检索结果-内蒙古大学图书馆

arXiv 2022年

作者： He, Kun Wang, Chunyang Yin, Yitong The Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China No. 59 Zhongguancun Street Haidian District Beijing China State Key Laboratory for Novel Software Technology Nanjing University 163 Xianlin Avenue Jiangsu Province Nanjing China

We give a fast algorithm for sampling uniform solutions of general constraint satisfaction problems (CSPs) in a local lemma regime. Suppose that the CSP has n variables with domain size at most q, each constraint contains at most k variables, shares variables with at most Δ constraints, and is violated with probability at most p by a uniform random assignment. The algorithm returns an almost uniform satisfying assignment in expected poly(q,k, Δ) ·(n) time, as long as a local lemma condition is satisfied: k · p · q2 · Δ5 ≤ C0 for a suitably small absolute constant C0. Previously, under similar local lemma conditions, sampling algorithms with running time polynomial in both nand Δ were only known for the almost atomic case, where each constraint is violated by a small number of forbidden local configurations. The key term Δ5 in our local lemma condition also improves the previously best known Δ7 for general CSPs [JPV21b] and Δ5.714 for atomic CSPs, including the special case of k-CNF [JPV21a, HSW21]. Our sampling approach departs from previous fast algorithms for sampling LLL, which were based on Markov chains. A crucial step of our algorithm is a recursive marginal sampler that is of independent interests. Within a local lemma regime, this marginal sampler can draw a random value for a variable according to its marginal distribution, at a cost independent of the size of the CSP. Copyright © 2022, The Authors. All rights reserved.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Context-Dependent Propagating-Based Video Recommendation in Multimodal Heterogeneous Information Networks

引用

IEEE Transactions on Multimedia 2021年 23卷 2019-2032页

作者： Lei Sang Min Xu Shengsheng Qian Matt Martin Peter Li Xindong Wu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei China Faculty of Engineering and Information Technology University of Technology Sydney Sydney NSW Australia Institute of Automation Chinese Academy of Sciences Beijing China INTERACT Technology Sydney NSW Australia Mininglamp Academy of Sciences Mininglamp Technology Beijing China

With the emergence of online social networks (OSNs), video recommendation has come to play a crucial role in mitigating the semantic gap between users and videos. Conventional approaches to video recommendation primarily focus on exploiting content features or simple user-video interactions to model the users’ preferences. Although these methods have achieved promising results, they fail to model the complex video context interdependency, which is obscure/hidden in heterogeneous auxiliary data from OSNs. In this paper, we study the problem of video recommendation in Heterogeneous Information Networks (HINs) due to its excellence in characterizing heterogeneous and complex context information. We propose a Context-Dependent Propagating Recommendation network (CDPRec) to obtain accurate video embedding and capture global context cues among videos in HINs. The CDPRec can iteratively propagate the contexts of a video along links in a graph-structured HIN and explore multiple types of dependencies among the surrounding video nodes. Then, each video is represented as the composition of the multimodal content feature and global dependency structure information using an attention network. The learned video embedding with sequential based recommendation are jointly optimized for the final rating prediction. Experimental results on real-world YouTube video recommendation scenarios demonstrate the effectiveness of the proposed methods compared with strong baselines.

关键词： Semantics Collaboration YouTube Australia Visualization Context modeling

来源：评论

学校读者我要写书评

暂无评论

Classification of Epileptic and Non-epileptic Events using Tensor Decomposition

Classification of Epileptic and Non-epileptic Events using T...

引用

IEEE International Conference on Bioinformatics and Bioengineering

作者： Vasileios G. Kanas Evangelia I. Zacharaki Evangelia Pippa Vasiliki Tsirka Michael Koutroumanidis Vasileios Megalooikonomou Multidimensional Data Analysis and Knowledge Management Laboratory Dept. of Computer Engineering and Informatics University of Patras Dept. of Clinical Neurophysiology and Epilepsies Guy's & St. Thomas' and Evelina Hospital for Children

ISBN: (纸本)9781467379847

Misdiagnosis of epilepsy, even by experienced clinicians, can cause exposure of patients to medical procedures and treatments with potential complications. Moreover, diagnostic delays (for 7 to 10 years on average) impose economic burden at individual and population levels. In this paper, a seizure classification framework of epileptic and non-epileptic events from multi-channel EEG data is proposed. In contrast to relevant studies found in the literature, in this study, the non-epileptic class consists of two types of paroxysmal episodes of loss of consciousness, namely the psychogenic non-epileptic seizure (PNES) and the vasovagal syncope (VVS). EEG signals are represented in the spectral-spatial-temporal domain. A tensor-based approach is employed to extract signature features to feed the classification models. TUCKER decomposition is applied to learn the essence of original, high-dimensional domain of feature space and extract a multilinear discriminative subspace. The classification models were evaluated on EEG epochs from 11 subjects in an inter-subject cross-validation setting and achieved an accuracy of 96%.

关键词： Electroencephalography Feature extraction Tensile stress Epilepsy Brain models Training

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

Suppress Content Shift: Better Diffusion Features via Off-th...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

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

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

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 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

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

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 this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Short Text Classification Based On Dual-channel data Augmentation

Semi-supervised Short Text Classification Based On Dual-chan...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jiajun Li Peipei Li Xuegang Hu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei City Anhui Province China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei City Anhui Province China

In practical applications, high-quality labeled data is critical for short text classification. But in many cases, it is expensive and time-consuming to obtain labeled information. Semi-supervised short text classification is hence attracting more attention. However, due to the sparsity of short texts, the performance of existing short text classification models always needs to be improved. Therefore, in this paper, we propose a semi-supervised Short text classification method based on Dual-Channel data Augmentation called SDCA. More specifically, in order to solve the sparsity of short texts, this model first adopts the multi-stage word-level TCN (Temporal Convolutional Network)-based attention to enhanced semantic features and an one-dimensional convolution-based attention mechanism to augment the relevance of surrounding short texts. Secondly, the unlabeled data are augmented by word embedding weighted augmentation and word replacement augmentation, so that the model can make full use of the unlabeled short texts and further enhance the network training. Finally, extensive experiments conducted on four benchmark datasets demonstrate the effectiveness of the proposed model on semi-supervised short text classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition

arXiv

引用

arXiv 2021年

作者： Fan, Zhaoxin Song, Zhenbo Liu, Hongyan Lu, Zhiwu He, Jun Du, Xiaoyong Key Laboratory of Data Engineering Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Management Science and Engineering Tsinghua University Beijing100084 China

Simultaneous Localization and Mapping (SLAM) and Autonomous Driving are becoming increasingly more important in recent years. Point cloud-based large scale place recognition is the spine of them. While many models have been proposed and have achieved acceptable performance by learning short-range local features, they always skip long-range contextual properties. Moreover, the model size also becomes a serious shackle for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net. On top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed respectively to learn both short-range local features and long-range contextual features. Consisting of ASVT and CSVT, SVT-Net can achieve state-of-the-art performance in terms of both recognition accuracy and running speed with a super-light model size (0.9M parameters). Meanwhile, for the purpose of further boosting efficiency, we introduce two simplified versions, which also achieve state-of-the-art performance and further reduce the model size to 0.8M and 0.4M respectively. Copyright © 2021, 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

The K-Step H Indices in Citation Networks at the Paper, Author, and Institution Levels

SSRN

引用

SSRN 2023年

作者： Yang, Alex Jie Wu, Linwei Zhang, Qi Wang, Hao Deng, Sanhong School of Information Management Nanjing University 22 Hankou Rd. Nanjing210093 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing University Nanjing210093 China International Joint Informatics Laboratory Nanjing University China

From the viewpoint of high-generation citation networks, h indices can be extended to global metrics at both basic and aggregated levels. To accomplish this, three types of networks are designed: the paper-paper network, the author-paper-paper network, and the institution-paper-paper network. The k-step h index is then proposed at the level of papers, authors, and institutions, respectively. Through a comprehensive empirical study based on the APS dataset, it is found that the k-step h index extends the depth and dimensionality of the Hirsh core, allowing for more global information. The consistency and convergent validity of the k-step h indices are quantitatively assessed. The results indicate that the k-step h index demonstrates a high degree of consistency and focuses on the potential for further research, and is capable of measuring the long-term reputation rather than short-term popularity. The convergent validity of the k-step h indices is rigorously tested using benchmark examples such as Nobel laureates and their publications, and they demonstrate superior performance in identifying seminal papers and prominent scientists compared to traditional metrics at the paper and author levels. The k-step h index also excels in ranking institutions, offering a promising new approach for evaluating the impact and influence of scientific entities at both the basic and aggregate levels. This opens up exciting avenues for future research. © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

BanFEL: A Blockchain Based Smart Contract for Fair and Efficient Lottery Scheme

BanFEL: A Blockchain Based Smart Contract for Fair and Effic...

引用

IEEE Conference on Dependable and Secure Computing

作者： Jiasheng Li Zijian Zhang Meng Li Beijing Engineering Research Center of Massive Language Information Beijing Institute of Technology Beijing China School of Computer Science University of Auckland Aukland New Zealand Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Hefei University of Technology Anhui China

Lottery is a game with many people's dreams. But corruptions of lottery centers make the lottery unfair. To address this unfair issue, fair lottery schemes have been studied for several years. In these schemes, delay functions or aggregation protocols can be used to generate the winning numbers fairly. However, to the best of our knowledge, none of the existing schemes can achieve the winning number generated randomly, while the randomness can be verified fairly. In this article, we first propose a [B]lockchain based sm[a]rt co[n]tract for [F]air and [E]fficient [L]ottery (BanFEL) scheme. We further present a winning number random generation smart contract, by which players submit the purchased numbers and the non-tampering property is protected. Security analysis and experiments show that the fairness of BanFEL is protected better than the existing works. Meanwhile, the verification cost of this scheme are at least 0.03s lower than the traditional Grumbach's scheme between 1000 and 10000 players.

关键词： Blockchain Smart contracts Security Mathematical model Privacy Information processing

来源：评论

学校读者我要写书评

暂无评论

Counterfactual Faithful data Generation Based on Disentangled Representation for Compound Fault Diagnosis of Rolling Bearings

Counterfactual Faithful Data Generation Based on Disentangle...

引用

Sensing, Measurement & data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Xu Ding Qiang Zhu Song Wang Yiqi Zhang Hui Wang Juan Xu Institute of Industry and Equipment Technology Hefei University of Technology Hefei China School of Mechanical Engineering Hefei University of Technology Hefei China Bengbu Triumph Engineering Technology Co. Ltd Bengbu China Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology Hefei China

Recently, deep learning and human-out-of-the-loop methods enjoy their prosperous applications in mechanical fault diagnosis. Nonetheless, the None-IID(independent and identically distributed) issue radicated in acquired data severely limits the stability and accuracy of compound fault diagnosis of rolling bearings. This paper proposes a sample augmentation method for generating simulated signals based on the concept of counterfactuals. Firstly, disentangled representations and counterfactual faithful theory are applied to classify the original signal into two categories of properties. One is the fault semantics encoded from the original vibration signal. And the other is the sample attribute encoded by the encoder of Variational Autoencoders (VAEs). Secondly, the counterfactual faithful pseudo-samples are conjured through the Generative Adversarial Network(GAN) using the seeds of the “factual” sample attributes and “counterfactual” fault semantics to compensate for the drawback of distribution shift. Finally, the original samples and pseudo-samples are used as the CNN classifier dataset to realize bearing fault diagnosis. Experiments show that this method can generate counterfactual signals that are highly consistent with the original data distribution and can achieve better classification accuracy after balancing the dataset.

关键词： Fault diagnosis Wavelet transforms Vibrations Semantics Rolling bearings Feature extraction Stability analysis

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：