arXiv subjects

Yang Zhong

Publications and source records attributed to Yang Zhong.

At least 55 records · Page 3Linked to original sources

arXiv2023

Accelerating the electronic-structure calculation of magnetic systems by equivariant neural networks

Complex spin-spin interactions in magnets can often lead to magnetic superlattices with complex local magnetic arrangements, and many of the magnetic superlattices have been found to possess non-trivial topological electronic properties. Due to the huge size and complex magnetic moment arrangement of the magnetic superlattices, it is a great challenge to perform a direct DFT calculation on them. In this work, an equivariant deep learning framework is designed to accelerate the electronic calculation of magnetic systems by exploiting both the equivariant constraints of the magnetic Hamiltonian matrix and the physical rules of spin-spin interactions. This framework can bypass the costly self-consistent iterations and build a direct mapping from a magnetic configuration to the ab initio Hamiltonian matrix. After training on the magnets with random magnetic configurations, our model achieved high accuracy on the test structures outside the training set, such as spin spiral and non-collinear antiferromagnetic configurations. The trained model is also used to predict the energy bands of a skyrmion configuration of NiBrI containing thousands of atoms, showing the high efficiency of our model on large magnetic superlattices.

cond-mat.mtrl-sci↗

arXiv2023

Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking

We propose a simple approach for the abstractive summarization of long legal opinions that considers the argument structure of the document. Legal opinions often contain complex and nuanced argumentation, making it challenging to generate a concise summary that accurately captures the main points of the legal opinion. Our approach involves using argument role information to generate multiple candidate summaries, then reranking these candidates based on alignment with the document's argument structure. We demonstrate the effectiveness of our approach on a dataset of long legal opinions and show that it outperforms several strong baselines.

cs.CL↗

arXiv2023

Spin-Dependent Graph Neural Network Potential for Magnetic Materials

The development of machine learning interatomic potentials has immensely contributed to the accuracy of simulations of molecules and crystals. However, creating interatomic potentials for magnetic systems that account for both magnetic moments and structural degrees of freedom remains a challenge. This work introduces SpinGNN, a spin-dependent interatomic potential approach that employs the graph neural network (GNN) to describe magnetic systems. SpinGNN consists of two types of edge GNNs: Heisenberg edge GNN (HEGNN) and spin-distance edge GNN (SEGNN). HEGNN is tailored to capture Heisenberg-type spin-lattice interactions, while SEGNN accurately models multi-body and high-order spin-lattice coupling. The effectiveness of SpinGNN is demonstrated by its exceptional precision in fitting a high-order spin Hamiltonian and two complex spin-lattice Hamiltonians with great precision. Furthermore, it successfully models the subtle spin-lattice coupling in BiFeO3 and performs large-scale spin-lattice dynamics simulations, predicting its antiferromagnetic ground state, magnetic phase transition, and domain wall energy landscape with high accuracy. Our study broadens the scope of graph neural network potentials to magnetic systems, serving as a foundation for carrying out large-scale spin-lattice dynamic simulations of such systems.

physics.comp-ph↗

arXiv2023

Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids

Using the message-passing mechanism in machine learning (ML) instead of self-consistent iterations to directly build the mapping from structures to electronic Hamiltonian matrices will greatly improve the efficiency of density functional theory (DFT) calculations. In this work, we proposed a general analytic Hamiltonian representation in an E(3) equivariant framework, which can fit the ab initio Hamiltonian of molecules and solids by a complete data-driven method and are equivariant under rotation, space inversion, and time reversal operations. Our model reached state-of-the-art precision in the benchmark test and accurately predicted the electronic Hamiltonian matrices and related properties of various periodic and aperiodic systems, showing high transferability and generalization ability. This framework provides a general transferable model that can be used to accelerate the electronic structure calculations on different large systems with the same network weights trained on small structures.

physics.comp-ph↗

arXiv2023

Accelerating the calculation of electron-phonon coupling by machine learning methods

Electron-phonon coupling (EPC) plays an important role in many fundamental physical phenomena, but the high computational cost of the EPC matrix hinders the theoretical research on them. In this paper, an analytical formula is derived to calculate the EPC matrix in terms of the Hamiltonian and its gradient in the nonorthogonal atomic orbital bases. The recently-developed E(3) equivariant neural network is used to directly predict the Hamiltonian and its gradient needed by the formula, thus bypassing the expensive self-consistent iterations in DFT. The correctness of the proposed EPC calculation formula and the accuracy of the predicted EPC values of the network are illustrated by the tests on a water molecule and a MoS2 crystal.

physics.comp-ph↗

arXiv2022

Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions

Though many algorithms can be used to automatically summarize legal case decisions, most fail to incorporate domain knowledge about how important sentences in a legal decision relate to a representation of its document structure. For example, analysis of a legal case summarization dataset demonstrates that sentences serving different types of argumentative roles in the decision appear in different sections of the document. In this work, we propose an unsupervised graph-based ranking model that uses a reweighting algorithm to exploit properties of the document structure of legal case decisions. We also explore the impact of using different methods to compute the document structure. Results on the Canadian Legal Case Law dataset show that our proposed method outperforms several strong baselines.

cs.CL↗

arXiv2022

Electronically phase separated nano-network in antiferromagnetic insulating LaMnO3/PrMnO3/CaMnO3 tricolor superlattice

Strongly correlated materials often exhibit an electronic phase separation (EPS) phenomena whose domain pattern is random in nature. The ability to control the spatial arrangement of the electronic phases at microscopic scales is highly desirable for tailoring their macroscopic properties and/or designing novel electronic devices. Here we report the formation of EPS nanoscale network in a mono-atomically stacked LaMnO3/CaMnO3/PrMnO3 superlattice grown on SrTiO3 (STO) (001) substrate, which is known to have an antiferromagnetic (AFM) insulating ground state. The EPS nano-network is a consequence of an internal strain relaxation triggered by the structural domain formation of the underlying STO substrate at low temperatures. The same nanoscale network pattern can be reproduced upon temperature cycling allowing us to employ different local imaging techniques to directly compare the magnetic and transport state of a single EPS domain. Our results confirm the one-to-one correspondence between ferromagnetic (AFM) to metallic (insulating) state in manganite. It also represents a significant step in a paradigm shift from passively characterizing EPS in strongly correlated systems to actively engaging in its manipulation.

cond-mat.str-el↗

arXiv2022

Modeling Intensification for Sign Language Generation: A Computational Approach

End-to-end sign language generation models do not accurately represent the prosody in sign language. A lack of temporal and spatial variations leads to poor-quality generated presentations that confuse human interpreters. In this paper, we aim to improve the prosody in generated sign languages by modeling intensification in a data-driven manner. We present different strategies grounded in linguistics of sign language that inform how intensity modifiers can be represented in gloss annotations. To employ our strategies, we first annotate a subset of the benchmark PHOENIX-14T, a German Sign Language dataset, with different levels of intensification. We then use a supervised intensity tagger to extend the annotated dataset and obtain labels for the remaining portion of it. This enhanced dataset is then used to train state-of-the-art transformer models for sign language generation. We find that our efforts in intensification modeling yield better results when evaluated with automatic metrics. Human evaluation also indicates a higher preference of the videos generated using our model.

cs.CL↗

arXiv2022

A Machine Learning Generative Method for Automating Antenna Design and Optimization

To facilitate the antenna design with the aid of computer, one of the practices in consumer electronic industry is to model and optimize antenna performances with a simplified antenna geometric scheme. Traditional antenna modeling requires profound prior knowledge of electromagnetics in order to achieve a good design which satisfies the performance specifications from both antenna and product designs. The ease of handling multidimensional optimization problems and the less dependence on domain knowledge and experience are the key to achieve the popularity of simulation driven antenna design and optimization for the industry. In this paper, we introduce a flexible geometric scheme with the concept of mesh network that can form any arbitrary shape by connecting different nodes. For such problems with high dimensional parameters, we propose a machine learning based generative method to assist the searching of optimal solutions. It consists of discriminators and generators. The discriminators are used to predict the performance of geometric models, and the generators to create new candidates that will pass the discriminators. Moreover, an evolutionary criterion approach is proposed for further improving the efficiency of our method. Finally, not only optimal solutions can be found, but also the well trained generators can be used to automate future antenna design and optimization. For a dual resonance antenna design with wide bandwidth, our proposed method is in par with Trust Region Framework and much better than the other mature machine learning algorithms including the widely used Genetic Algorithm and Particle Swarm Optimization. When there is no wide bandwidth requirement, it is better than Trust Region Framework.

cs.LG↗

arXiv2022

Edge-based Tensor prediction via graph neural networks

Message-passing neural networks (MPNN) have shown extremely high efficiency and accuracy in predicting the physical properties of molecules and crystals, and are expected to become the next-generation material simulation tool after the density functional theory (DFT). However, there is currently a lack of a general MPNN framework for directly predicting the tensor properties of the crystals. In this work, a general framework for the prediction of tensor properties was proposed: the tensor property of a crystal can be decomposed into the average of the tensor contributions of all the atoms in the crystal, and the tensor contribution of each atom can be expanded as the sum of the tensor projections in the directions of the edges connecting the atoms. On this basis, the edge-based expansions of force vectors, Born effective charges (BECs), dielectric (DL) and piezoelectric (PZ) tensors were proposed. These expansions are rotationally equivariant, while the coefficients in these tensor expansions are rotationally invariant scalars which are similar to physical quantities such as formation energy and band gap. The advantage of this tensor prediction framework is that it does not require the network itself to be equivariant. Therefore, in this work, we directly designed the edge-based tensor prediction graph neural network (ETGNN) model on the basis of the invariant graph neural network to predict tensors. The validity and high precision of this tensor prediction framework were shown by the tests of ETGNN on the extended systems, random perturbed structures and JARVIS-DFT datasets. This tensor prediction framework is general for nearly all the GNNs and can achieve higher accuracy with more advanced GNNs in the future.

cond-mat.mtrl-sci↗

arXiv2021

Neural CRF Model for Sentence Alignment in Text Simplification

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity. Experiments demonstrate that our proposed approach outperforms all the previous work on monolingual sentence alignment task by more than 5 points in F1. We apply our CRF aligner to construct two new text simplification datasets, Newsela-Auto and Wiki-Auto, which are much larger and of better quality compared to the existing datasets. A Transformer-based seq2seq model trained on our datasets establishes a new state-of-the-art for text simplification in both automatic and human evaluation.

cs.CL↗

arXiv2020

Discourse Level Factors for Sentence Deletion in Text Simplification

This paper presents a data-driven study focusing on analyzing and predicting sentence deletion -- a prevalent but understudied phenomenon in document simplification -- on a large English text simplification corpus. We inspect various document and discourse factors associated with sentence deletion, using a new manually annotated sentence alignment corpus we collected. We reveal that professional editors utilize different strategies to meet readability standards of elementary and middle schools. To predict whether a sentence will be deleted during simplification to a certain level, we harness automatically aligned data to train a classification model. Evaluated on our manually annotated data, our best models reached F1 scores of 65.2 and 59.7 for this task at the levels of elementary and middle school, respectively. We find that discourse level factors contribute to the challenging task of predicting sentence deletion for simplification.

cs.CL↗

arXiv2020

Regularizing CNN Transfer Learning with Randomised Regression

This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this context are commonly due to the use of additional regularization objectives. They guide the training away from the target task using some forms of concrete tasks. Unlike those related approaches, we suggest that an objective without a concrete goal can still serve well as a regularized. In particular, we demonstrate Pseudo-task Regularization (PtR) which dynamically regularizes a network by simply attempting to regress image representations to pseudo-regression targets during fine-tuning. That is, a CNN is efficiently regularized without additional resources of data or prior domain expertise. In sum, the proposed PtR provides: a) an alternative for network regularization without dependence on the design of concrete regularization objectives or extra annotations; b) a dynamically adjusted and maintained strength of regularization effect by balancing the gradient norms between objectives on-line. Through numerous experiments, surprisingly, the improvements on classification accuracy by PtR are shown greater or on a par to the recent state-of-the-art methods.

cs.CV↗

arXiv2019

Thermal boundary resistance predictions with non-equilibrium Green's function and molecular dynamics simulations

The non-equilibrium Green's function (NEGF) method with Büttiker probe scattering self-energies is assessed by comparing its predictions for the thermal boundary resistance with molecular dynamics (MD) simulations. For simplicity, the interface of Si/heavy-Si is considered, where heavy-Si differs from Si only in the mass value. With Büttiker probe scattering parameters tuned against MD in homogeneous Si, the NEGF-predicted thermal boundary resistance quantitatively agrees with MD for wide mass ratios. Artificial resistances that the unaltered Landauer approach yield at virtual interfaces in homogeneous systems are absent in the present NEGF approach. Spectral information result from NEGF in its natural representation without further transformations. The spectral results show that the scattering between different phonon modes plays a crucial role in thermal transport across interfaces. Büttiker probes provide an efficient and reliable way to include anharmonicity in phonon related NEGF. NEGF including the Büttiker probes can reliably predict phonon transport across interfaces and at finite temperatures.

physics.app-ph↗

arXiv2019

Energy loss of heavy and light quarks in holographic magnetized background

We systematically study holographic effects on the magnetic field dependence of the drag force, diffusion coefficient, jet quenching parameter of heavy quarks and the shooting string energy loss of light quarks in the RHIC and LHC energy regions by using the AdS/CFT correspondence in this paper. This study is motivated by the phenomena of strong magnetic field and jet quenching, which have been found in relativistic heavy ion collisions. The probe's direction of motion is perpendicular and parallel to the direction of magnetic field $B$. The effects of magnetic field on energy loss when moving perpendicular to the magnetic field direction are larger than moving parallel to the magnetic field direction, which implies that the magnetic field tends to suppress more quarks and jets when moving in the transverse direction than in the parallel direction. It is found that the diffusion coefficient decreases with the magnetic field in the transverse direction, but increases with the magnetic field in the parallel direction, which indicates that the quark may diffuse farther when moving parallel to the magnetic field direction. We also find that the magnetic field will enhance the energy loss of the light quarks when moving in the transverse direction than in the parallel direction.

hep-ph↗

arXiv2018

Target Aware Network Adaptation for Efficient Representation Learning

This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e.g., image classification, for efficiency as well as accuracy in transfer learning. We call the concept target-aware transfer learning. Given only small-scale labeled data, and starting from an ImageNet pre-trained network, we exploit a scheme of removing its potential redundancy for the target task through iterative operations of filter-wise pruning and network optimization. The basic motivation is that compact networks are on one hand more efficient and should also be more tolerant, being less complex, against the risk of overfitting which would hinder the generalization of learned representations in the context of transfer learning. Further, unlike existing methods involving network simplification, we also let the scheme identify redundant portions across the entire network, which automatically results in a network structure adapted to the task at hand. We achieve this with a few novel ideas: (i) cumulative sum of activation statistics for each layer, and (ii) a priority evaluation of pruning across multiple layers. Experimental results by the method on five datasets (Flower102, CUB200-2011, Dog120, MIT67, and Stanford40) show favorable accuracies over the related state-of-the-art techniques while enhancing the computational and storage efficiency of the transferred model.

cs.CV↗

arXiv2018

Chiral magnetic currents with QGP medium response in heavy ion collisions at RHIC and LHC energies

We calculate the electromagnetic current with a more realistic approach in the RHIC and LHC energy regions in the article. We take the partons formation time as the initial time of the magnetic field response of QGP medium. The maximum electromagnetic current and the time-integrated current are two important characteristics of the chiral magnetic effect (CME), which can characterize the intensity and duration of fluctuations of CME. We consider the finite frequency response of CME to a time-varying magnetic field, find a significant impact from QGP medium feedback, and estimate the generated electromagnetic current as a function of time, beam energy and impact parameter.

hep-ph↗

arXiv2018

Moving heavy quarkonium entropy, effective string tension, and the QCD phase diagram

The entropy and effective string tension of the moving heavy quark-antiquark pair in the strongly coupled plasmas are calculated by using a deformed an anti-de Sitter/Reissner-Nordstr$\ddot{o}$m black hole metric. A sharp peak of the heavy-quarkonium entropy around the deconfinement transition can be realized in our model, which is consistent with the lattice QCD result. The effective string tension of the heavy quark-antiquark pair is related to the deconfinement phase transition. Thus, we investigate the deconfinement phase transition by analyzing the characteristics of the effective string tension with different temperatures, chemical potentials, and rapidities. It is found that the results of phase diagram calculated through effective string tension are in agreement with results calculated through a Polyakov loop. We argue that a moving system will reach the phase transition point at a lower temperature and chemical potential than a stationary system. It means that the lifetime of the moving QGP becomes longer than the static one.

hep-ph↗