检索结果-内蒙古大学图书馆

DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fields

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Xuhui Yu, Fugang Hou, Fei Wang, Wencheng Zhang, Zhebin He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China The OPPO Research Center United States The College of Computing and Data Science Nanyang Technological University Singapore

Unsigned distance fields (UDFs) allow for the representation of models with complex topologies, but extracting accurate zero level sets from these fields poses significant challenges, particularly in preserving topological accuracy and capturing fine geometric details. To overcome these issues, we introduce DCUDF2, an enhancement over DCUDF-the current state-of-the-art method-for extracting zero level sets from UDFs. Our approach utilizes an accuracy-aware loss function, enhanced with self-adaptive weights, to improve geometric quality significantly. We also propose a topology correction strategy that reduces the dependence on hyper-parameter, increasing the robustness of our method. Furthermore, we develop new operations leveraging self-adaptive weights to boost runtime efficiency. Extensive experiments on surface extraction across diverse datasets demonstrate that DCUDF2 outperforms DCUDF and existing methods in both geometric fidelity and topological accuracy. We will make the source code publicly available. © 2024, CC BY.

关键词：

Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xia, Xiaobo Liu, Xiaofeng Liu, Jiale Fang, Kuai Lu, Lu Oymak, Samet Currie, William S. Liu, Tongliang School of Computer Science University of Sydney Australia Department of Statistics and Data Science Yale University United States Michigan Institute for Data and AI in Society University of Michigan United States School for Environment and Sustainability University of Michigan United States College of Information Science and Technology Penn State University United States Department of Earth System Science Stanford University United States Department of Electrical Engineering and Computer Science University of Michigan United States

Water quality is foundational to environmental sustainability, ecosystem resilience, and public health. Deep learning models, particularly Long Short-Term Memory (LSTM) networks, offer trans-formative potential for large-scale water quality prediction and scientific insights generation. However, their widespread adoption in high-stakes decision-making, such as pollution mitigation and equitable resource allocation, is prevented by unresolved trustworthiness challenges including fairness, uncertainty, interpretability, robustness, generalizability, and reproducibility. In this work, we present the first comprehensive evaluation of trustworthiness in a continental-scale multi-task LSTM model predicting 20 water quality variables (encompassing physical/chemical processes, geochemical weathering, and nutrient cycling) across 482 U.S. basins. Our investigation uncovers systematic patterns of model performance disparities linked to basin characteristics, the inherent complexity of biogeochemical processes, and variable predictability, emphasizing critical performance fairness concerns. We further propose methodological frameworks for quantitatively evaluating critical aspects of trustworthiness, including uncertainty, interpretability, and robustness, identifying key limitations that could challenge reliable real-world deployment. This work serves as a timely call to action for advancing trustworthy data-driven methods for water resources management and provides a pathway to offering critical insights for researchers, decision-makers, and practitioners seeking to leverage artificial intelligence (AI) responsibly in environmental management. Copyright © 2025, The Authors. All rights reserved.

关键词： Resource allocation

OPTIMIZATION MODELS TO MEET THE CONDITIONS OF ORDER PRESERVATION IN THE ANALYTIC HIERARCHY PROCESS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tu, Jiancheng Zhibin, Wu Li, Yueyuan XIang, Chuankai Department of Computing Hong Kong Polytechnic University Hong Kong Business School Sichuan University Chengdu610065 China City University of Hong Kong School of Data Science Kowloon Tong Hong Kong

Deriving a priority vector from a pairwise comparison matrix (PCM) is a crucial step in the Analytical Hierarchy Process (AHP). Although there exists a priority vector that satisfies the conditions of order preservation (COP), the priority vectors obtained through existing prioritization methods frequently violate these conditions, resulting in numerous COP violations. To address this issue, this paper introduces a novel procedure to manage COP violations in AHP. Firstly, we prove that the index-exchangeability condition is both a necessary and sufficient condition for determining whether a priority vector satisfies COP. This enables the direct detection of COP violations, relying solely on the pairwise comparison preferences of decision-makers, rather than the prioritization methods utilized. Subsequently, we propose the Minimal Number of Violations and Deviations Method (MNVDM) model, which aims to derive a priority vector with the minimal number of COP violations. In particular, the MNVDM can obtain a violation-free priority vector when the PCM meets the index exchangeability conditions. Furthermore, an optimization model based on minimizing information loss is designed to ensure the COP by revising the preferences when the index-exchangeability conditions are violated. Finally, the feasibility and efficiency of the proposed models are validated through numerical examples and Monte Carlo simulation experiments. Our implementation is available at: https://***/Tommytutu/COP. © 2024, CC BY.

关键词： Vectors

Gradient Tracking with Multiple Local SGD for Decentralized Non-Convex Learning

学校读者我要写书评

暂无评论

Gradient Tracking with Multiple Local SGD for Decentralized ...

IEEE Conference on Decision and Control

作者： Songyang Ge Tsung-Hui Chang School of Science and Engineering The Chinese University of Hong Kong Shenzhen and Shenzhen Research Institute of Big Data Shenzhen China

The stochastic Gradient Tracking (GT) method for distributed optimization, is known to be robust against the inter-client variance caused by data heterogeneity. However, the stochastic GT method can be communication-intensive, requiring a large number of communication rounds of message exchange for convergence. To address this challenge, this paper proposes a new communication-efficient stochastic GT algorithm called the Local Stochastic GT(LSGT) algorithm, which adopts the local stochastic gradient descent (local SGD) technique in the GT method. With LSGT, each agent can perform multiple SGD updates locally within each communication round. Although it is not known previously whether the stochastic GT method can benefit from the local SGD, we establish the conditions under which our proposed LSGT algorithm enjoys the linear speedup brought by local SGD. Compared with the existing work, our analysis requires less restrictive conditions on the mixing matrix and algorithm stepsize. Moreover, it reveals that the local SGD does not only reserve the resilience of the stochastic GT method against the data heterogeneity but also speeds up reducing the tracking error reduction in the optimization process. The experimental results demonstrate that the proposed LSGT exhibits improved convergence speed and robust performance in various heterogeneous environments.

关键词：

Unifying and Improving Graph Convolutional Neural Networks with Wavelet Denoising Filters 23

学校读者我要写书评

暂无评论

Unifying and Improving Graph Convolutional Neural Networks w...

32nd ACM World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Li, Xiaona Han, Huijin Yan, Xiaoran Sun, Lu Ning, Zhaolong Xia, Feng Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Graph convolutional neural network (GCN) is a powerful deep learning framework for network data. However, variants of graph neural architectures can lead to drastically different performance on different tasks. Model comparison calls for a unifying framework with interpretability and principled experimental procedures. Based on the theories from graph signal processing (GSP), we show that GCN's capability is fundamentally limited by the uncertainty principle, and wavelets provide a controllable trade-off between local and global information. We adapt wavelet denoising filters to the graph domain, unifying popular variants of GCN under a common interpretable mathematical framework. Furthermore, we propose WaveThresh and WaveShrink which are novel GCN models based on proven denoising filters from the signal processing literature. Empirically, we evaluate our models and other popular GCNs under a more principled procedure and analyze how trade-offs between local and global graph signals can lead to better performance in different datasets. © 2023 ACM.

关键词： Convolution

Overview of SMP-CAIL2020-Argmine:The Interactive Argument-Pair Extraction in Judgement Document Challenge

学校读者我要写书评

暂无评论

data Intelligence 2021年第2期3卷 287-307页

作者： Jian Yuan Zhongyu Wei Yixu Gao Wei Chen Yun Song Donghua Zhao Jinglei Ma Zhen Hu Shaokun Zou Donghai Li Xuanjing Huang School of Data Science Fudan UniversityShanghai 200433China Heilongjiang University Heilongjiang 150080China School of Mathematical Sciences Fudan UniversityShanghai 200433China China Judicial Big Data Institute Beijing 100043China THUNISOFT Co. Ltd.Beijing 100084China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China School of Computer Science Fudan UniversityShanghai 200433China

In this paper we present the results of the Interactive Argument-Pair Extraction in Judgement Document Challenge held by both the Chinese AI and Law Challenge(CAIL)and the Chinese National Social Media Processing Conference(SMP),and introduce the related data *** task challenged participants to choose the correct argument among five candidates proposed by the defense to refute or acknowledge the given argument made by the plaintiff,providing the full context recorded in the judgement documents of both *** received entries from 63 competing teams,38 of which scored higher than the provided baseline model(BERT)in the first phase and entered the second *** best performing system in the two phases achieved accuracy of 0.856 and 0.905,*** this paper,we will present the results of the competition and a summary of the systems,highlighting commonalities and innovations among participating *** SMP-CAIL2020-Argmine data set and baseline modelshave been already released.

关键词： Argumentation mining Judgement documents Natural language understanding Pretrained language model

An Overview on Machine Learning Methods for Partial Differential Equations: From Physics Informed Neural Networks to Deep Operator Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gonon, Lukas Jentzen, Arnulf Kuckuck, Benno Liang, Siyu Riekert, Adrian von Wurstemberger, Philippe Department of Mathematics Imperial College London United Kingdom School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen [CUHK-Shenzhen China Applied Mathematics: Institute for Analysis and Numerics Faculty of Mathematics and Computer Science University of Münster Germany School of Mathematics and Statistics Nanjing University of Science and Technology Nanjing China School of Data Science The Chinese University of Hong Kong Shenzhen [CUHK-Shenzhen China Mathematisches Institut Ludwig-Maximilians-Universität München Germany Risklab Department of Mathematics ETH Zurich Switzerland

The approximation of solutions of partial differential equations (PDEs) with numerical algorithms is a central topic in applied mathematics. For many decades, various types of methods for this purpose have been developed and extensively studied. One class of methods which has received a lot of attention in recent years are machine learning-based methods, which typically involve the training of artificial neural networks (ANNs) by means of stochastic gradient descent type optimization methods. While approximation methods for PDEs using ANNs have first been proposed in the 1990s they have only gained wide popularity in the last decade with the rise of deep learning. This article aims to provide an introduction to some of these methods and the mathematical theory on which they are based. We discuss methods such as physics-informed neural networks (PINNs) and deep BSDE methods and consider several operator learning approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Partial differential equations

MP-GAN: Cyber-Attack Detection and Localization for Cyber-Physical Systems with Multi-Process Generative Adversarial Networks*

学校读者我要写书评

暂无评论

MP-GAN: Cyber-Attack Detection and Localization for Cyber-Ph...

Artificial Intelligence of Things and Systems (AIoTSys), International Conference on

作者： Yikui Zhou Jie Wang Junnan Tang Chao Gou Zigui Jiang Dan Li See-Kiong Ng School of Software Engineering Sun-Yat Sen University Zhuhai China School of Intelligent Systems Engineering Sun-Yat Sen University Shenzhen China Institute of Data Science/School of Computing National University of Singapore

Cyber-Physical System (CPS) integrates sensing, computation, cybernetics, and networking to control a hybrid physical system consisting of different functional subsystems, making the production process more intelligent and controllable. However, cyber-attacks during its operation will lead to abnormal system behaviors or even system breakdowns. In recent years, data-driven anomaly detection methods have been adopted to judge whether the CPS system is under cyber-attacks based on rich sensor measurements to avoid further economic losses or safety issues. However, the multi-process essence of CPS has not been adequately addressed in existing works to locate the processes or points being attacked for in-time actions. In this work, we proposed a Multi-Process Generative Adversarial Network (MP-GAN) framework to detect anomalous CPS statuses and locate cyber-attacks. Specifically, the Long-Short-Term-Memory Recurrent Neural Networks (LSTM-RNN) was adopted as the base model to capture the temporal correlation of time series distributions, and the data was transferred between latent space and data space in a bi-directional manner, which regulated the generator to generate more realistic samples and thus better grasping the underline principles of the system. Moreover, parallel generators were employed to capture system performances at different physical processes, thus localizing the attacked CPS processes. Experiments on three CPS datasets, two collected from the Secure Water Treatment (SWaT) system and one collected from the water Distribution (WADI) system, showed that the proposed MP-GAN framework effectively reported anomalies caused by various cyber-attacks inserted in these complex multiprocess CPSs, which outperforms the state-of-the-art methods and can also locate most of the detected irregularities at the corresponding stages where the attacks were inserted.

关键词：

WHEN GNNS MEET SYMMETRY IN ILPS: AN ORBIT-BASED FEATURE AUGMENTATION APPROACH

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Qian Li, Lei Li, Qian Wu, Jianghua Wang, Akang Sun, Ruoyu Luo, Xiaodong Chang, Tsung-Hui Shi, Qingjiang School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Artificial Intelligence The Chinese University of Hong Kong Shenzhen China School of Software Engineering Tongji University Shanghai China

A common characteristic in integer linear programs (ILPs) is symmetry, allowing variables to be permuted without altering the underlying problem structure. Recently, GNNs have emerged as a promising approach for solving ILPs. However, a significant challenge arises when applying GNNs to ILPs with symmetry: classic GNN architectures struggle to differentiate between symmetric variables, which limits their predictive accuracy. In this work, we investigate the properties of permutation equivariance and invariance in GNNs, particularly in relation to the inherent symmetry of ILP formulations. We reveal that the interaction between these two factors contributes to the difficulty of distinguishing between symmetric variables. To address this challenge, we explore the potential of feature augmentation and propose several guiding principles for constructing augmented features. Building on these principles, we develop an orbit-based augmentation scheme that first groups symmetric variables and then samples augmented features for each group from a discrete uniform distribution. Empirical results demonstrate that our proposed approach significantly enhances both training efficiency and predictive performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Integer linear programming