检索结果-内蒙古大学图书馆

Disentangled Cascaded Graph Convolution Networks for Multi-Behavior Recommendation

ACM Transactions on Recommender Systems 2024年第4期2卷 1-27页

作者： Zhiyong Cheng Jianhua Dong Fan Liu Lei Zhu Xun Yang Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Shandong Artificial Intelligence Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computing National University of Singapore Singapore Singapore School of Electronic and Information Engineering Tongji University Shanghai China School of Information Science and Technology University of Science and Technology of China Hefei China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China and Hefei Comprehensive National Science Center Hefei China

Multi-behavioral recommender systems have emerged as a solution to address data sparsity and cold-start issues by incorporating auxiliary behaviors alongside target behaviors. However, existing models struggle to accurately capture varying user preferences across different behaviors and fail to account for diverse item preferences within behaviors. Various user preference factors (such as price or quality) entangled in the behavior may lead to sub-optimization problems. Furthermore, these models overlook the personalized nature of user behavioral preferences by employing uniform transformation networks for all users and items. To tackle these challenges, we propose the Disentangled Cascaded Graph Convolutional Network (Disen-CGCN), a novel multi-behavior recommendation model. Disen-CGCN employs disentangled representation techniques to effectively separate factors within user and item representations, ensuring their independence. In addition, it incorporates a multi-behavioral meta-network, enabling personalized feature transformation across user and item behaviors. Furthermore, an attention mechanism captures user preferences for different item factors within each behavior. By leveraging attention weights, we aggregate user and item embeddings separately for each behavior, computing preference scores that predict overall user preferences for items. Our evaluation of benchmark datasets demonstrates the superiority of Disen-CGCN over state-of-the-art models, showcasing an average performance improvement of 7.07% and 9.00% on respective datasets. These results highlight Disen-CGCN’s ability to effectively leverage multi-behavioral data, leading to more accurate recommendations.

关键词： Multi-Behavior Recommendation disentangled representation learning graph convolutional network multi-behavior recommendation multi-task learning

来源：评论

学校读者我要写书评

暂无评论

ViGT: Proposal-free Video Grounding with Learnable Token in Transformer

arXiv

引用

arXiv 2023年

作者： Li, Kun Guo, Dan Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei230601 China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

The video grounding (VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely Video Grounding Transformer (ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows. (1) The token is unrelated to the video or the query and avoids data bias toward the original video and query. (2) The token simultaneously performs global context aggregation from video and query features. First, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention (i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets: ANet Captions, TACoS and YouCookII. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT. Copyright © 2023, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Few-shot deep adversarial learning for video-based person re-identification

arXiv

引用

arXiv 2019年

作者： Wu, Lin Wang, Yang Yin, Hongzhi Wang, Meng Shao, Ling Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei230000 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230000 China University of Queensland St Lucia4072 Australia School of Computer Science and Information Engineering Hefei University of Technology Hefei230000 China Abu Dhabi United Arab Emirates

Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages. Existing methods rely on supervision signals to optimise a projected space under which the distances between inter/intra-videos are maximised/minimised. However, this demands exhaustively labelling people across camera views, rendering them unable to be scaled in large networked cameras. Also, it is noticed that learning effective video representations with view invariance is not explicitly addressed for which features exhibit different distributions otherwise. Thus, matching videos for person re-ID demands flexible models to capture the dynamics in time-series observations and learn view-invariant representations with access to limited labeled training samples. In this paper, we propose a novel few-shot deep learning approach to video-based person re-ID, to learn comparable representations that are discriminative and view-invariant. The proposed method is developed on the variational recurrent neural networks (VRNNs) and trained adversarially to produce latent variables with temporal dependencies that are highly discriminative yet view-invariant in matching persons. Through extensive experiments conducted on three benchmark datasets, we empirically show the capability of our method in creating view-invariant temporal features and state-of-the-art performance achieved by our method. Copyright © 2019, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised keyword Extraction Method Based on Chinese Patent Clustering

Unsupervised Keyword Extraction Method Based on Chinese Pate...

引用

IEEE International Conference on Big knowledge (ICBK)

作者： Yuxin Xie Xuegang Hu Yuhong Zhang Shi Li Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China Intelligent Connected Vehicle Research Institute (JAC Technical Center) Anhui Jianghuai Automobile Group Corp.Ltd Hefei China

Recently, patent data analysis has attracted a lot of attention, and patent keyword extraction is a hot problem. Most existing methods for patent keyword extraction are based on the frequency of words without semantic information. In this paper, we propose an Unsupervised keyword Extraction Method (UKEM) based on Chinese patent clustering. More specifically, we use a Skip-gram model to train word embeddings based on a Chinese patent corpus. Then each patent is represented as a vector called patent vector. These patent vectors are clustered to obtain several cluster centroids. Next, the distance between each word vector in patent abstract and cluster centroid is computed to indicate the semantic importance of this word. The experimental results on several Chinese patent datasets show that the performance of our proposed method is better than several competitive methods.

关键词： Patents Semantics data mining knowledge engineering Neural networks Big data Computer science

来源：评论

学校读者我要写书评

暂无评论

Towards efficient local causal structure learning

arXiv

引用

arXiv 2021年

作者： Yang, Shuai Wang, Hao Yu, Kui Cao, Fuyuan Wu, Xindong The School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China The School of Computer and Information Technology Shanxi University Taiyuan030006 China The Key Laboratory of Knowledge Engineering With Big Data Ministry of Education Hefei University of Technology Hefei230601 China Mininglamp Academy of Sciences Mininglamp Technology Beijing100102 China

Local causal structure learning aims to discover and distinguish direct causes (parents) and direct effects (children) of a variable of interest from data. While emerging successes have been made, existing methods need to search a large space to distinguish direct causes from direct effects of a target variable T. To tackle this issue, we propose a novel Efficient Local Causal Structure learning algorithm, named ELCS. Specifically, we first propose the concept of N-structures, then design an efficient Markov Blanket (MB) discovery subroutine to integrate MB learning with N-structures to learn the MB of T and simultaneously distinguish direct causes from direct effects of T. With the proposed MB subroutine, ELCS starts from the target variable, sequentially finds MBs of variables connected to the target variable and simultaneously constructs local causal structures over MBs until the direct causes and direct effects of the target variable have been distinguished. Using eight Bayesian networks the extensive experiments have validated that ELCS achieves better accuracy and efficiency than the state-of-the-art algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Automatically Labeling Aging Scenarios with a Machine Learning Approach 1

引用

24th International Conference on Human-Computer Interaction, HCII 2022

作者： An, Ning Xu, Yang Gao, Qinglin Zhu, Wenjie Wu, Aoran Chen, Honglin School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China National Smart Eldercare International S&T Cooperation Base Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Shanghai Tianyu Senior Living Service Co. Ltd. Shanghai China School of Basic Courses Bengbu Medical College Bengbu China Management and Business Department Skidmore College Saratoga SpringsNY United States Department of Social Sciences University of Eastern Finland Kuopio70150 Finland

ISBN: (数字)9783031179020

ISBN: (纸本)9783031179013

Older adults have diversified needs often associated with particular aging scenarios. People started to use aging scenarios to provide better Smart Eldercare services and develop innovative solutions. The problem is how to manage these scenarios effectively. To our best knowledge, this study is the first to develop a model to provide a structured framework of aging scenarios for research and teaching of eldercare services. Labeling aging scenarios can facilitate their collection, classification, and consolidation within this model. This study uses the automatic labeling approach to manage and utilize aging scenarios. Under each class, there are labels with different numbers and smaller granularity to reflect the requirements in each scenario case. Since a scenario case often involves more than one label, properly labeling it becomes a multi-label text classification problem. We extend the multi-label text classification model LSAN for labeling aging scenario cases. For evaluation purposes, we collected 938 scenario cases as the dataset. Experimental results show that our proposed method can achieve an average accuracy of 61.66%, better than other classical methods. © 2022, Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

arXiv

引用

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. 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

Towards Feature Distribution Alignment and Diversity Enhancement for data-Free Quantization

Towards Feature Distribution Alignment and Diversity Enhance...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yangcheng Gao Zhao Zhang Richang Hong Haijun Zhang Jicong Fan Shuicheng Yan School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Department of Computer Science Harbin Institute of Technology (Shenzhen) Xili University Town Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China National University of Singapore Singapore

To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous methods (such as quantization aware training and post training quantization) require original data for the fine-tuning or calibration of quantized model, which makes them inapplicable to the cases that original data are not accessed due to privacy or security. This gives birth to the data-free quantization method with synthetic data generation. While current data-free quantization methods still suffer from severe performance degradation when quantizing a model into lower bit, caused by the low inter-class separability of semantic features. To this end, we propose a new and effective data-free quantization method termed ClusterQ, which utilizes the feature distribution alignment for synthetic data generation. To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics to imitate the distribution of real data, so that the performance degradation is alleviated. Moreover, we incorporate the diversity enhancement to solve class-wise mode collapse. We also employ the exponential moving average to update the centroid of each cluster for further feature distribution improvement. Extensive experiments based on different deep models (e.g., ResNet-18 and MobileNet-V2) over the ImageNet dataset demonstrate that our proposed ClusterQ model obtains state-of-the-art performance.

关键词： Degradation Training Quantization (signal) Semantics Neural networks Memory management data models

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Approximations for Matrix-based Rényi's Entropy

arXiv

引用

arXiv 2021年

作者： Gong, Tieliang Dong, Yuxin Yu, Shujian Dong, Bo The School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an710049 China The Machine Learning Group UiT - The Arctic University of Norway Department of Computer Science Vrije University Amsterdam Amsterdam Netherlands

The recently developed matrix-based Rényi's αorder entropy enables measurement of information in data simply using the eigenspectrum of symmetric positive semi-definite (PSD) matrices in reproducing kernel Hilbert space, without estimation of the underlying data distribution. This intriguing property makes this new information measurement widely adopted in multiple statistical inference and learning tasks. However, the computation of such quantity involves the trace operator on a PSD matrix G to power α (i.e., tr(Gα)), with a normal complexity of nearly O(n3), which severely hampers its practical usage when the number of samples (i.e., n) is large. In this work, we present computationally efficient approximations to this new entropy functional that can reduce its complexity to even significantly less than O(n2). To this end, we leverage the recent progress on Randomized Numerical Linear Algebra, developing Taylor, Chebyshev and Lanczos approximations to tr(Gα) for arbitrary values of α by converting it into a matrix-vector multiplication problem. We also establish the connection between the matrix-based Rényi's entropy and PSD matrix approximation, which enables exploiting both clustering and block low-rank structure of G to further reduce the computational cost. We theoretically provide approximation accuracy guarantees and illustrate the properties for different approximations. Large-scale experimental evaluations on both synthetic and real-world data corroborate our theoretical findings, showing promising speedup with negligible loss in accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

DualConvNet: Enhancing CNN Inference Efficiency Through Compressed Convolutions and Reparameterization

DualConvNet: Enhancing CNN Inference Efficiency Through Comp...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Haipeng Du Muyan Jiao Jiageng Zhang Xin Lv Jie Zhang School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China School of Continuing Education Xi’an Jiaotong University Xi’an China Network Information Center Xi’an Jiaotong University Xi’an China School of Computer Science and Engineering Xi’an University of Technology Xi’an China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Convolutional Neural Networks (CNNs) have significantly advanced computer vision tasks, but their increasing complexity poses challenges for efficient inference, particularly on resource-constrained devices. We present DualConvNet, a novel CNN architecture that enhances inference efficiency through two key innovations: compressed convolutions and reparameterization. Compressed convolutions reduce computational complexity by selectively processing input channel subsets during both training and inference. For inference, we introduce a reparameterization technique that merges the multi-branch structure into a single, efficient operation, significantly improving speed. Experiments on CIFAR-10, CIFAR-100, and ImageNet-1k demonstrate DualConvNet’s effectiveness, consistently outperforming state-of-the-art models in both accuracy and inference speed. On the COCO dataset, DualConvNet shows competitive accuracy in object detection and instance segmentation tasks while substantially reducing GPU latency. Ablation studies validate the impact of our dual-strategy approach, revealing significant improvements in both accuracy and computational efficiency compared to alternative designs. These results demonstrate DualConvNet’s effectiveness in improving inference efficiency while maintaining high accuracy across various tasks and datasets, making it particularly suitable for real-time applications in resource-constrained scenarios.

关键词： Training Technological innovation Accuracy Image coding Computational modeling Computer architecture Transformers Computational efficiency Convolutional neural networks Computational complexity

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：