arXiv subjects

Chen Liang

Publications and source records attributed to Chen Liang.

At least 145 records · Page 8Linked to original sources

arXiv2023

Hybrid Proca-boson stars

In this paper, we construct a hybrid boson star model that contains a complex scalar field and a Proca field. The scalar field is in the ground state, while the Proca field is in the first excited state. We numerically solve the model and obtain solution families of different coexisting states by considering both synchronized and nonsynchronized cases. By examining the relation between ADM mass and synchronized frequency $\tildeω$ or nonsynchronized frequency $\tildeω_P$, we identify several types of solution families for the hybrid boson stars. In addition to solutions that intersect the scalar field and the Proca field at each end, there are also several types of multi-branch coexisting state solutions. The characteristics of various solutions are analyzed and discussed in detail. We calculate the binding energy $E$ of the hybrid Proca-boson stars and provide the relationship between $E$ and both synchronized frequency $\tildeω$ and nonsynchronized frequency $\tildeω_P$. Furthermore, we obtain the stability of the corresponding hybrid star solution families from these analyses above.

gr-qc↗

arXiv2023

Moment-based space-variant Shack-Hartmann wavefront reconstruction

Based on image moment theory, an approach for space-variant Shack-Hartmann wavefront reconstruction is presented in this article. The relation between the moment of a pair of subimages and the local transformation coefficients is derived. The square guide 'star' is used to obtain a special solution from this relation. The moment-based wavefront reconstruction has a reduced computational complexity compared to the iteration-based algorithm. Image restorations are executed by the tiling strategy with 5 $\times$ 5 PSFs as well as the conventional strategy with a global average PSF. Visual and quantitative evaluations support our approach.

physics.optics↗

arXiv2023

Observation of fast sound in two-dimensional dusty plasma liquids

Equilibrium molecular dynamics simulations are performed to study two-dimensional (2D) dusty plasma liquids. Based on the stochastic thermal motion of simulated particles, the longitudinal and transverse phonon spectra are calculated, and used to determine the corresponding dispersion relations. From there, the longitudinal and transverse sound speeds of 2D dusty plasma liquids are obtained. It is discovered that, for wavenumbers beyond the hydrodynamic regime, the longitudinal sound speed of a 2D dusty plasma liquid exceeds its adiabatic value, i.e., the so-called fast sound. This phenomenon appears at roughly the same length scale of the cutoff wavenumber for transverse waves, confirming its relation to the emergent solidity of liquids in the non-hydrodynamic regime. Using the thermodynamic and transport coefficients extracted from the previous studies, and relying on the Frenkel theory, the ratio of the longitudinal to the adiabatic sound speeds is derived analytically, providing the optimal conditions for fast sound, which are in quantitative agreement with the current simulation results.

physics.plasm-ph↗

arXiv2023

DR-Label: Improving GNN Models for Catalysis Systems by Label Deconstruction and Reconstruction

Attaining the equilibrium state of a catalyst-adsorbate system is key to fundamentally assessing its effective properties, such as adsorption energy. Machine learning methods with finer supervision strategies have been applied to boost and guide the relaxation process of an atomic system and better predict its properties at the equilibrium state. In this paper, we present a novel graph neural network (GNN) supervision and prediction strategy DR-Label. The method enhances the supervision signal, reduces the multiplicity of solutions in edge representation, and encourages the model to provide node predictions that are graph structural variation robust. DR-Label first Deconstructs finer-grained equilibrium state information to the model by projecting the node-level supervision signal to each edge. Reversely, the model Reconstructs a more robust equilibrium state prediction by transforming edge-level predictions to node-level with a sphere-fitting algorithm. The DR-Label strategy was applied to three radically distinct models, each of which displayed consistent performance enhancements. Based on the DR-Label strategy, we further proposed DRFormer, which achieved a new state-of-the-art performance on the Open Catalyst 2020 (OC20) dataset and the Cu-based single-atom-alloyed CO adsorption (SAA) dataset. We expect that our work will highlight crucial steps for the development of a more accurate model in equilibrium state property prediction of a catalysis system.

cs.LG↗

arXiv2023

HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers

Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained model that can be easily fine-tuned on various tasks with small computational costs and memory footprints. Despite the practical benefits, task-agnostic distillation is challenging. Since the teacher model has a significantly larger capacity and stronger representation power than the student model, it is very difficult for the student to produce predictions that match the teacher's over a massive amount of open-domain training data. Such a large prediction discrepancy often diminishes the benefits of knowledge distillation. To address this challenge, we propose Homotopic Distillation (HomoDistil), a novel task-agnostic distillation approach equipped with iterative pruning. Specifically, we initialize the student model from the teacher model, and iteratively prune the student's neurons until the target width is reached. Such an approach maintains a small discrepancy between the teacher's and student's predictions throughout the distillation process, which ensures the effectiveness of knowledge transfer. Extensive experiments demonstrate that HomoDistil achieves significant improvements on existing baselines.

cs.CL↗

arXiv2023

Unified Functional Hashing in Automatic Machine Learning

The field of Automatic Machine Learning (AutoML) has recently attained impressive results, including the discovery of state-of-the-art machine learning solutions, such as neural image classifiers. This is often done by applying an evolutionary search method, which samples multiple candidate solutions from a large space and evaluates the quality of each candidate through a long training process. As a result, the search tends to be slow. In this paper, we show that large efficiency gains can be obtained by employing a fast unified functional hash, especially through the functional equivalence caching technique, which we also present. The central idea is to detect by hashing when the search method produces equivalent candidates, which occurs very frequently, and this way avoid their costly re-evaluation. Our hash is "functional" in that it identifies equivalent candidates even if they were represented or coded differently, and it is "unified" in that the same algorithm can hash arbitrary representations; e.g. compute graphs, imperative code, or lambda functions. As evidence, we show dramatic improvements on multiple AutoML domains, including neural architecture search and algorithm discovery. Finally, we consider the effect of hash collisions, evaluation noise, and search distribution through empirical analysis. Altogether, we hope this paper may serve as a guide to hashing techniques in AutoML.

cs.LG↗

arXiv2022

Space-variant Shack-Hartmann wavefront sensing based on affine transformation estimation

The space-variant wavefront reconstruction problem inherently exists in deep tissue imaging. In this paper,we propose a framework of Shack-Hartmann wavefront space-variant sensing with extended source illumination. The space-variant wavefront is modeled as a four-dimensional function where two dimensionsare in the spatial domain and two in the Fourier domain with priors that both gently vary. Here, the affinetransformation is used to characterize the wavefront space-variant function. Correspondingly, the zonaland modal methods are both escalated to adapt to four-dimensional representation and reconstruction.Experiments and simulations show double to quadruple improvements in space-variant wavefront reconstruction accuracy compared to the conventional space-invariant correlation method.

physics.optics↗

arXiv2022

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel feature|class), and struggles to identify out-of-distribution data. Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature,class). For each class, GMMSeg builds Gaussian Mixture Models (GMMs) via Expectation-Maximization (EM), so as to capture class-conditional densities. Meanwhile, the deep dense representation is end-to-end trained in a discriminative manner, i.e., maximizing p(class|pixel feature). This endows GMMSeg with the strengths of both generative and discriminative models. With a variety of segmentation architectures and backbones, GMMSeg outperforms the discriminative counterparts on three closed-set datasets. More impressively, without any modification, GMMSeg even performs well on open-world datasets. We believe this work brings fundamental insights into the related fields.

cs.CV↗

arXiv2022

Multi-Task Mixture Density Graph Neural Networks for Predicting Cu-based Single-Atom Alloy Catalysts for CO2 Reduction Reaction

Graph neural networks (GNNs) have drawn more and more attention from material scientists and demonstrated a high capacity to establish connections between the structure and properties. However, with only unrelaxed structures provided as input, few GNN models can predict the thermodynamic properties of relaxed configurations with an acceptable level of error. In this work, we develop a multi-task (MT) architecture based on DimeNet++ and mixture density networks to improve the performance of such task. Taking CO adsorption on Cu-based single-atom alloy catalysts as an illustration, we show that our method can reliably estimate CO adsorption energy with a mean absolute error of 0.087 eV from the initial CO adsorption structures without costly first-principles calculations. Further, compared to other state-of-the-art GNN methods, our model exhibits improved generalization ability when predicting catalytic performance of out-of-domain configurations, built with either unseen substrate surfaces or doping species. We show that the proposed MT GNN strategy can facilitate catalyst discovery.

cond-mat.mtrl-sci↗

arXiv2022

Dirac-boson stars

In this paper, we construct \textit{Dirac-boson stars} (DBSs) model composed of a scalar field and two Dirac fields. The scalar field and both Dirac fields are in the ground state. We consider the solution families of the DBSs for the synchronized frequency $\tildeω$ and the nonsynchronized frequency $\tildeω_D$ cases, respectively. We find several different solutions when the Dirac mass $\tildeμ_D$ and scalar field frequency $\tildeω_S$ are taken in some particular ranges. In contrast, no similar case has been found in previous studies of multistate boson stars. Moreover, we discuss the characteristics of each type of solution family of the DBSs and present the relationship between the ADM mass $M$ of the DBSs and the synchronized frequency $\tildeω$ or the nonsynchronized frequency $\tildeω_D$. Finally, we calculate the binding energy $E_B$ of the DBSs and investigate the relationship of $E_B$ with the synchronized frequency $\tildeω$ or the nonsynchronized frequency $\tildeω_D$.

gr-qc↗

arXiv2022

PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance

Large Transformer-based models have exhibited superior performance in various natural language processing and computer vision tasks. However, these models contain enormous amounts of parameters, which restrict their deployment to real-world applications. To reduce the model size, researchers prune these models based on the weights' importance scores. However, such scores are usually estimated on mini-batches during training, which incurs large variability/uncertainty due to mini-batch sampling and complicated training dynamics. As a result, some crucial weights could be pruned by commonly used pruning methods because of such uncertainty, which makes training unstable and hurts generalization. To resolve this issue, we propose PLATON, which captures the uncertainty of importance scores by upper confidence bound (UCB) of importance estimation. In particular, for the weights with low importance scores but high uncertainty, PLATON tends to retain them and explores their capacity. We conduct extensive experiments with several Transformer-based models on natural language understanding, question answering and image classification to validate the effectiveness of PLATON. Results demonstrate that PLATON manifests notable improvement under different sparsity levels. Our code is publicly available at https://github.com/QingruZhang/PLATON.

cs.LG↗

arXiv2022

Adaptive Network Response to Line Failures in Power Systems

Transmission line failures in power systems propagate and cascade non-locally. In this work, we propose an adaptive control strategy that offers strong guarantees in both the mitigation and localization of line failures. Specifically, we leverage the properties of network bridge-block decomposition and a frequency regulation method called the unified control. If the balancing areas over which the unified control operates coincide with the bridge-blocks of the network, the proposed strategy drives the post-contingency system to a steady state where the impact of initial line outages is localized within the areas where they occurred whenever possible, stopping the cascading process. When the initial line outages cannot be localized, the proposed control strategy provides a configurable design that progressively involves and coordinates more balancing areas. We compare the proposed control strategy with the classical Automatic Generation Control (AGC) on the IEEE 118-bus and 2736-bus test networks. Simulation results show that our strategy greatly improves overall reliability in terms of the N-k security standard, and localizes the impact of initial failures in the majority of the simulated contingencies. Moreover, the proposed framework incurs significantly less load loss, if any, compared to AGC, in all our case studies.

eess.SY↗

arXiv2022

Interface Networks for Failure Localization in Power Systems

Transmission power systems usually consist of interconnected sub-grids that are operated relatively independently. When a failure happens, it is desirable to localize its impact within the sub-grid where the failure occurs. This paper introduces three interface networks to connect sub-grids, achieving better failure localization while maintaining robust network connectivity. The proposed interface networks are validated with numerical experiments on the IEEE 118-bus test network under both DC and AC power flow models.

eess.SY↗

arXiv2022

Self-Training with Differentiable Teacher

Self-training achieves enormous success in various semi-supervised and weakly-supervised learning tasks. The method can be interpreted as a teacher-student framework, where the teacher generates pseudo-labels, and the student makes predictions. The two models are updated alternatingly. However, such a straightforward alternating update rule leads to training instability. This is because a small change in the teacher may result in a significant change in the student. To address this issue, we propose DRIFT, short for differentiable self-training, that treats teacher-student as a Stackelberg game. In this game, a leader is always in a more advantageous position than a follower. In self-training, the student contributes to the prediction performance, and the teacher controls the training process by generating pseudo-labels. Therefore, we treat the student as the leader and the teacher as the follower. The leader procures its advantage by acknowledging the follower's strategy, which involves differentiable pseudo-labels and differentiable sample weights. Consequently, the leader-follower interaction can be effectively captured via Stackelberg gradient, obtained by differentiating the follower's strategy. Experimental results on semi- and weakly-supervised classification and named entity recognition tasks show that our model outperforms existing approaches by large margins.

cs.CL↗

arXiv2022

Temporal Events Detector for Pregnancy Care (TED-PC): A Rule-based Algorithm to Infer Gestational Age and Delivery Date from Electronic Health Records of Pregnant Women with and without COVID-19

Objective: To develop a rule-based algorithm that detects temporal information of clinical events during pregnancy for women with COVID-19 by inferring gestational weeks and delivery dates from Electronic Health Records (EHR) from the National COVID Cohort Collaborate (N3C). Materials and Methods: The EHR are normalized by the Observational Medical Outcomes Partnership (OMOP) Clinical Data Model (CDM). EHR phenotyping resulted in 270,897 pregnant women (2018-06-01 to 2021-05-31). We developed a rule-based algorithm and performed a multi-level evaluation to test content validity and clinical validity of the algorithm; and extreme value analysis for individuals with <150 or >300 days of gestation. Results: The algorithm identified 296,194 pregnancies (16,659 COVID-19 174 and 744 without COVID-19 peri-pandemic) in 270,897 pregnant women. For inferring gestational age, 95% cases (n=40) have moderate-high accuracy (Cohen Kappa = 0.62); 100% cases (n=40) have moderate-high granularity of temporal information (Cohen Kappa = 1). For inferring delivery dates, the accuracy is 100% (Cohen Kappa = 1). Accuracy of gestational age detection for extreme length of gestation is 93.3% (Cohen Kappa = 1). Mothers with COVID-19 showed higher prevalence in obesity (35.1% vs. 29.5%), diabetes (17.8% vs. 17.0%), chronic obstructive pulmonary disease (COPD) (0.2% vs. 0.1%), respiratory distress syndrome (ARDS) (1.8% vs. 0.2%). Discussion: We explored the characteristics of pregnant women by different timing of COVID-19 with our algorithm: the first to infer temporal information from complete antenatal care and detect the timing of SARS-CoV-2 infection for pregnant women using N3C. Conclusion: The algorithm shows excellent validity in inferring gestational age and delivery dates, which supports national EHR cohorts on N3C studying the impact of COVID-19 on pregnancy.

stat.AP↗

arXiv2022

MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation

Pre-trained language models have demonstrated superior performance in various natural language processing tasks. However, these models usually contain hundreds of millions of parameters, which limits their practicality because of latency requirements in real-world applications. Existing methods train small compressed models via knowledge distillation. However, performance of these small models drops significantly compared with the pre-trained models due to their reduced model capacity. We propose MoEBERT, which uses a Mixture-of-Experts structure to increase model capacity and inference speed. We initialize MoEBERT by adapting the feed-forward neural networks in a pre-trained model into multiple experts. As such, representation power of the pre-trained model is largely retained. During inference, only one of the experts is activated, such that speed can be improved. We also propose a layer-wise distillation method to train MoEBERT. We validate the efficiency and effectiveness of MoEBERT on natural language understanding and question answering tasks. Results show that the proposed method outperforms existing task-specific distillation algorithms. For example, our method outperforms previous approaches by over 2% on the MNLI (mismatched) dataset. Our code is publicly available at https://github.com/SimiaoZuo/MoEBERT.

cs.CL↗

arXiv2022

Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach

Adversarial regularization has been shown to improve the generalization performance of deep learning models in various natural language processing tasks. Existing works usually formulate the method as a zero-sum game, which is solved by alternating gradient descent/ascent algorithms. Such a formulation treats the adversarial and the defending players equally, which is undesirable because only the defending player contributes to the generalization performance. To address this issue, we propose Stackelberg Adversarial Regularization (SALT), which formulates adversarial regularization as a Stackelberg game. This formulation induces a competition between a leader and a follower, where the follower generates perturbations, and the leader trains the model subject to the perturbations. Different from conventional approaches, in SALT, the leader is in an advantageous position. When the leader moves, it recognizes the strategy of the follower and takes the anticipated follower's outcomes into consideration. Such a leader's advantage enables us to improve the model fitting to the unperturbed data. The leader's strategic information is captured by the Stackelberg gradient, which is obtained using an unrolling algorithm. Our experimental results on a set of machine translation and natural language understanding tasks show that SALT outperforms existing adversarial regularization baselines across all tasks. Our code is available at https://github.com/SimiaoZuo/Stackelberg-Adv.

cs.LG↗

arXiv2022

ARCH: Efficient Adversarial Regularized Training with Caching

Adversarial regularization can improve model generalization in many natural language processing tasks. However, conventional approaches are computationally expensive since they need to generate a perturbation for each sample in each epoch. We propose a new adversarial regularization method ARCH (adversarial regularization with caching), where perturbations are generated and cached once every several epochs. As caching all the perturbations imposes memory usage concerns, we adopt a K-nearest neighbors-based strategy to tackle this issue. The strategy only requires caching a small amount of perturbations, without introducing additional training time. We evaluate our proposed method on a set of neural machine translation and natural language understanding tasks. We observe that ARCH significantly eases the computational burden (saves up to 70% of computational time in comparison with conventional approaches). More surprisingly, by reducing the variance of stochastic gradients, ARCH produces a notably better (in most of the tasks) or comparable model generalization. Our code is available at https://github.com/SimiaoZuo/Caching-Adv.

cs.CL↗