g., retrieved context or candidate answers) for directly supervising downstream modules (e.g., the reader or the reranker). As a result, the whole network can be trained end-to-end to avoid the context inconsistency problem. Experiments show that our model outperforms the pipelined baseline and achieves state-of-the-art results on two versions of TriviaQA and two variants of SQuAD.

cs.CL↗