检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Pu, Yuanhao Chen, Xiaolong Huang, Xu Chen, Jin Lian, Defu Chen, Enhong School of Artificial Intelligence and Data Science University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China School of Business and Management Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Cognitive Intelligence China

The weighted squared loss is a common component in several Collaborative Filtering (CF) algorithms for item recommendation, including the representative implicit Alternating Least Squares (iALS). Despite its widespread use, this loss function lacks a clear connection to ranking objectives such as Discounted Cumulative Gain (DCG), posing a fundamental challenge in explaining the exceptional ranking performance observed in these algorithms. In this work, we make a breakthrough by establishing a connection between squared loss and ranking metrics through a Taylor expansion of the DCG-consistent surrogate loss-softmax loss. We also discover a new surrogate squared loss function, namely Ranking-Generalizable Squared (RG2) loss, and conduct thorough theoretical analyses on the DCG-consistency of the proposed loss function. Later, we present an example of utilizing the RG2 loss with Matrix Factorization (MF), coupled with a generalization upper bound and an ALS optimization algorithm that leverages closed-form solutions over all items. Experimental results over three public datasets demonstrate the effectiveness of the RG2 loss, exhibiting ranking performance on par with, or even surpassing, the softmax loss while achieving faster convergence. Copyright 2024 by the author(s)

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Modality Fused Class-Proxy with Knowledge Distillation for Zero-Shot Sketch-based Image Retrieval

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 6158-6169页

作者： Li, Chang-Xing Zhang, Donglin Hu, Zhikai Wu, Xiao-Jun Jiangnan University School of Artificial Intelligence and Computer Science Wuxi China Hong Kong Baptist University Department of Computer Science SAR Hong Kong Hong Kong

In recent years, zero-shot sketch-based image retrieval (ZS-SBIR) task has attracted considerable attention. Although some ZS-SBIR approaches have been proposed, it remains challenging to handle the inherent linkages between the sketch and image domains. Moreover, how to transfer semantic knowledge from seen categories to unseen categories is still an open problem, significantly affecting retrieval performance. In this article, we propose a novel approach Modality Fused Class-Proxy with Knowledge Distillation, named MFCPKD, which develops two novel schemes to remedy the above issues. Specifically, MFCPKD leverages a Modality Fusion Model to learn modality-fused feature embeddings and class proxies. The knowledge distillation is employed for student to learn the feature from seen categories and infer the unknown category through class proxies. Furthermore, three losses constrain the student network to narrow the modality gap between sketch and image domains. Finally, we conduct extensive experiments on three benchmark datasets (Sketchy Ext, TU-Berlin Ext, and QuickDraw Ext) and demonstrate that our MFCPKD method can achieve excellent performance compared to some existing methods in ZS-SBIR scenarios. The code for our project is available at https://***/li1changxing/MFCPKD. © 1991-2012 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Feature Selection With Multi-Scale Fuzzy Information Fusion: From Both Global and Local Perspectives

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1825-1839页

作者： Zhou, Nan Liao, Shujiao Chen, Hongmei Ding, Weiping Lu, Yaqian Minnan Normal University School of Mathematics and Statistics Fujian Key Laboratory of Granular Computing and Applications Zhangzhou363000 China Southwest Jiaotong University School of Computing and Artificial Intelligence National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multi-scale data have received widespread attention due to its rich knowledge representation. However, current research on multi-scale data primarily focuses on supervised learning environments, while semi-supervised feature selection for multi-scale data with limited labels remains inadequately explored. Meanwhile, existing studies on multi-scale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multi-scale fuzzy information fusion mechanism, this article proposes two new semi-supervised feature selection approaches for multi-scale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multi-scale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semi-supervised feature selection algorithms are developed based on global and local multi-scale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multi-scale data with limited labels and exhibit superior classification performance, computational efficiency and robustness. © 1993-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

YOLO-CSPOKM: Efficient Small Object Detector via CSP Omni-Kernel Model 24

YOLO-CSPOKM: Efficient Small Object Detector via CSP Omni-Ke...

引用

4th Asia-Pacific artificial intelligence and Big data Forum, AIBDF 2024

作者： Wei, Wu The School of Computer Science and Artificial Intelligence Wuhan University of Technology Hubei Wuhan China

ISBN: (纸本)9798400710865

In the field of real-time object detection, the YOLO series has become a mainstream approach due to its exceptional performance. However, its performance on small object detection still has room for improvement. Small objects often struggle with limited feature representation in the P3, P4, and P5 detection layers. Traditional methods to address this issue typically add a P2 detection layer to enhance small object detection capabilities, but this often leads to a significant increase in computation and extended post-processing time. Therefore, developing an efficient and effective feature pyramid tailored for small objects has become an urgent problem to solve. This paper proposes a network specifically optimized for small object detection-YOLO-CSPOKM, which significantly enhances the performance of small object detection while also improving the detection of general objects. Based on the original PAFPN structure, we designed a Small Object Enhance Pyramid: the P2 feature layer is processed using SPD-Conv to extract features rich in small object information and then fused with the P3 layer. Subsequently, the CSP (Cross Stage Partial) strategy is employed to split input features along the channel dimension. One portion of the features is passed through the Omni-Kernel module to effectively capture multi-scale features ranging from global to local levels, while the other portion is concatenated with the Omni-Kernel output via skip connections. Furthermore, the P3, P4, and P5 features are passed through the SSFF module, and their output is added to the results from the CSPOKM module. Finally, the combined features are sent to the detection head, achieving a comprehensive enhancement in small object detection. Experiments on the MS COCO dataset demonstrate that compared to the baseline YOLOv8n model, YOLO-CSPOKM improves mAP@0.5:0.95 to 39.2%, a 2.8% increase, while maintaining a compact model size. When extended to the YOLOv8s model, the enhanced version achieves an mA

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Denoising Graph Inference Network for Document-Level Relation Extraction

引用

Big data Mining and Analytics 2023年第2期6卷 248-262页

作者： Hailin Wang Ke Qin Guiduo Duan Guangchun Luo School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Computing and Artificial Intelligence Southwestern University of Finance and EconomicsChengdu 611130China

Relation Extraction(RE)is to obtain a predefined relation type of two entities mentioned in a piece of text,e.g.,a sentence-level or a document-level *** existing studies suffer from the noise in the text,and necessary pruning is of great *** conventional sentence-level RE task addresses this issue by a denoising method using the shortest dependency path to build a long-range semantic dependency between entity ***,this kind of denoising method is scarce in document-level *** this work,we explicitly model a denoised document-level graph based on linguistic knowledge to capture various long-range semantic dependencies among *** first formalize a Syntactic Dependency Tree forest(SDT-forest)by introducing the syntax and discourse dependency ***,the Steiner tree algorithm extracts a mention-level denoised graph,Steiner Graph(SG),removing linguistically irrelevant words from the *** then devise a slide residual attention to highlight word-level evidence on text and ***,the classification is established on the SG to infer the relations of entity *** conduct extensive experiments on three public *** results evidence that our method is beneficial to establish long-range semantic dependency and can improve the classification performance with longer texts.

关键词： Relation Eextraction(RE) document-level denoising linguistic knowledge attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Federated Learning on Heterogeneous Opportunistic Networks 5

Federated Learning on Heterogeneous Opportunistic Networks

引用

5th International Seminar on artificial intelligence, Networking and Information technology, AINIT 2024

作者： Deng, Yuchen Yan, Xin School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798350385557

Opportunistic learning plays a crucial role in heterogeneous opportunity networks. Federated learning enables nodes to learn new knowledge from models of other nodes, facilitating opportunistic learning in heterogeneous opportunity networks. However, applying federated learning to heterogeneous opportunity networks faces challenges such as slow convergence rates in large-scale networks, lack of training efficiency, node heterogeneity, and data heterogeneity. In this paper, we propose a distributed opportunistic federated learning model designed for large-scale networks, providing a multi-node grouping protocol. We present the convergence proof of the opportunistic federated learning algorithm. Additionally, we optimize the transfer matrix of opportunistic federated learning for addressing data heterogeneity and network heterogeneity shifts. © 2024 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

New Energy Power data Prediction Research based on Cross Validation Method 5

New Energy Power Data Prediction Research based on Cross Val...

引用

5th International Conference on Advances in Electrical Engineering and computer Applications, AEECA 2024

作者： Sun, Lijuan Li, Lan Zhang, Xujuan Lanzhou Institute of Technology School of Computer Science & Artificial Intelligence Lanzhou China

ISBN: (纸本)9798350355253

In order to improve the prediction accuracy of photovoltaic power generation and reduce the impact of grid-connected operation of photovoltaic power station on the security, stability and economic operation of power system, a power prediction method combining data mining and machine learning algorithm was proposed. The statistical analysis technology in data mining is used to describe the real historical data of the output of a distributed photovoltaic power plant. Combined with correlation analysis, the main parameters affecting the generation power prediction are found. Three power prediction models are designed based on machine learning, including linear regression, gradient boosting tree and random forest. The experimental results show that the gradient boosting tree regression prediction model has the smallest prediction error and the highest generalization ability when the full sample data set is used as the training set to train the model. This method improves the prediction accuracy of photovoltaic power generation, and plays an important role in the optimal operation of photovoltaic power station, the scheduling of photovoltaic power system and the security and stability of power grid. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

TCRNet: An Efficient Vehicle Re-Identification Network Using TinyCLIP-Assisted Feature Representation 24

TCRNet: An Efficient Vehicle Re-Identification Network Using...

引用

4th Asia-Pacific artificial intelligence and Big data Forum, AIBDF 2024

作者： Fu, Zihao School of Computer Science and Artificial Intelligence Wuhan University of Technology Hubei Wuhan China

ISBN: (纸本)9798400710865

Vehicle re-identification (ReID) is an important component of intelligent transportation systems, yet existing methods often struggle with challenges such as inter-class similarity, viewpoint variations, and environmental noise. While CLIP-based approaches have shown promise in bridging visual and semantic domains, they often rely heavily on the pre-trained CLIP model, limiting flexibility and integration with standard baselines. To address this, we propose TCRNet, an efficient vehicle ReID network that integrates semantic features from TinyCLIP into the visual features extracted by a baseline ResNet50-IBN model. By fusing TinyCLIP-assisted semantic features with visual representations in an end-to-end training pipeline, TCRNet demonstrates strong capability in robust and discriminative feature learning. Extensive ablation experiments on the VeRi-776 dataset validate the discriminative ability of the proposed model, achieving 89.7% mAP and 97.5% Rank-1. © 2024 Copyright held by the owner/author(s).

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

VaLW: Multi-centric motion forecasting with variable length window 4

VaLW: Multi-centric motion forecasting with variable length ...

引用

4th International Conference on Internet of Things and Smart City, IoTSC 2024

作者： Qin, Heng School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9781510681767

Trajectory prediction plays a crucial role in achieving autonomous driving, as it significantly reduces driving risks by predicting the movement trajectory of other vehicles. The key challenge lies in effectively encoding scene information and generating accurate multimodal results for each agent. To address this challenge, we propose a graph neural network framework that enables multi-centric modeling of relationships between heterogeneous inputs. This framework establishes various spatiotemporal adjacency relationships among scene nodes, leveraging graph attention mechanisms to allow each scene node to learn neighborhood features effectively and generate scene context enriched with valuable information. To tackle the problem of declining prediction accuracy as the prediction time increases, we propose a variable length window structure. The structure consists of a long window prediction module for multi-agent multimodal prediction, followed by a short window optimization module for refining the predictions. By utilizing this structure, we successfully strike a balance between model size and prediction accuracy. To validate our proposed model, we conducted experiments on the Argverse 1 motion forecasting dataset, and the results showcased excellent predictive performance. © 2024 SPIE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Fractal autoencoder with redundancy regularization for unsupervised feature selection

引用

science China(Information sciences) 2025年第2期68卷 89-102页

作者： Meiting SUN Fangyu LI Honggui HAN School of Information Science and Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education Beijing Institute of Artificial Intelligence

Feature selection is a crucial step in data preprocessing because feature selection reduces the dimensionality of data by eliminating irrelevant and redundant features. Since manual labeling is expensive, unsupervised feature selection has received increasing attention in recent years. However, existing unsupervised feature selection methods tend to prioritize selecting highly correlated features over exploring feature diversity. Thus, a regularized fractal autoencoder(RFAE) method is proposed to select informative features in an unsupervised way. Specifically, the fractal autoencoder network extends autoencoders to construct a correspondence neural network and a selection neural network. The correspondence neural network exploits interfeature correlations and the selection neural network selects the informative features. A redundancy regularization strategy consists of a redundancy elimination regularization term based on the dependency between features and a sparse regularization term based on the group lasso. The redundancy regularization strategy eliminates feature subset redundancy and enhances network generalization ability. Extensive experimental results on six publicly available datasets show that the proposed RFAE outperforms the compared methods regarding clustering accuracy and classification accuracy. Moreover, the proposed RFAE achieves acceptable computation efficiency.

关键词： unsupervised feature selection fractal autoencoder correspondence neural network selection neural network redundancy regularization strategy

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：