arXiv subjects

Zhouwang Yang

Publications and source records attributed to Zhouwang Yang.

17 recordsLinked to original sources

arXiv2026

Distributed Team Orchestration via Supervisor Networks: Convergence, Optimality, and Resilience

In this paper, we study zero-sum potential team games with a supervisor network, where agents rely on supervisor-provided belief information rather than accurate common beliefs. The main challenge is that such belief information can be inaccurate because of supervisors' belief-estimation errors and the misreporting of joint actions by Byzantine teams. We propose the distributed team-orchestrating algorithm (DTOA), which combines team fictitious play with supervisor-based distributed belief learning. We prove the convergence of supervisors' belief estimates and establish that the induced learning dynamics converge to a near team-Nash equilibrium (TNE) in terms of the team-Nash gap (TNG). In the Byzantine setting, we consider a misreporting attack model and develop a Byzantine-resilient DTOA. We further provide probabilistic guarantees for Byzantine-team identification and establish an asymptotic bound on the honest TNG. Numerical experiments illustrate the theoretical findings, compare DTOA with baseline learning methods, and evaluate its performance in a Markov decision process setting.

cs.MA↗

arXiv2025

HistCAD: A Constraint-Aware Parametric History-Based CAD Representation, Dataset, and Benchmark with Industrial Complexity

Parametric CAD sequences are reusable because dimensional and geometric constraints govern how parameter changes propagate. Existing CAD generation datasets and benchmarks emphasize reconstruction fidelity, execution validity, or static shape similarity, leaving preservation of design intent under edits largely unmeasured. We introduce HistCAD, a representation standard, dataset, and benchmark for executable parametric CAD with explicit constraints. HistCAD defines an intermediate language independent of CAD software, recording sketch primitives, constraints, feature operations, and 3D point boundary references for operations such as fillet and chamfer. The dataset contains 170,236 executable sequences aligned with native CAD models, STEP files, rendered views, and text annotations, combining academic scale with professionally authored industrial complexity. Building on this representation, the Constraint-Aware Editability Benchmark applies parameter edits and reports Edit Reachability, conditional preserved constraint satisfaction, and Overall Editable Success, abbreviated ER, cPCSR, and OES; these metrics separate failures to reach a valid edited state from failures to preserve required constraints. Experiments show that explicit constraints are essential for preserving design intent after edits, and that HistCAD supports supervised CAD generation from text and direct LLM workflows. We argue that HistCAD reframes CAD generation from static shape imitation to the synthesis of reusable parametric sequences with explicit constraints.

cs.GR↗

arXiv2025

Efficient Global-Local Fusion Sampling for Physics-Informed Neural Networks

The accuracy of Physics-Informed Neural Networks (PINNs) critically depends on the placement of collocation points, as the PDE loss is approximated through sampling over the solution domain. Global sampling ensures stability by covering the entire domain but requires many samples and is computationally expensive, whereas local sampling improves efficiency by focusing on high-residual regions but may neglect well-learned areas, reducing robustness. We propose a Global-Local Fusion (GLF) Sampling Strategy that combines the strengths of both approaches. Specifically, new collocation points are generated by perturbing training points with Gaussian noise scaled inversely to the residual, thereby concentrating samples in difficult regions while preserving exploration. To further reduce computational overhead, a lightweight linear surrogate is introduced to approximate the global residual-based distribution, achieving similar effectiveness at a fraction of the cost. Together, these components, residual-adaptive sampling and residual-based approximation, preserve the stability of global methods while retaining the efficiency of local refinement. Extensive experiments on benchmark PDEs demonstrate that GLF consistently improves both accuracy and efficiency compared with global and local sampling strategies. This study provides a practical and scalable framework for enhancing the reliability and efficiency of PINNs in solving complex and high-dimensional PDEs.

cs.LG↗

arXiv2025

When a Reinforcement Learning Agent Encounters Unknown Unknowns

An AI agent might surprisingly find she has reached an unknown state which she has never been aware of -- an unknown unknown. We mathematically ground this scenario in reinforcement learning: an agent, after taking an action calculated from value functions $Q$ and $V$ defined on the {\it {aware domain}}, reaches a state out of the domain. To enable the agent to handle this scenario, we propose an {\it episodic Markov decision {process} with growing awareness} (EMDP-GA) model, taking a new {\it noninformative value expansion} (NIVE) approach to expand value functions to newly aware areas: when an agent arrives at an unknown unknown, value functions $Q$ and $V$ whereon are initialised by noninformative beliefs -- the averaged values on the aware domain. This design is out of respect for the complete absence of knowledge in the newly discovered state. The upper confidence bound momentum Q-learning is then adapted to the growing awareness for training the EMDP-GA model. We prove that (1) the regret of our approach is asymptotically consistent with the state of the art (SOTA) without exposure to unknown unknowns in an extremely uncertain environment, and (2) our computational complexity and space complexity are comparable with the SOTA -- these collectively suggest that though an unknown unknown is surprising, it will be asymptotically properly discovered with decent speed and an affordable cost.

cs.LG↗

arXiv2025

Cross-Hierarchical Bidirectional Consistency Learning for Fine-Grained Visual Classification

Fine-Grained Visual Classification (FGVC) aims to categorize closely related subclasses, a task complicated by minimal inter-class differences and significant intra-class variance. Existing methods often rely on additional annotations for image classification, overlooking the valuable information embedded in Tree Hierarchies that depict hierarchical label relationships. To leverage this knowledge to improve classification accuracy and consistency, we propose a novel Cross-Hierarchical Bidirectional Consistency Learning (CHBC) framework. The CHBC framework extracts discriminative features across various hierarchies using a specially designed module to decompose and enhance attention masks and features. We employ bidirectional consistency loss to regulate the classification outcomes across different hierarchies, ensuring label prediction consistency and reducing misclassification. Experiments on three widely used FGVC datasets validate the effectiveness of the CHBC framework. Ablation studies further investigate the application strategies of feature enhancement and consistency constraints, underscoring the significant contributions of the proposed modules.

cs.CV↗

arXiv2024

A Multigrid Graph U-Net Framework for Simulating Multiphase Flow in Heterogeneous Porous Media

Numerical simulation of multi-phase fluid dynamics in porous media is critical to a variety of geoscience applications. Data-driven surrogate models using Convolutional Neural Networks (CNNs) have shown promise but are constrained to regular Cartesian grids and struggle with unstructured meshes necessary for accurately modeling complex geological features in subsurface simulations. To tackle this difficulty, we build surrogate models based on Graph Neural Networks (GNNs) to approximate space-time solutions of multi-phase flow and transport processes. Particularly, a novel Graph U-Net framework, referred to as AMG-GU, is developed to enable hierarchical graph learning for the parabolic pressure component of the coupled partial differential equation (PDE) system. Drawing inspiration from aggregation-type Algebraic Multigrid (AMG), we propose a graph coarsening strategy adapted to heterogeneous PDE coefficients, achieving an effective graph pooling operation. Results of three-dimensional heterogeneous test cases demonstrate that the multi-level surrogates predict pressure and saturation dynamics with high accuracy, significantly outperforming the single-level baseline. Our Graph U-Net model exhibits great generalization capability to unseen model configurations.

physics.comp-ph↗

arXiv2024

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?

The widespread use of large language models (LLMs) has sparked concerns about the potential misuse of AI-generated text, as these models can produce content that closely resembles human-generated text. Current detectors for AI-generated text (AIGT) lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text. This paper investigates the robustness of existing AIGT detection methods and introduces a novel detector, the Siamese Calibrated Reconstruction Network (SCRN). The SCRN employs a reconstruction network to add and remove noise from text, extracting a semantic representation that is robust to local perturbations. We also propose a siamese calibration technique to train the model to make equally confidence predictions under different noise, which improves the model's robustness against adversarial perturbations. Experiments on four publicly available datasets show that the SCRN outperforms all baseline methods, achieving 6.5\%-18.25\% absolute accuracy improvement over the best baseline method under adversarial attacks. Moreover, it exhibits superior generalizability in cross-domain, cross-genre, and mixed-source scenarios. The code is available at \url{https://github.com/CarlanLark/Robust-AIGC-Detector}.

cs.CL↗

arXiv2023

The Random Feature Method for Solving Interface Problems

Interface problems have long been a major focus of scientific computing, leading to the development of various numerical methods. Traditional mesh-based methods often employ time-consuming body-fitted meshes with standard discretization schemes or unfitted meshes with tailored schemes to achieve controllable accuracy and convergence rate. Along another line, mesh-free methods bypass mesh generation but lack robustness in terms of convergence and accuracy due to the low regularity of solutions. In this study, we propose a novel method for solving interface problems within the framework of the random feature method. This approach utilizes random feature functions in conjunction with a partition of unity as approximation functions. It evaluates partial differential equations, boundary conditions, and interface conditions on collocation points in equal footing, and solves a linear least-squares system to obtain the approximate solution. To address the issue of low regularity, two sets of random feature functions are used to approximate the solution on each side of the interface, which are then coupled together via interface conditions. We validate our method through a series of increasingly complex numerical examples. Our findings show that despite the solution often being only continuous or even discontinuous, our method not only eliminates the need for mesh generation but also maintains high accuracy, akin to the spectral collocation method for smooth solutions. Remarkably, for the same accuracy requirement, our method requires two to three orders of magnitude fewer degrees of freedom than traditional methods, demonstrating its significant potential for solving interface problems with complex geometries.

math.NA↗

arXiv2022

Bridging Traditional and Machine Learning-based Algorithms for Solving PDEs: The Random Feature Method

One of the oldest and most studied subject in scientific computing is algorithms for solving partial differential equations (PDEs). A long list of numerical methods have been proposed and successfully used for various applications. In recent years, deep learning methods have shown their superiority for high-dimensional PDEs where traditional methods fail. However, for low dimensional problems, it remains unclear whether these methods have a real advantage over traditional algorithms as a direct solver. In this work, we propose the random feature method (RFM) for solving PDEs, a natural bridge between traditional and machine learning-based algorithms. RFM is based on a combination of well-known ideas: 1. representation of the approximate solution using random feature functions; 2. collocation method to take care of the PDE; 3. the penalty method to treat the boundary conditions, which allows us to treat the boundary condition and the PDE in the same footing. We find it crucial to add several additional components including multi-scale representation and rescaling the weights in the loss function. We demonstrate that the method exhibits spectral accuracy and can compete with traditional solvers in terms of both accuracy and efficiency. In addition, we find that RFM is particularly suited for complex problems with complex geometry, where both traditional and machine learning-based algorithms encounter difficulties.

math.NA↗

arXiv2022

A Deep Neural Network for Knot Placement in B-spline Approximation

Automatically determining knot number and positions is a fundamental and challenging problem in B-spline approximation. In this paper, the knot placement is abstracted as a mapping from initial knots to the optimal knots. We innovatively introduce a deep neural network solver to approximate the mapping. The neural network is composed of several subnetworks. Each subnetwork is designed to approximate the optimal knot positions in the case of fixed knot number. All the subnetworks are stacked together to find the optimal knots (including knot number and knot positions) within some given tolerance. Owing to the powerful approximation capabilities, as well as mature algorithms developed in deep learning, the proposed method can effectively and efficiently find the optimal knot number and knot positions. Several numerical examples are demonstrated to show the superiority of our method.

math.OC↗

arXiv2021

Use square root affinity to regress labels in semantic segmentation

Semantic segmentation is a basic but non-trivial task in computer vision. Many previous work focus on utilizing affinity patterns to enhance segmentation networks. Most of these studies use the affinity matrix as a kind of feature fusion weights, which is part of modules embedded in the network, such as attention models and non-local models. In this paper, we associate affinity matrix with labels, exploiting the affinity in a supervised way. Specifically, we utilize the label to generate a multi-scale label affinity matrix as a structural supervision, and we use a square root kernel to compute a non-local affinity matrix on output layers. With such two affinities, we define a novel loss called Affinity Regression loss (AR loss), which can be an auxiliary loss providing pair-wise similarity penalty. Our model is easy to train and adds little computational burden without run-time inference. Extensive experiments on NYUv2 dataset and Cityscapes dataset demonstrate that our proposed method is sufficient in promoting semantic segmentation networks.

cs.CV↗

arXiv2021

Multi-Instance Learning by Utilizing Structural Relationship among Instances

Multi-Instance Learning(MIL) aims to learn the mapping between a bag of instances and the bag-level label. Therefore, the relationships among instances are very important for learning the mapping. In this paper, we propose an MIL algorithm based on a graph built by structural relationship among instances within a bag. Then, Graph Convolutional Network(GCN) and the graph-attention mechanism are used to learn bag-embedding. In the task of medical image classification, our GCN-based MIL algorithm makes full use of the structural relationships among patches(instances) in an original image space domain, and experimental results verify that our method is more suitable for handling medical high-resolution images. We also verify experimentally that the proposed method achieves better results than previous methods on five bechmark MIL datasets and four medical image datasets.

cs.LG↗

arXiv2020

Forecasting confirmed cases of the COVID-19 pandemic with a migration-based epidemiological model

The unprecedented coronavirus disease 2019 (COVID-19) pandemic is still a worldwide threat to human life since its invasion into the daily lives of the public in the first several months of 2020. Predicting the size of confirmed cases is important for countries and communities to make proper prevention and control policies so as to effectively curb the spread of COVID-19. Different from the 2003 SARS epidemic and the worldwide 2009 H1N1 influenza pandemic, COVID-19 has unique epidemiological characteristics in its infectious and recovered compartments. This drives us to formulate a new infectious dynamic model for forecasting the COVID-19 pandemic within the human mobility network, named the SaucIR-model in the sense that the new compartmental model extends the benchmark SIR model by dividing the flow of people in the infected state into asymptomatic, pathologically infected but unconfirmed, and confirmed. Furthermore, we employ dynamic modeling of population flow in the model in order that spatial effects can be incorporated effectively. We forecast the spread of accumulated confirmed cases in some provinces of mainland China and other countries that experienced severe infection during the time period from late February to early May 2020. The novelty of incorporating the geographic spread of the pandemic leads to a surprisingly good agreement with published confirmed case reports. The numerical analysis validates the high degree of predictability of our proposed SaucIR model compared to existing resemblance. The proposed forecasting SaucIR model is implemented in Python. A web-based application is also developed by Dash (under construction).

stat.AP↗

arXiv2020

A Group Norm Regularized Factorization Model for Subspace Segmentation

Subspace segmentation assumes that data comes from the union of different subspaces and the purpose of segmentation is to partition the data into the corresponding subspace. Low-rank representation (LRR) is a classic spectral-type method for solving subspace segmentation problems, that is, one first obtains an affinity matrix by solving a LRR model and then performs spectral clustering for segmentation. This paper proposes a group norm regularized factorization model (GNRFM) inspired by the LRR model for subspace segmentation and then designs an Accelerated Augmented Lagrangian Method (AALM) algorithm to solve this model. Specifically, we adopt group norm regularization to make the columns of the factor matrix sparse, thereby achieving a purpose of low rank, which means no Singular Value Decompositions (SVD) are required and the computational complexity of each step is greatly reduced. We obtain affinity matrices by using different LRR models and then performing cluster testing on different sets of synthetic noisy data and real data, respectively. Compared with traditional models and algorithms, the proposed method is faster and more robust to noise, so the final clustering results are better. Moreover, the numerical results show that our algorithm converges fast and only requires approximately ten iterations.

cs.LG↗

arXiv2019

Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention

Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person ReID. Many existing methods tackle this problem by average/maximum temporal pooling or RNNs with attention. However, these methods cannot deal with temporal dependency and spatial misalignment problems at the same time. We are inspired by video action recognition that involves the identification of different actions from video tracks. Firstly, we use 3D convolutions on video volume, instead of using 2D convolutions across frames, to extract spatial and temporal features simultaneously. Secondly, we use a non-local block to tackle the misalignment problem and capture spatial-temporal long-range dependencies. As a result, the network can learn useful spatial-temporal information as a weighted sum of the features in all space and temporal positions in the input feature map. Experimental results on three datasets show that our framework outperforms state-of-the-art approaches by a large margin on multiple metrics.

cs.CV↗

arXiv2018

Geometric Operator Convolutional Neural Network

The Convolutional Neural Network (CNN) has been successfully applied in many fields during recent decades; however it lacks the ability to utilize prior domain knowledge when dealing with many realistic problems. We present a framework called Geometric Operator Convolutional Neural Network (GO-CNN) that uses domain knowledge, wherein the kernel of the first convolutional layer is replaced with a kernel generated by a geometric operator function. This framework integrates many conventional geometric operators, which allows it to adapt to a diverse range of problems. Under certain conditions, we theoretically analyze the convergence and the bound of the generalization errors between GO-CNNs and common CNNs. Although the geometric operator convolution kernels have fewer trainable parameters than common convolution kernels, the experimental results indicate that GO-CNN performs more accurately than common CNN on CIFAR-10/100. Furthermore, GO-CNN reduces dependence on the amount of training examples and enhances adversarial stability. In the practical task of medically diagnosing bone fractures, GO-CNN obtains 3% improvement in terms of the recall.

cs.CV↗

arXiv2015

Splitting and successively solving augmented Lagrangian method for optimization with semicontinuous variables and cardinality constraint

We propose a new splitting and successively solving augmented Lagrangian (SSAL) method for solving an optimization problem with both semicontinuous variables and a cardinality constraint. This optimization problem arises in several contexts such as the portfolio selection problem, the compressed sensing problem and the unit commitment problem, etc. The problem is in general NP-hard. We derive an optimality condition for this optimization problem, under some suitable assumptions. By introducing an auxiliary variable and using an augmented Lagrangian function, the constraints are decomposed into two parts. By fixing particular variables, the optimization problem is split into two subproblems, which are solved alternatively. Furthermore, we prove the convergence of SSAL, under some suitable assumptions. Finally, we implement our method for the portfolio selection problem and the compressed sensing problem, respectively. Real world data and simulation study show that SSAL outperforms the well-known CPLEX 12.6 and the penalty decomposition (PD) method, while enjoying a similar cardinality of decision variable. For example, the numerical results are even nearly 200 times faster than that of CPLEX 12.6 for the portfolio selection problem, and more than 40 times faster than PD method for the compressed sensing problem, respectively. In particularly, SSAL is powerful when the size of problem increase largely.

math.OC↗