检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cai, Tingyi Jiang, Yunliang Li, Ming Huang, Changqin Wang, Yi Huang, Qionghao School of Computer Science and Technology Zhejiang Normal University China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Information Engineering Huzhou University China Zhejiang Institute of Optoelectronics China

ISBN: (纸本)157735897X

The out-of-distribution (OOD) detection on graph-structured data is crucial for deploying graph neural networks securely in open-world scenarios. However, existing methods have overlooked the prevalent scenario of multi-label classification in real-world applications. In this work, we investigate the unexplored issue of OOD detection within multi-label node classification tasks. We propose ML-GOOD, a simple yet sufficient approach that utilizes an energy function to gauge the OOD score for each label. We further develop a strategy for amalgamating multiple label energies, allowing for the comprehensive utilization of label information to tackle the primary challenges encountered in multi-label scenarios. Extensive experimentation conducted on seven diverse sets of real-world multi-label graph datasets, encompassing cross-domain scenarios. The results show that the AUROC of ML-GOOD is improved by 5.26% in intra-domain and 6.54% in cross-domain compared to the previous methods. These empirical validations not only affirm the robustness of our methodology but also illuminate new avenues for further exploration within this burgeoning field of research. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

: heterogeneous hypergraph attention network with counterfactual learning for multimodal sentiment analysis

引用

Complex & Intelligent Systems 2025年第4期11卷 1-16页

作者： Huang, Changqin Lin, Zhenheng Huang, Qionghao Huang, Xiaodi Jiang, Fan Chen, Jili Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua China School of Education Zhejiang Normal University Jinhua China School of Computer Science and Technology Zhejiang Normal University Jinhua China School of Computing Mathematics and Engineering Charles Sturt University Albury Australia

Multimodal sentiment analysis (MSA) has garnered significant attention for its immense potential in human-computer interaction. While cross-modality attention mechanisms are widely used in MSA to capture inter-modality interactions, existing methods are limited to pairwise interactions between two modalities. Additionally, these methods can not utilize the causal relationship to guide attention learning, making them susceptible to bias information. To address these limitations, we introduce a novel method called Heterogeneous Hypergraph Attention Network with Counterfactual Learning $$(\text {H}^2\text {CAN}).$$ The method constructs a heterogeneous hypergraph based on sentiment expression characteristics and employs Heterogeneous Hypergraph Attention Networks (HHGAT) to capture interactions beyond pairwise constraints. Furthermore, it mitigates the effects of bias through a Counterfactual Intervention Task (CIT). Our model comprises two main branches: hypergraph fusion and counterfactual fusion. The former uses HHGAT to capture inter-modality interactions, while the latter constructs a counterfactual world using Gaussian distribution and additional weighting for the biased modality. The CIT leverages causal inference to maximize the prediction discrepancy between the two branches, guiding attention learning in the hypergraph fusion branch. We utilize unimodal labels to help the model adaptively identify the biased modality, thereby enhancing the handling of bias information. Experiments on three mainstream datasets demonstrate that $$\text {H}^2\text {CAN}$$ sets a new benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Long-range Brain Graph Transformer

arXiv

引用

arXiv 2025年

作者： Yu, Shuo Jin, Shan Li, Ming Sarwar, Tabinda Xia, Feng School of Computer Science and Technology Dalian University of Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China School of Software Dalian University of Technology China Zhejiang Institute of Optoelectronics China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Computing Technologies RMIT University Australia

Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the short-range dependencies within brain networks while neglecting the long-range dependencies, limiting an integrated understanding of brain-wide communication. To address this limitation, we propose Adaptive Long-range aware TransformER (ALTER), a brain graph transformer to capture long-range dependencies between brain ROIs utilizing biased random walk. Specifically, we present a novel long-range aware strategy to explicitly capture long-range dependencies between brain ROIs. By guiding the walker towards the next hop with higher correlation value, our strategy simulates the real-world brain-wide communication. Furthermore, by employing the transformer framework, ALERT adaptively integrates both short- and long-range dependencies between brain ROIs, enabling an integrated understanding of multilevel communication across the entire brain. Extensive experiments on ABIDE and ADNI datasets demonstrate that ALTER consistently outperforms generalized state-of-the-art graph learning methods (including SAN, Graphormer, GraphTrans, and LRGNN) and other graph learning based brain network analysis methods (including FBNETGEN, BrainNetGNN, BrainGNN, and BrainNETTF) in neurological disease diagnosis. Cases of long-range dependencies are also presented to further illustrate the effectiveness of ALTER. The implementation is available at https://***/yushuowiki/ALTER. Copyright © 2025, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach with Fusion Edge Prediction Strategy for Table Structure Recognition

A Novel Approach with Fusion Edge Prediction Strategy for Ta...

引用

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

作者： Yingli Liu Guangtao Zhang Tao Shen Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China

Table, as an information carrier with high information density and direct display form, are widely used in scientific literature and social production documents. Accurately identifying tables from various documents will significantly promote the intelligent application of documents. The table’s structural information is crucial for comprehending how the text content in the table relates to one another, but teaching a computer to fully understand a table’s structure is still a very difficult undertaking. In this research work, we provided a unique edge-based method to recognize table structures. Specifically, we define the inter-cell relationships as an edge prediction problem and leverage graph convolutional networks to learn representations of the cells. These learned representations are then utilized to directly predict the connections between the cells. The experimental results conducted on three publicly available datasets for table structure recognition provide compelling evidence supporting the feasibility and usefulness of our presented methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross Modal Training for ASR Error Correction with Contrastive Learning

Cross Modal Training for ASR Error Correction with Contrasti...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jin Jiang Xiaojun Wan Wei Peng Rongjun Li Jingyuan Yang Yanquan Zhou Beijing University of Posts and Telecommunications Wangxuan Institute of Computer Technology Peking University The MOE Key Laboratory of Computational Linguistics Peking University Artificial Intelligence Application Research Center Huawei Technologies

ASR Error Correction (AEC) aims to post-process the output of ASR systems and further reduce the word error rate. In this paper, we propose a cross-modal training framework with contrastive learning on the AEC task. This framework enables a shared encoder-decoder model to learn text, pinyin (phoneme 1 ) and audio information simultaneously, which is trained by three subtasks: text correction, pinyin to text and ASR. On this basis, we introduce contrastive learning loss to shrink the distance between the three modalities and construct a unified representation. Experiments 2 on four AEC datasets show that our method effectively corrects a large number of ASR errors to state-of-the-art levels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Independent Pitch Controller based on Fuzzy Adaptive Tuning PI for Load Mitigation of Large Land Wind Turbine 2

Independent Pitch Controller based on Fuzzy Adaptive Tuning ...

引用

2023 2nd International Conference on Energy Internet and Power Systems, ICEIPS 2023

作者： Li, Shengshan Du, Ming Li, Yanggui He, Jun Ma, Fuliang Chen, Qingyun Department of Computer Science Qinghai University Qinghai Xining China Geospatial and Natural Resources Big Data Center Qinghai Xining China Key Laboratory of Geospatial Information Technology and Application Qinghai Xining China College of Chemical Engineering Qinghai University Qinghai Xining China Qinghai Telecom Qinghai Xining China

With the development of wind power generation units towards the mega-scale, the blade root and tower have large load and vibration problems during the operation of wind turbines. In order to extend the operational life of wind turbines, a PI independent pitch control (IPC) strategy with fuzzy adaptive tuning (FAT) is introduced based on the existing wind turbine model and control strategy to achieve optimal control of wind turbine loads. Simulations are carried out by the FAST software of the US Renewable Energy laboratory to compare the independent pitch and the cooperative pitch. The results show that IPC reduces the load on the blade roots and improves the quality of the electrical energy. © 2023 Published under licence by IOP Publishing Ltd.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Assisted Enhance Vertical Field Confinement of Spot Size Converter

Deep Learning Assisted Enhance Vertical Field Confinement of...

引用

Cross Strait Quad-Regional Radio Science and Wireless technology Conference (CSRWTC)

作者： Qinghao Tan Jiandao Huang Zan Hui Chen School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guilin China

We propose a spot size converter using pixelated nano-dots waveguide, to enhance the vertical field confinement. Theoretical analysis shows a converter efficiency of -2.1 dB for the TE mode at $\lambda_{0}=1.55$ ...

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Signal Perception Network for Textile Composition Identification 48

A Multi-Signal Perception Network for Textile Composition Id...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Peng, Bo He, Liren Wu, Dong Chi, Mingmin Chen, Jintao Shanghai Key Laboratory of Data Science Fudan University School of Computer Science Shanghai China Zhongshan PoolNet Technology Co. Ltd Zhongshan Fudan Joint Innovation Center Zhongshan China Shanghai Fabric Eyes Artificial Intelligence Technology Co. Ltd Shanghai China Zhengzhou Zhongke Institute of Integrated Circuit and System Application China

ISBN: (纸本)9781728163277

Textile composition identification (TCI) is an essential basic link in the textile industry. Methods based on computer vision or near-infrared (NIR) signal processing have shown potential for the nondestructive TCI task. However, these methods ignore that the integration of NIR signals and visual information may help the model learn a better representation through information complementarity. This paper propose a Multi-Signal Perception Network (MSPNet) for nondestructive textile composition identification, allowing the model to benefit from the advantages of multimodal data. Firstly, a two-way feature extraction network is used to obtain multi-modal features. After that, we propose a multimodal signal fusion module to control the aggregation granularity among multimodal data. Specifically, the target areas of the image are perceived by a target area perception module (TAP). Then a bi-gated aggregation (Bi-GFA) is designed to capture consistent semantic information from signal to image and image to signal. The quantitative and qualitative results of the proposed MSPNet are significantly improved compared to both single and multimodal approaches. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Lightweight Transformer Network and Self-supervised Task for Kinship Verification 8

Lightweight Transformer Network and Self-supervised Task for...

引用

8th IEEE International Conference on computer and Communications, ICCC 2022

作者： Zhu, Xiaoke Li, Yunwei Li, Danyang Dong, Lingyun Chen, Xiaopan School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University China

ISBN: (纸本)9781665450515

Kinship verification is one of the interesting and critical problems in computer vision research, with significant progress in the past decades. Meanwhile, Vision Transformer (VIT) has recently achieved impressive success in many domains, including object detection, image recognition, and semantic segmentation, among others. Most of the previous work on kinship verification are based on convolutional or recurrent neural networks. Compared with the local processing of images like convolutions, transformers can effectively understand and process images globally. However, due to overuse, there are many Transformer layers of fully connected layers, and VIT speed is still an issue. Therefore, in this paper, inspired by the recent success of Transformer models in vision tasks, we propose a Transformer-based kinship verification for training and optimizing kinship verification models. We first train the basic vision transformer (VIT-B) with 12 transformer layers, then we reduce the transformer layers to 6 layers, namely VIT-S (Small Vit) and 4 layers, namely VIT-T (Tiny Vit), to make a tradeoff between optimization accuracy and efficiency. As the first attempt to apply Transformer to the kinship verification task, it provides a feasible strategy for kinship research topics and verifies the effectiveness of the method in terms of the accuracy of the experimental results. © 2022 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Long-range brain graph transformer 24

Long-range brain graph transformer

引用

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

作者： Shuo Yu Shan Jin Ming Li Tabinda Sarwar Feng Xia School of Computer Science and Technology Dalian University of Technology China and Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology) Ministry of Education China School of Software Dalian University of Technology China Zhejiang Institute of Optoelectronics China and Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Computing Technologies RMIT University Australia

ISBN: (纸本)9798331314385

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：