arXiv subjects

Weiwei Zhang

Publications and source records attributed to Weiwei Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2024

Deploying Graph Neural Networks in Wireless Networks: A Link Stability Viewpoint

As an emerging artificial intelligence technology, graph neural networks (GNNs) have exhibited promising performance across a wide range of graph-related applications. However, information exchanges among neighbor nodes in GNN pose new challenges in the resource-constrained scenario, especially in wireless systems. In practical wireless systems, the communication links among nodes are usually unreliable due to wireless fading and receiver noise, consequently resulting in performance degradation of GNNs. To improve the learning performance of GNNs, we aim to maximize the number of long-term average (LTA) communication links by the optimized power control under energy consumption constraints. Using the Lyapunov optimization method, we first transform the intractable long-term problem into a deterministic problem in each time slot by converting the long-term energy constraints into the objective function. In spite of this non-convex combinatorial optimization problem, we address this problem via equivalently solving a sequence of convex feasibility problems together with a greedy based solver. Simulation results demonstrate the superiority of our proposed scheme over the baselines.

cs.DC↗

arXiv2024

New Interpretation for error propagation of data-driven Reynolds stress closures via global stability analysis

In light of the challenges surrounding convergence and error propagation encountered in Reynolds-averaged Navier-Stokes (RANS) equations with data-driven Reynolds stress closures, researchers commonly attribute these issues to ill-conditioning through conditional number analysis. This paper delves into an additional factor, numerical instability, contributing to these challenges. We conduct global stability analysis for the RANS equations, closed by the Reynolds stress of direct numerical simulation (DNS), with the time-averaged solution of DNS as the base flow. Our findings reveal that, for turbulent channel flow at high Reynolds numbers, significant ill-conditioning exists, yet the system remains stable. Conversely, for separated flow over periodic hills, notable ill-conditioning is absent, but unstable eigenvalues are present, indicating that error propagation arises from the mechanism of numerical instability. Furthermore, the effectiveness of the decomposition method employing eddy viscosity is compared, results show that the spatial distribution and amplitude of eddy viscosity influences the numerical stability.

physics.flu-dyn↗

arXiv2024

SQL-Encoder: Improving NL2SQL In-Context Learning Through a Context-Aware Encoder

Detecting structural similarity between queries is essential for selecting examples in in-context learning models. However, assessing structural similarity based solely on the natural language expressions of queries, without considering SQL queries, presents a significant challenge. This paper explores the significance of this similarity metric and proposes a model for accurately estimating it. To achieve this, we leverage a dataset comprising 170k question pairs, meticulously curated to train a similarity prediction model. Our comprehensive evaluation demonstrates that the proposed model adeptly captures the structural similarity between questions, as evidenced by improvements in Kendall-Tau distance and precision@k metrics. Notably, our model outperforms strong competitive embedding models from OpenAI and Cohere. Furthermore, compared to these competitive models, our proposed encoder enhances the downstream performance of NL2SQL models in 1-shot in-context learning scenarios by 1-2\% for GPT-3.5-turbo, 4-8\% for CodeLlama-7B, and 2-3\% for CodeLlama-13B.

cs.CL↗

arXiv2024

A solver for subsonic flow around airfoils based on physics-informed neural networks and mesh transformation

Physics-informed neural networks (PINNs) have recently become a new popular method for solving forward and inverse problems governed by partial differential equations (PDEs). However, in the flow around airfoils, the fluid is greatly accelerated near the leading edge, resulting in a local sharper transition, which is difficult to capture by PINNs. Therefore, PINNs are still rarely used to solve the flow around airfoils. In this study, we combine physical-informed neural networks with mesh transformation, using neural network to learn the flow in the uniform computational space instead of physical space. Mesh transformation avoids the network from capturing the local sharper transition and learning flow with internal boundary (wall boundary). We successfully solve inviscid flow and provide an open-source subsonic flow solver for arbitrary airfoils. Our results show that the solver exhibits higher-order attributes, achieving nearly an order of magnitude error reduction over second-order finite volume methods (FVM) on very sparse meshes. Limited by the learning ability and optimization difficulties of neural network, the accuracy of this solver will not improve significantly with mesh refinement. Nevertheless, it achieves comparable accuracy and efficiency to second-order FVM on fine meshes. Finally, we highlight the significant advantage of the solver in solving parametric problems, as it can efficiently obtain solutions in the continuous parameter space about the angle of attack.

physics.flu-dyn↗

arXiv2024

A complete state-space solution model for inviscid flow around airfoils based on physics-informed neural networks

Engineering problems often involve solving partial differential equations (PDEs) over a range of similar problem setups with various state parameters. In traditional numerical methods, each problem is solved independently, resulting in many repetitive tasks and expensive computational costs. Data-driven modeling has alleviated these issues, enabling fast solution prediction. Nevertheless, it still requires expensive labeled data and faces limitations in modeling accuracy, generalization, and uncertainty. The recently developed methods for solving PDEs through neural network optimization, such as physics-informed neural networks (PINN), enable the simultaneous solution of a series of similar problems. However, these methods still face challenges in achieving stable training and obtaining correct results in many engineering problems. In prior research, we combined PINN with mesh transformation, using neural network to learn the solution of PDEs in the computational space instead of physical space. This approach proved successful in solving inviscid flow around airfoils. In this study, we expand the input dimensions of the model to include shape parameters and flow conditions, forming an input encompassing the complete state-space (i.e., all parameters determining the solution are included in the input). Our results show that the model has significant advantages in solving high-dimensional parametric problems, achieving continuous solutions in a broad state-space in only about 18.8 hours. This is a task that traditional numerical methods struggle to accomplish. Once established, the model can efficiently complete airfoil flow simulation and shape inverse design tasks in approximately 1 second. Furthermore, we introduce a pretraining-finetuning method, enabling the fine-tuning of the model for the task of interest and quickly achieving accuracy comparable to the finite volume method.

physics.flu-dyn↗

arXiv2024

VW-PINNs: A volume weighting method for PDE residuals in physics-informed neural networks

Physics-informed neural networks (PINNs) have shown remarkable prospects in the solving the forward and inverse problems involving partial differential equations (PDEs). The method embeds PDEs into the neural network by calculating PDE loss at a series of collocation points, providing advantages such as meshfree and more convenient adaptive sampling. However, when solving PDEs using nonuniform collocation points, PINNs still face challenge regarding inefficient convergence of PDE residuals or even failure. In this work, we first analyze the ill-conditioning of the PDE loss in PINNs under nonuniform collocation points. To address the issue, we define volume-weighted residual and propose volume-weighted physics-informed neural networks (VW-PINNs). Through weighting the PDE residuals by the volume that the collocation points occupy within the computational domain, we embed explicitly the spatial distribution characteristics of collocation points in the residual evaluation. The fast and sufficient convergence of the PDE residuals for the problems involving nonuniform collocation points is guaranteed. Considering the meshfree characteristics of VW-PINNs, we also develop a volume approximation algorithm based on kernel density estimation to calculate the volume of the collocation points. We verify the universality of VW-PINNs by solving the forward problems involving flow over a circular cylinder and flow over the NACA0012 airfoil under different inflow conditions, where conventional PINNs fail; By solving the Burgers' equation, we verify that VW-PINNs can enhance the efficiency of existing the adaptive sampling method in solving the forward problem by 3 times, and can reduce the relative error of conventional PINNs in solving the inverse problem by more than one order of magnitude.

cs.CE↗

arXiv2023

A novel paradigm for solving PDEs: multi scale neural computing

Numerical simulation is dominant in solving partial difference equations (PDEs), but balancing fine-grained grids with low computational costs is challenging. Recently, solving PDEs with neural networks (NNs) has gained interest, yet cost-effectiveness and high accuracy remains a challenge. This work introduces a novel paradigm for solving PDEs, called multi scale neural computing (MSNC), considering spectral bias of NNs and local approximation properties in the finite difference method (FDM). The MSNC decomposes the solution with a NN for efficient capture of global scale and the FDM for detailed description of local scale, aiming to balance costs and accuracy. Demonstrated advantages include higher accuracy (10 times for 1D PDEs, 20 times for 2D PDEs) and lower costs (4 times for 1D PDEs, 16 times for 2D PDEs) than the standard FDM. The MSNC also exhibits stable convergence and rigorous boundary condition satisfaction, showcasing the potential for hybrid of NN and numerical method.

physics.comp-ph↗

arXiv2023

Fast simulation of airfoil flow field via deep neural network

Computational Fluid Dynamics (CFD) has become an indispensable tool in the optimization design, and evaluation of aircraft aerodynamics. However, solving the Navier-Stokes (NS) equations is a time-consuming, memory demanding and computationally expensive task. Artificial intelligence offers a promising avenue for flow field solving. In this work, we propose a novel deep learning framework for rapidly reconstructing airfoil flow fields. Channel attention and spatial attention modules are utilized in the downsampling stage of the UNet to enhance the feature learning capabilities of the deep learning model. Additionally, integrating the predicted flow field values generated by the deep learning model into the NS equation solver validates the credibility of the flow field prediction results. The NACA series airfoils were used to validate the prediction accuracy and generalization of the deep learning model. The experimental results represent the deep learning model achieving flow field prediction speeds three orders of magnitude faster than CFD solver. Furthermore, the CFD solver integrated with deep learning model demonstrates a threefold acceleration compared to CFD solver. By extensively mining historical flow field data, an efficient solution is derived for the rapid simulation of aircraft flow fields.

physics.flu-dyn↗

arXiv2023

Effective Quantization for Diffusion Models on CPUs

Diffusion models have gained popularity for generating images from textual descriptions. Nonetheless, the substantial need for computational resources continues to present a noteworthy challenge, contributing to time-consuming processes. Quantization, a technique employed to compress deep learning models for enhanced efficiency, presents challenges when applied to diffusion models. These models are notably more sensitive to quantization compared to other model types, potentially resulting in a degradation of image quality. In this paper, we introduce a novel approach to quantize the diffusion models by leveraging both quantization-aware training and distillation. Our results show the quantized models can maintain the high image quality while demonstrating the inference efficiency on CPUs. The code is publicly available at: https://github.com/intel/intel-extension-for-transformers.

cs.CV↗

arXiv2023

TSONN: Time-stepping-oriented neural network for solving partial differential equations

Deep neural networks (DNNs), especially physics-informed neural networks (PINNs), have recently become a new popular method for solving forward and inverse problems governed by partial differential equations (PDEs). However, these methods still face challenges in achieving stable training and obtaining correct results in many problems, since minimizing PDE residuals with PDE-based soft constraint make the problem ill-conditioned. Different from all existing methods that directly minimize PDE residuals, this work integrates time-stepping method with deep learning, and transforms the original ill-conditioned optimization problem into a series of well-conditioned sub-problems over given pseudo time intervals. The convergence of model training is significantly improved by following the trajectory of the pseudo time-stepping process, yielding a robust optimization-based PDE solver. Our results show that the proposed method achieves stable training and correct results in many problems that standard PINNs fail to solve, requiring only a simple modification on the loss function. In addition, we demonstrate several novel properties and advantages of time-stepping methods within the framework of neural network-based optimization approach, in comparison to traditional grid-based numerical method. Specifically, explicit scheme allows significantly larger time step, while implicit scheme can be implemented as straightforwardly as explicit scheme.

cs.LG↗

arXiv2023

LaTeX: Language Pattern-aware Triggering Event Detection for Adverse Experience during Pandemics

The COVID-19 pandemic has accentuated socioeconomic disparities across various racial and ethnic groups in the United States. While previous studies have utilized traditional survey methods like the Household Pulse Survey (HPS) to elucidate these disparities, this paper explores the role of social media platforms in both highlighting and addressing these challenges. Drawing from real-time data sourced from Twitter, we analyzed language patterns related to four major types of adverse experiences: loss of employment income (LI), food scarcity (FS), housing insecurity (HI), and unmet needs for mental health services (UM). We first formulate a sparsity optimization problem that extracts low-level language features from social media data sources. Second, we propose novel constraints on feature similarity exploiting prior knowledge about the similarity of the language patterns among the adverse experiences. The proposed problem is challenging to solve due to the non-convexity objective and non-smoothness penalties. We develop an algorithm based on the alternating direction method of multipliers (ADMM) framework to solve the proposed formulation. Extensive experiments and comparisons to other models on real-world social media and the detection of adverse experiences justify the efficacy of our model.

cs.LG↗

arXiv2023

Social media use among American Indians in South Dakota: Preferences and perceptions

Social media use data is widely being used in health, psychology, and marketing research to analyze human behavior. However, we have very limited knowledge on social media use among American Indians. In this context, this study was designed to assess preferences and perceptions of social media use among American Indians during COVID-19. We collected data from American Indians in South Dakota using online survey. Results show that Facebook, YouTube, TikTok, Instagram and Snapchat are the most preferred social media platforms. Most of the participants reported that the use of social media increased tremendously during COVID-19 and had perceptions of more negative effects than positive effects. Hate/harassment/extremism, misinformation/made up news, and people getting one point of view were the top reasons for negative effects.

econ.GN↗

arXiv2023

Bootstrap The Original Latent: Learning a Private Model from a Black-box Model

In this paper, considering the balance of data/model privacy of model owners and user needs, we propose a new setting called Back-Propagated Black-Box Adaptation (BPBA) for users to better train their private models via the guidance of the back-propagated results of a Black-box foundation/source model. Our setting can ease the usage of foundation/source models as well as prevent the leakage and misuse of foundation/source models. Moreover, we also propose a new training strategy called Bootstrap The Original Latent (BTOL) to fully utilize the foundation/source models. Our strategy consists of a domain adapter and a freeze-and-thaw strategy. We apply our BTOL under BPBA and Black-box UDA settings on three different datasets. Experiments show that our strategy is efficient and robust in various settings without manual augmentations.

cs.CV↗

arXiv2023

High speed silicon photonic electro-optic Kerr modulation

Electro-optic silicon-based modulators contribute to ease the integration of high-speed and low-power consumption circuits for classical optical communications or quantum computers. However, the inversion symmetry in the silicon crystal structure inhibits the use of Pockels effect. An electric field-induced optical modulation equivalent to a Pockels effect can nevertheless be achieved in silicon by the use of DC Kerr effect. Although some theoretical and experimental studies have shown its existence in silicon, the DC Kerr effect in optical modulation have led to a negligible contribution so far. This paper reports demonstration of high-speed optical modulation based on the electric field-induced linear electro-optic effect in silicon PIN junction waveguides. The relative contributions of both plasma dispersion and Kerr effects are quantified and we show that the Kerr induced modulation is dominant when a high external DC electric field is applied. Finally, the high-speed modulation response is analyzed and eye diagram up to 100 Gbits/s in NRZ format are obtained. This work demonstrates high speed modulation based on Kerr effect in silicon, and its potential for low loss, quasi-pure phase modulation.

physics.optics↗

arXiv2022

A novel convergence enhancement method based on Online Dimension Reduction Optimization

Iterative steady-state solvers are widely used in computational fluid dynamics. Unfortunately, it is difficult to obtain steady-state solution for unstable problem caused by physical instability and numerical instability. Optimization is a better choice for solving unstable problem because steady-state solution is always the extreme point of optimization regardless of whether the problem is unstable or ill-conditioned, but it is difficult to solve partial differential equations (PDEs) due to too many optimization variables. In this study, we propose an Online Dimension Reduction Optimization (ODRO) method to enhance the convergence of the traditional iterative method to obtain the steady-state solution of unstable problem. This method performs proper orthogonal decomposition (POD) on the snapshots collected from a few iteration steps, optimizes PDE residual in the POD subspace to get a solution with lower residual, and then continues to iterate with the optimized solution as the initial value, repeating the above three steps until the residual converges. Several typical cases show that the proposed method can efficiently calculate the steady-state solution of unstable problem with both the high efficiency and robustness of the iterative method and the good convergence of the optimization method. In addition, this method is easy to implement in almost any iterative solver with minimal code modification.

cs.CE↗

arXiv2022

Fast sparse flow field prediction around airfoils via multi-head perceptron based deep learning architecture

In order to obtain the information about flow field, traditional computational fluid dynamics methods need to solve the Navier-Stokes equations on the mesh with boundary conditions, which is a time-consuming task. In this work, a data-driven method based on convolutional neural network and multi-head perceptron is used to predict the incompressible laminar steady sparse flow field around the airfoils. Firstly, we use convolutional neural network to extract the geometry parameters of the airfoil from the input gray scale image. Secondly, the extracted geometric parameters together with Reynolds number, angle of attack and flow field coordinates are used as the input of the multi-layer perceptron and the multi-head perceptron. The proposed multi-head neural network architecture can predict the aerodynamic coefficients of the airfoil in seconds. Furthermore, the experimental results show that for sparse flow field, multi-head perceptron can achieve better prediction results than multi-layer perceptron.

physics.flu-dyn↗

arXiv2022

An experimental modal testing method for subcritical flow around a cylinder

Modal analysis of fluid flows is essential to understand flow physics and fluid-solid interaction mechanisms, and to implement flow control. Unlike unstable flow, the intrinsic attenuation of subcritical flow has led to failures to experimentally extract the subcritical flow modes clearly. To this end, this paper proposes a modal testing method for subcritical flows. Using Dynamic Mode Decomposition (DMD), dominate modes of flow around a cylinder at subcritical Reynolds numbers are extracted experimentally for the first time. The extracted structures and parameters of the modes are in good agreement with the numerical results in the literature. It is found that the first-order von Kármán mode can be observed at a Reynolds number as low as 19.3, which is very close to the lower boundary of subcritical vortex induced vibrations (VIV). This experimental observation elucidates the correlation between von Kármán mode and fluid-solid interaction instability in subcritical flows.

physics.flu-dyn↗

arXiv2022

Individual and Collective Performance Deteriorate in a New Team: A Case Study of CS:GO Tournaments

How does the team formation relates to team performance in professional video game playing? This study examined one aspect of group dynamics - team switching - and aims to answer how changing a team affects individual and collective performance in eSports tournaments. In this study we test the hypothesis that switching teams can be detrimental to individual and team performance both in short term and in a long run. We collected data from professional tournaments of a popular first-person shooter game {\itshape Counter-Strike: Global Offensive (CS:GO)} and perform two natural experiments. We found that the player's performance was inversely correlated with the number of teams a player had joined. After a player switched to a new team, both the individual and the collective performance dropped initially, and then slowly recovered. The findings in this study can provide insights for understanding group dynamics in eSports team play and eventually emphasize the importance of team cohesion in facilitating team collaboration, coordination, and knowledge sharing in teamwork in general.

cs.HC↗