检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Yang, Yifan Chen, Lin Zhou, Pan Ding, Xiaofeng Department of Computer Science University of California Santa BarbaraCA93106 United States National Engineering Research Center for Big Data Technology and System Lab Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430072 China

This paper considers online convex optimization (OCO) with generated i.i.d. stochastic constraints, where the distribution of environment is changing and the performance is measured by \textit{adaptive regret}. The stochastic constraints are disclosed at each round to the learner after the decision is made. Different from the previous non-adaptive constrained OCO algorithm which is generalized based on the traditional online gradient descent algorithm, we propose a novel \textit{Virtual queue based Following-the-Leader-History} (VFLH) strategy to make the constrained OCO algorithm adaptive and design the VFLH algorithm. In this setting, the algorithm firstly generalizes all the experts in the specified time interval, then decides the optimal decision with each expert and gives out the final choice by combining the predictions of active experts. In terms of the algorithm performance, there are two performance metrics to be evaluated, i.e., the bounds of constraint violation and regret. For the constraint violation, we bring in the multi-objective drift analysis approach to deal with the constraints via a virtual queue which provides a new method to bound the constraints violations. For the regret, we give out its upper bound and then achieve a corresponding lower bound that proves the upper bound is sufficiently tight. Finally, we provide some numerical experiments to validate the feasibility of our algorithm. © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

DACNet: A Dual-Attention Contrastive Learning Network for 3D Point Cloud Classification

DACNet: A Dual-Attention Contrastive Learning Network for 3D...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hang Sun Yuanyue Zhhang Shuifa Sun Jing Li Lin Cui Lei Zhang Hubei Engineering Technology Research Center for Farmland Environment Monitoring College of Computer and Information Technology China Three Gorges University Yichang China College of Computer and Information Technology China Three Gorges University Yichang China School of Computer Science Wuhan University Wuhan China Big data & New Technology Research Institute Suzhou University Anhui China

ISBN: (数字)9781728186719

ISBN: (纸本)9781665495264

Convolutional neural networks, which achieved remarkable results, have been widely used in object detection, anomaly detection, and point cloud classification. However, the unordered, sparsity and abnormal samples of point cloud make the classification result of point cloud still need to be improved in point cloud classification. This is because the local features correlation is seldom explored in most point cloud classification networks. In addition, Ground-Truth is only used as positive samples to guide networks training, and the use of negative information is neglected. In this paper, an efficient Dual-Attention Contrastive learning Network (DACNet) is developed. Specifically, DACNet includes a Feature Correlation Fusion (FCF) unit and a Contrastive Regularization Enhanced by Mixup (CREM) unit. The FCF unit primarily acts on local features of point cloud, and strengthens the interaction between local features from two aspects of channel information and positional information, to improve the expression ability of the extracted features of the network. In addition, the CREM ensures that features in the same category are pulled together and features in different categories are pushed away in the representation space, to improve the discriminant ability of the extracted features of the network during the training of DACNet. The experimental results show that, compared with existing excellent point cloud classification networks, the DACNet proposed in this paper achieves the best performance on the public synthetic and real-scene datasets such as ModelNet10, ModelNet40 and ScanObjectNN.

关键词： Point cloud compression Training Solid modeling Correlation Three-dimensional displays Neural networks Object detection

来源：评论

学校读者我要写书评

暂无评论

ToFM: Topic-specific Facet Mining by Facet Propagation within Clusters 12

ToFM: Topic-specific Facet Mining by Facet Propagation withi...

引用

12th IEEE International Conference on big Knowledge, ICBK 2021

作者： Li, Hongxuan Wei, Bifan Liu, Jun Guo, Zhaotong Qi, Jingchao Wu, Bei Liu, Yong Shi, Yuanyuan Xi'An Jiaotong University School of Computer Science and Technology Xi'an China Xi'An Jiaotong University National Engineering Lab For Big Data Analytics Xi'an China School of Continuous Education Xi'An Jiaotong University Xi'an China Servyou Software Group Co. Ltd. China

ISBN: (纸本)9781665438582

Mining the facets of topics is an essential task for information retrieval, information extraction and knowledge base construction. For the topics in courses, there are three challenges: different topics have different facet, the labels of facets rarely appear in the topic description text and not all topics have enough textural information to mine facets. In this paper we propose a weakly-supervised algorithm for topic-specific facet mining (ToFM for short) based on our finding that similar topics in a cluster have similar facet sets. For example, topics Binary Search Tree, Suffix Tree and AVL tree in Tree cluster have example, insertion, deletion, traversal and other similar facets. ToFM first splits topics in a domain into several topic clusters based on the topic description text. Then ToFM extracts initial facet sets for all topics from the corresponding Wikipedia article pages. Finally, ToFM performs a normalized facet propagation within each topic cluster to acquire final facet sets of every topic. We evaluate the performance of ToFM on six real-world datasets and experimental results show that ToFM achieves better performance than the existing facet mining algorithms. © 2021 IEEE.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A Two-Layer Surrogate-Assisted Fish Migration Optimization for Urban Rail Transit Train Route Optimization

SSRN

引用

SSRN 2022年

作者： Du, Zhi-Gang Pan, Jeng-Shyang Wang, Xiao-Yang 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

Meta-heuristic evolutionary algorithms have been widely used in global optimization problems. Still, the global optimization of meta-heuristic evolutionary algorithms relies on a large number of frequent fitness evaluations, which hinders their application in expensive and time-consuming real-world issues. For example, in a large-scale transportation network, due to the large search space and high computational complexity, the performance of the algorithm is degraded. After years of research, many scholars have proposed the idea of using the Surrogate-assisted model to reduce the number of real evaluations for expensive problems and solve the time-consuming global optimization problem in reality. To solve the high-dimensional and time-consuming problem, in reality, a two-layer Surrogate-assisted Fish Migration Optimization (SA-FMO) is proposed. The global surrogate-assisted model is an accurate fit for the entire search space. The local surrogate-assisted model is to capture the topographic details near the current optimal solution position and improves the accuracy estimation of local optimization. In order to verify the effectiveness of our proposed algorithm, this paper first tests six benchmark functions in 50 dimensions. Finally, The optimization of long and short routes in urban rail transit, also known as the Train Routing Optimization problem, is modeled and optimized using the SA-FMO algorithm to improve operational efficiency and accelerate vehicle turnover in the case of unbalanced passenger flow distribution in urban rail transit interruption surfaces. © 2022, The Authors. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit

arXiv

引用

arXiv 2023年

作者： Wan, Yao He, Yang Bi, Zhangqian Zhang, Jianguo Zhang, Hongyu Sui, Yulei Xu, Guandong Jin, Hai Yu, Philip S. 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 Huazhong University of Science and Technology Wuhan China Simon Fraser University Vancouver Canada School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Salesforce Research United States Chongqing University China University of New South Wales Australia University of Technology Sydney Australia University of Illinois at Chicago Chicago United States

Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is already a thriving research community focusing on code intelligence, with efforts ranging from software engineering, machine learning, data mining, natural language processing, and programming languages. In this paper, we conduct a comprehensive literature review on deep learning for code intelligence, from the aspects of code representation learning, deep learning techniques, and application tasks. We also benchmark several state-of-the-art neural models for code intelligence, and provide an open-source toolkit tailored for the rapid prototyping of deep-learning-based code intelligence models. In particular, we inspect the existing code intelligence models under the basis of code representation learning, and provide a comprehensive overview to enhance comprehension of the present state of code intelligence. Furthermore, we publicly release the source code and data resources to provide the community with a ready-to-use benchmark, which can facilitate the evaluation and comparison of existing and future code intelligence models (https://***). At last, we also point out several challenging and promising directions for future research. Copyright © 2023, The Authors. All rights reserved.

关键词： Computer programming languages

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

arXiv

引用

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Prior-Guided Adversarial Initialization for Fast Adversarial Training

arXiv

引用

arXiv 2022年

作者： Jia, Xiaojun Zhang, Yong Wei, Xingxing Wu, Baoyuan Ma, Ke Wang, Jue Cao, Xiaochun SKLOIS Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Tencent AI Lab Shenzhen China Institute of Artificial Intelligence Beihang University Beijing China School of Data Science Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China School of Computer Science and Technology UCAS Beijing China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Shenzhen518107 China

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e., the robust accuracy against adversarial attacks suddenly and dramatically decreases. Though several FAT variants spare no effort to prevent overfitting, they sacrifice much calculation cost. In this paper, we explore the difference between the training processes of SAT and FAT and observe that the attack success rate of adversarial examples (AEs) of FAT gets worse gradually in the late training stage, resulting in overfitting. The AEs are generated by the fast gradient sign method (FGSM) with a zero or random initialization. Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process. The initialization is formed by leveraging historically generated AEs without additional calculation cost. We further provide a theoretical analysis for the proposed initialization method. We also propose a simple yet effective regularizer based on the prior-guided initialization, i.e., the currently generated perturbation should not deviate too much from the prior-guided initialization. The regularizer adopts both historical and current adversarial perturbations to guide the model learning. Evaluations on four datasets demonstrate that the proposed method can prevent catastrophic overfitting and outperform state-of-the-art FAT methods. The code is released at https://***/jiaxiaojunQAQ/FGSM-PGI. 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

Semantic and syntactic enhanced aspect sentiment triplet extraction

arXiv

引用

arXiv 2021年

作者： Chen, Zhexue Huang, Hong Liu, Bang Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Huazhong University of Science and Technology China RALI & Mila University of Montreal

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment. Most existing research addresses this problem in a multi-stage pipeline manner, which neglects the mutual information between such three elements and has the problem of error propagation. In this paper, we propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model (S3E2) to fully exploit the syntactic and semantic relationships between the triplet elements and jointly extract them. Specifically, we design a Graph-Sequence duel representation and modeling paradigm for the task of ASTE: we represent the semantic and syntactic relationships between word pairs in a sentence by graph and encode it by Graph Neural Networks (GNNs), as well as modeling the original sentence by LSTM to preserve the sequential information. Under this setting, we further apply a more efficient inference strategy for the extraction of triplets. Extensive evaluations on four benchmark datasets show that S3E2 significantly outperforms existing approaches, which proves our S3E2’s superiority and flexibility in an end-to-end fashion. Copyright © 2021, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Classification of Coastal Wetland Based on Multi-objective CNN and Decision Fusion Model

Hyperspectral Classification of Coastal Wetland Based on Mul...

引用

Information Systems and Computing technology (ISCTech), International Conference on

作者： Yabin Hu Junfang Yang Guangbo Ren Yi Ma Jianbu Wang Xiaoheng Zhu Lab of Marine Physics and Remote Sensing First Institute of Oceanography Ministry of Natural Resources Qingdao China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xian China College of Oceanography and Space Informatics China University of Petroleum Qingdao China College of Geodesy and Geomatics ShanDong University of Science and Technology Qingdao China

Coastal wetland play an irreplaceable role in maintaining biodiversity and improving climate. In this paper, we proposed a hyperspectral classification algorithm of coastal wetland based on multi-objective Convolutional Neural Networks (CNN) and decision fusion model. The algorithm is named that the multi-objective spatial-spectral CNN classification with binary morphological strategy decision fusion model algorithm (MB2SCNN-BMSDF). The multi-objective hyperspectral feature band selection model of coastal wetland based on spectral deviation algorithm is developed and constructed to effectively obtain hyperspectral sensitive bands for single target surface object types. On this basis, a CNN hyperspectral classification model that integrates multi-objective spatial spectral information, and a binary morphological decision fusion algorithm that combines spatial position information and fuzzy membership degrees are proposed, which solves the problems of salt and pepper noise and sand eye effect in the classification process, and reduces noise information. The results showed that the CNN classification of multi-objective spatial spectral information and the decision fusion model of binary morphology strategy have better classification effect and performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not all diffusion model activations have been evaluated as discriminative features 24

Not all diffusion model activations have been evaluated as d...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at https://***/Darkbblue/generic-diffusion-feature.

关键词：

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：