检索结果-内蒙古大学图书馆

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Zhu Cuiling Yang Chengwei School of Management Science and Engineering Shandong University of Finance and Economic Big Data and Artificial Intelligence Lab Shandong University of Finance and Economic Intelligent Elderly Care and Big Data Engineering Laboratory of ShanDong Province Ji'Nan China

ISBN: (纸本)9781728194202

With the advent of big data, the construction of new engineering in higher education is urgently required, and the requirements of information management and information system specialty(IMIS for short) in big data analysis and application are also increased. The integration between industry and education is an effective way for IMIS to cultivate new engineering talents needed by the society. It firstly analyzed the current situation of integration between industry, education for IMIS. On this basis, the cultivation mode of big data talents for IMIS based on the deep integration between industry and education is discussed, which are include the construction of application-oriented and innovative talents cultivation system, the curriculum practice system of big data course, and the policy of government financial support.

关键词： Industries Training Economics Technological innovation Government Buildings big data

来源：评论

学校读者我要写书评

暂无评论

Structure-Aware DropEdge Towards Deep Graph Convolutional Networks

arXiv

引用

arXiv 2023年

作者： Han, Jiaqi Huang, Wenbing Rong, Yu Xu, Tingyang Sun, Fuchun Huang, Junzhou Department of Computer Science and Technology Tsinghua University Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tencent AI Lab Shenzhen China Department of Computer Science and Engineering The University of Texas Arlington United States

It has been discovered that Graph Convolutional Networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. The main factor that accounts for why deep GCNs fail lies in over-smoothing, which isolates the network output from the input with the increase of network depth, weakening expressivity and trainability. In this paper, we start by investigating refined measures upon DropEdge—an existing simple yet effective technique to relieve over-smoothing. We term our method as DropEdge++ for its two structure-aware samplers in contrast to DropEdge: layer-dependent sampler and feature-dependent sampler. Regarding the layer-dependent sampler, we interestingly find that increasingly sampling edges from the bottom layer yields superior performance than the decreasing counterpart as well as DropEdge. We theoretically reveal this phenomenon with Mean-Edge-Number (MEN), a metric closely related to over-smoothing. For the feature-dependent sampler, we associate the edge sampling probability with the feature similarity of node pairs, and prove that it further correlates the convergence subspace of the output layer with the input features. Extensive experiments on several node classification benchmarks, including both full- and semi- supervised tasks, illustrate the efficacy of DropEdge++ and its compatibility with a variety of backbones by achieving generally better performance over DropEdge and the no-drop version. Copyright © 2023, The Authors. All rights reserved.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

WebCode2M: A Real-World dataset for Code Generation from Webpage Designs

arXiv

引用

arXiv 2024年

作者： Gui, Yi Li, Zhen Wan, Yao Shi, Yemin Zhang, Hongyu Su, Yi Chen, Bohua Chen, Dongping Wu, Siyuan Zhou, Xing Jiang, Wenbin Jin, Hai Zhang, Xiangliang Huazhong University of Science and Technology Wuhan China Peking University Beijing China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our investigation reveals that most existing MLLMs are constrained by the absence of high-quality, large-scale, real-world datasets, resulting in inadequate performance in automated webpage code generation. To fill this gap, this paper introduces WebCode2M, a new dataset comprising 2.56 million instances, each containing a design image along with the corresponding webpage code and layout details. Sourced from real-world web resources, WebCode2M offers a rich and valuable dataset for webpage code generation across a variety of applications. The dataset quality is ensured by a scoring model that filters out instances with aesthetic deficiencies or other incomplete elements. To validate the effectiveness of WebCode2M, we introduce a baseline model based on the Vision Transformer (ViT), named WebCoder, and establish a benchmark for fair comparison. Additionally, we introduce a new metric, TreeBLEU, to measure the structural hierarchy recall. The benchmarking results demonstrate that our dataset significantly improves the ability of MLLMs to generate code from webpage designs, confirming its effectiveness and usability for future applications in front-end design tools. Finally, we highlight several practical challenges introduced by our dataset, calling for further research. The code and dataset are publicly available at our project homepage: https://***. Copyright © 2024, The Authors. All rights reserved.

关键词： Web Design

来源：评论

学校读者我要写书评

暂无评论

DEEP GENERATIVE MODELING ON LIMITED data WITH REGULARIZATION BY NONTRANSFERABLE PRE-TRAINED MODELS

arXiv

引用

arXiv 2022年

作者： Zhong, Yong Liu, Hongtao Liu, Xiaodong Bao, Fan Shen, Weiran Li, Chongxuan Gaoling School of AI Renmin University of China Beijing China Beijing Key Lab of Big Data Management and Analysis Methods Beijing China Department of Computer Science Technology Tsinghua University Beijing China

Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized deep generative model (Reg-DGM), which leverages a nontransferable pre-trained model to reduce the variance of generative modeling with limited data. Formally, Reg-DGM optimizes a weighted sum of a certain divergence and the expectation of an energy function, where the divergence is between the data and the model distributions, and the energy function is defined by the pre-trained model w.r.t. the model distribution. We analyze a simple yet representative Gaussian-fitting case to demonstrate how the weighting hyperparameter trades off the bias and the variance. Theoretically, we characterize the existence and the uniqueness of the global minimum of Reg-DGM in a non-parametric setting and prove its convergence with neural networks trained by gradient-based methods. Empirically, with various pre-trained feature extractors and a data-dependent energy function, Reg-DGM consistently improves the generation performance of strong DGMs with limited data and achieves competitive results to the state-of-the-art methods. Our implementation is available at https://***/ML-GSAI/Reg-ADA-APA. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

3D-STGPCN: 3D Spatio-Temporal Graph Point-wise Convolutional Network for Traffic Forecasting

3D-STGPCN: 3D Spatio-Temporal Graph Point-wise Convolutional...

引用

IEEE International Conference on big data

作者： Manh-Phu Nguyen Minh-Son Dao Thanh-Binh Nguyen AISIA Research Lab University of Science (VNU-HCMUS) Vietnam National University HCM City Vietnam Big Data Integration Research Center National Institute of Information and Communications Technology (NICT) Tokyo Japan

ISBN: (纸本)9781665480468

Traffic forecasting has been an important research topic in the intelligent transportation system for smooth and safe transportation. Among research directions, spatiotemporal-graph-based traffic forecasting has been known as one of the popular directions. Unfortunately, many requirements, such as lightweight architecture, low resource consumption, and flexible transfer learning, have not had satisfactory answers. Hence, we propose a new method called 3D Spatial Temporal Graph Point-wise Convolutional Network (3D-STGPCN) to address these requirements. Differing from others, we proceed with spatial and temporal information simultaneously (i.e., wrap them into one structure). We evaluate and compare our model on three public traffic network datasets, METR-LA, PEMS-BAY, and STREETS, with different methods in the same domain. The experimental results show the advantage of our model over others. We publish our source code at https://***/dophanh-26/3D-STGPCN.

关键词： Three-dimensional displays Convolution Source coding Transfer learning Transportation big data Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Equivariant graph hierarchy-based neural networks 22

Equivariant graph hierarchy-based neural networks

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jiaqi Han Wenbing Huang Tingyang Xu Yu Rong Department of Computer Science and Technology Tsinghua University Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tencent AI Lab

ISBN: (纸本)9781713871088

Equivariant Graph neural Networks (EGNs) are powerful in characterizing the dynamics of multi-body physical systems. Existing EGNs conduct flat message passing, which, yet, is unable to capture the spatial/dynamical hierarchy for complex systems particularly, limiting substructure discovery and global information fusion. In this paper, we propose Equivariant Hierarchy-based Graph Networks (EGHNs) which consist of the three key components: generalized Equivariant Matrix Message Passing (EMMP), E-Pool and E-UnPool. In particular, EMMP is able to improve the expressivity of conventional equivariant message passing, E-Pool assigns the quantities of the low-level nodes into high-level clusters, while E-UnPool leverages the high-level information to update the dynamics of the low- level nodes. As their names imply, both E-Pool and E-UnPool are guaranteed to be E(n)-equivariant to meet the physical symmetry. Considerable experimental evaluations verify the effectiveness of our EGHN on several applications including multi-object dynamics simulation, motion capture, and protein dynamics modeling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Interest Modeling of Long-tailed Users for Click-Through Rate Prediction

Hierarchical Interest Modeling of Long-tailed Users for Clic...

引用

International Conference on data Engineering

作者： Xu Xie Jin Niu Lifang Deng Dan Wang Jiandong Zhang Zhihua Wu Kaigui Bian Gang Cao Bin Cui School of CS & Key Laboratory of High Confidence Software Technologies (MOE) Peking University Alibaba Group China Lazada National Engineering Lab for Big Data Analysis and Applications Beijing Academy of Artificial Intelligence (BAAI) Institute of Computational Social Science Peking University Qingdao China

Click-through rate (CTR) prediction, whose purpose is to predict the probability of a user clicking on an item, plays a pivotal role in recommender systems. Capturing users’ accurate preferences from their historical interactions (e.g., clicks) is an essential step for handling this task and has aroused wide concern in both academia and industry. However, most of the previous methods focus on the users with abundant clicks and ill-serve the users who rarely click or purchase items. Though the ratio of these long-tailed users may be small on popular platforms, such as Amazon and Taobao, they are the majority on the newborn e-commerce company like Lazada. To extract the interests of long-tailed users, several works attempt to integrate the side information, such as demographic features. Nevertheless, these features are usually not available and may even lead to privacy concerns. Therefore, how to utilize the noisy and limited clicks becomes the key *** this paper, we propose a novel model called Hierarchical Interest Modeling (HIM). It hierarchically utilizes long-tailed users’ limited behaviors and captures their preferences from both personalized and group-wise perspectives. HIM consists of two main components, including User Behavior Pyramid (UBP) and User Behavior Clustering (UBC). The UBP module utilizes additional negative feedback to reduce the noises in positive feedback, thus obtaining reliable user personalized representations. Then, the UBC module automatically discovers latent user groups with self-supervised reconstruction loss and learns another interest representation for each user in a group-wise aspect. Extensive experiments on both public and industrial datasets verify the superiority of HIM compared with the state-of-the-art baselines. Moreover, HIM has already been deployed on Lazada recommendation scenario and gains 3.38% on CTR prediction on average on the online A/B test. Our codes are available in https://***/xiaojin-nj/HIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FR²Seg: Continual Segmentation Across Multiple Sites via Fourier Style Replay and Adaptive Consistency Regularization 39

FR<sup>2</sup>Seg: Continual Segmentation Across Multiple Si...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Cheng Zhang, Weiwen Zhang, Hongrui Xu, Xuemiao Zhang, Huaidong Zou, Jing Qin, Jing South China University of Technology China The Hong Kong Polytechnic University Hong Kong Guangdong Engineering Center for Large Model and GenAI Technology China State Key Laboratory of Subtropical Building Science China Ministry of Education Key Laboratory of Big Data and Intelligent Robot China Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China

ISBN: (纸本)157735897X

In clinical imaging, medical segmentation networks typically require continually adapting to new data from multiple sites over time, as aggregating all data for learning at once can be impractical due to storage limitations and privacy concerns. However, existing methods basically overlook domain-specific characteristics and fall short of adequately capturing domain-invariant knowledge during continual learning, leading to undesired catastrophic forgetting of previous sites and inferior generalization to new sites. To tackle this issue, this paper introduces FR²Seg, to sufficiently exploit both domain-specific and domain-invariant knowledge for efficient continual learning with the aid of low-frequency cues. For the former aspect, we propose a Fourier style replay module to synthesize pseudo images with old-site styles for data augmentation during new-site training, effectively preventing catastrophic forgetting without sacrificing data privacy. For the latter, we present a Fourier adaptive consistency regularization to identify and constrain the optimization of domain-invariant parameters with explicit awareness of knowledge transferability across sites, ensuring excellent generalizability to new sites. Experimental results on two public datasets confirm our method's superiority over existing state-of-the-art continual learning methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Motif-based graph self-supervised learning for molecular property prediction 21

Motif-based graph self-supervised learning for molecular pro...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Zaixi Zhang Qi Liu Hao Wang Chengqiang Lu Chee-Kong Lee Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Tencent America

ISBN: (纸本)9781713845393

Predicting molecular properties with data-driven methods has drawn much attention in recent years. Particularly, Graph Neural Networks (GNNs) have demonstrated remarkable success in various molecular generation and prediction tasks. In cases where labeled data is scarce, GNNs can be pre-trained on unlabeled molecular data to first learn the general semantic and structural information before being finetuned for specific tasks. However, most existing self-supervised pre-training frameworks for GNNs only focus on node-level or graph-level tasks. These approaches cannot capture the rich information in subgraphs or graph motifs. For example, functional groups (frequently-occurred subgraphs in molecular graphs) often carry indicative information about the molecular properties. To bridge this gap, we propose Motif-based Graph Self-supervised Learning (MGSSL) by introducing a novel self-supervised motif generation framework for GNNs. First, for motif extraction from molecular graphs, we design a molecule fragmentation method that leverages a retrosynthesis-based algorithm BRICS and additional rules for controlling the size of motif vocabulary. Second, we design a general motif-based generative pre-training framework in which GNNs are asked to make topological and label predictions. This generative framework can be implemented in two different ways, i.e., breadth-first or depth-first. Finally, to take the multi-scale information in molecular graphs into consideration, we introduce a multi-level self-supervised pre-training. Extensive experiments on various downstream benchmark tasks show that our methods outperform all state-of-the-art baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assist Quasi-Affine Transformation Evolutionary for Multi-Objective Optimization of Empty Train Deployment on Heavy-Haul Railways

SSRN

引用

SSRN 2023年

作者： Du, Zhi-Gang Pan, Jeng-Shyang Xu, He-Ying Chu, Shu-Chuan Ni, Shao-Quan School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu610031 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031 China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031 China

In recent years, surrogate-assisted evolutionary algorithms have become increasingly popular for solving expensive and time-consuming single-objective and multi-objective problems. However, in multi-objective optimization, the Pareto non-dominated solution set space can quickly become computationally intractable, making it challenging to select which samples to evaluate using the expensive fitness function. In this paper, we propose a novel surrogate-assist QUasi-Affine TRansformation Evolutionary algorithm (SA-QUATRE/MO) for solving multi-objective optimization problems. The SA-QUATRE/MO algorithm uses a radial basis neural network as a surrogate model to improve the speed of the algorithm operation by replacing the expensive fitness evaluation with the surrogate model. To ensure the excellence and diversity of the selected samples while keeping the archived sample space fixed, we propose a technique called Vector Space Sampling, which samples objective points in the current set of non-dominated solutions by dividing several sub-vector spaces. Additionally, we propose an uncertain sample infilling strategy to select samples for real fitness evaluation using a designed uncertainty function. We compare the SA-QUATRE/MO algorithm with three state-of-the-art algorithms for multi-objective problems in the DTLZ, MaF, and ZDT test function suites. Finally, we apply the SA-QUATRE/MO algorithm to solve the optimization problem of the empty train deployment at the loading end of a heavy-haul railway. We build a model based on the S12 section of a certain railway and optimize it using the SA-QUATRE/MO algorithm, demonstrating the effectiveness and practicality of our proposed approach. © 2023, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：