检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Kou, Zhiqiang Wang, Jing Jia, Yuheng Geng, Xin School of Computer Science and Engineering Southeast University Nanjing210096 China MOE Key Laboratory of Computer Network and Information Integration China

Label Distribution Learning (LDL) is a novel machine learning paradigm that assigns label distribution to each instance. Many LDL methods proposed to leverage label correlation in the learning process to solve the exponential-sized output space;among these, many exploited the low-rank structure of label distribution to capture label correlation. However, recent studies disclosed that label distribution matrices are typically full-rank, posing challenges to those works exploiting low-rank label correlation. Note that multi-label is generally low-rank;low-rank label correlation is widely adopted in multi-label learning (MLL) literature. Inspired by that, we introduce an auxiliary MLL process in LDL and capture low-rank label correlation on that MLL rather than LDL. In such a way, low-rank label correlation is appropriately exploited in our LDL methods. We conduct comprehensive experiments and demonstrate that our methods are superior to existing LDL methods. Besides, the ablation studies justify the advantages of exploiting low-rank label correlation in the auxiliary MLL. © 2023, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Heterogeneous Federated Learning with Multi-Level Prototypes

arXiv

引用

arXiv 2023年

作者： Guo, Shunxin Wang, Hongsong Geng, Xin MOE Key Laboratory of Computer Network and Information Integration China School of Computer Science and Engineering Southeast University Nanjing210096 China

Federated learning shows promise as a privacy-preserving collaborative learning technique. Existing heterogeneous federated learning mainly focuses on skewing the label distribution across clients. However, most approaches suffer from catastrophic forgetting and concept drift, mainly when the global distribution of all classes is extremely unbalanced and the data distribution of the client dynamically evolves over time. In this paper, we study the new task, i.e., Dynamic Heterogeneous Federated Learning (DHFL), which addresses the practical scenario where heterogeneous data distributions exist among different clients and dynamic tasks within the client. Accordingly, we propose a novel federated learning framework named Federated Multi-Level Prototypes (FedMLP) and design federated multi-level regularizations. To mitigate concept drift, we construct prototypes and semantic prototypes to provide fruitful generalization knowledge and ensure the continuity of prototype spaces. To maintain the model stability and consistency of convergence, three regularizations are introduced as training losses, i.e., prototype-based regularization, semantic prototype-based regularization, and federated inter-task regularization. Extensive experiments show that the proposed method achieves state-of-the-art performance in various settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Entity Disambiguation Based on UCL Knowledge Space

Entity Disambiguation Based on UCL Knowledge Space

引用

2021 IEEE International Conference on Artificial Intelligence and Industrial Design, AIID 2021

作者： Xinchen, Chang Peng, Yang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9780738110837

Named entity disambiguation is an important task in the process of knowledge space construction and improvement, which builds a bridge between entities in text and entities in knowledge space. However, the existing entity disambiguation methods mainly rely on the similar or related entities in the context. For the short text widely appeared in the practical application scenarios, the performance of the existing methods drops sharply. In this paper, we propose an entity disambiguation method based on Uniform Content Label knowledge space (UCLKS-ED). This method uses UCL knowledge space to provide additional knowledge information for the matching task of candidate entities and the source entity, and extends the representation of the source entity by conceptualizing. The experimental results on a large manually annotated short-text dataset and another standard dataset demonstrate that the proposed method achieves significant improvement over the state-of-the-art baselines. © 2021 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A Novel Classical-Quantum Transfer Learning Framework for Image Recognition

SSRN

引用

SSRN 2024年

作者： Ruan, Banyao Liu, Zhihao Li, Xi School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

With the advent of the era of Noisy Intermediate-Scale quantum (NISQ), quantum processors have demonstrated clear quantum supremacy, marking a new milestone in the development of quantum computing. At the same time, classical deep learning algorithms have been widely used in many fields such as image recognition and natural language processing. In this context, the Classical-Quantum transfer learning (CQ-TL) method, which combines the advantages of quantum computing and classical deep learning algorithms, emerged. In view of the problem of unclear quantum advantage in the existing CQ-TL framework, this paper proposes a novel CQ-TL framework based on amplitude encoding and effective learning algorithm is given. It not only has the flexibility of the existing framework, but also reduces the number of classical parameters, and can better demonstrate quantum advantages. Based on the CQ-TL framework, we designed and implemented two CQ-TL neural network models: named Transfer Learning Quantum Neural network (TLQNN) and Transfer Learning Quantum Convolutional Neural network (TLQCNN). TLQNN is structurally similar to a multi-layer feedforward neural network, and it achieves feature extraction through repeated quantum unit layers (ansatz). TLQCNN, on the other hand, employs quantum convolution and quantum pooling operations, which can effectively alleviate the effects of the barren plateau phenomenon, making it highly trainable and possessing great potential for practical applications. In cross-experiments with three benchmark datasets (MNIST, Fashion-MNIST and CIFAR10) and three source models (ResNet18, ResNet50 and DenseNet121), the two models have exceeded the benchmark classical classifier in many performance measures such as accuracy, convergence, stability and generalization capability. Our research shows that the proposed novel CQ-TL framework and its models have potential quantum advantages in the NISQ era, providing strong support for the practical application of qu

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Graph Clustering with Enhanced Delivery Operator

Attention-Based Graph Clustering with Enhanced Delivery Oper...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Xuanqi Liu Sen Xu Xiufang Xu Naixuan Guo Xuesheng Bian Chaofeng Chen Yancheng Institute of Technology (School of Information Engineering) Yancheng China Yancheng Institute of Technology (School of Information Engineering) Key Laboratory of Computer Network and Information Integration (Southeast University) Yancheng China

ISBN: (数字)9798331511074

ISBN: (纸本)9798331511081

Recently, graph clustering methods that integrate structured information into deep clustering have become one of the important research directions. However, current methods still lack an efficient and flexible fusion strategy when combining auto encoders and Graph Convolutional network (GCN) to learn feature representation. Accordingly, we propose a network named Structural Attention-based Graph Clustering network (SAGC). Firstly, we use the attention coefficient as weighted values to dynamically allocate the contribution of node attribute features and structural features. Secondly, an enhanced delivery operator is designed to efficiently convey the node features learned by the autoencoder. Lastly, a dual self-supervised mechanism is employed to unify the optimization of the two types of node features, thereby enhancing the stability of the model. Experiments on various types of datasets validate that our method outperforms state-of-the-art methods.

关键词： Graph convolutional networks Clustering methods Autoencoders Big Data Stability analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

KGRN: Knowledge Graph Relational Path network for Target Prediction of TCM Prescriptions 17th

KGRN: Knowledge Graph Relational Path Network for Target Pre...

引用

17th International Conference on Intelligent Computing, ICIC 2021

作者： Gong, Zhuo Zhang, Naixin He, Jieyue School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University Nanjing210018 China

ISBN: (纸本)9783030845315

Accurately predicting the effect targets of Traditional Chinese Medicine (TCM) prescriptions is essential for exploring the molecular mechanism and clarifying the mechanism of TCM. Although some scholars have used network pharmacology to study the target prediction of TCM prescriptions, all of them are for the analysis of a specific prescription-disease association, and the universal method for predicting effect targets of TCM prescriptions has not discovered yet. Therefore, this paper proposes a Knowledge Graph Relational Path network for Target Prediction of TCM Prescriptions (KGRN), which can integrate prescription’s molecular and target information through the Knowledge Graph (KG). At the same time, the semantic information and high-level structure of the knowledge graph are extracted through Knowledge Graph Embedding and Graph Neural networks, which can effectively capture the correlation between the prescriptions and the targets. Moreover, by emphasizing the KG relations when aggregating neighborhood information, the Relational Path network of the KGRN model has the ability to capture the relationship dependence in the KG path, which enhances the ability to predict the relationship between the prescriptions and the targets. The experiments under multiple configurations demonstrate that KGRN outperforms the related competitive benchmarks. © 2021, Springer Nature Switzerland AG.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Improved NL2SQL based on Multi-layer Expert network

arXiv

引用

arXiv 2023年

作者： Hao, Chenduo Zhang, Xu School of Computer Science and Engineering Southeast University China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

The Natural Language to SQL (NL2SQL) technique is used to convert natural language queries into executable SQL statements. Typically, slot-filling is employed as a classification method for multi-task cases to achieve this goal. However, slot-filling can result in inaccurate SQL statement generation due to negative migration issues arising from different classification tasks. To overcome this limitation, this study introduces a new approach called Multi-Layer Expert Generate SQL (MLEG-SQL), which utilizes a dedicated multi-task hierarchical network. The lower layer of the network extracts semantic features of natural language statements, while the upper layer builds a specialized expert system for handling specific classification tasks. This hierarchical approach mitigates performance degradation resulting from different task conflicts. The proposed method was evaluated on the WiKSQL dataset and was found to be effective in generating accurate SQL statements. © 2023, CC BY.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

Vision-language models are strong noisy label detectors 24

Vision-language models are strong noisy label detectors

引用

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

作者： Tong Wei Hao-Tian Li Chun-Shu Li Jiang-Xin Shi Yu-Feng Li Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China and National Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China and School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9798331314385

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DEFT, for adapting vision-language models. DEFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DEFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DEFT in both noisy label detection and image classification tasks. Our source code is available at https://***/HotanLee/DeFT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating Syntactic and Semantic Knowledge in AMR Parsing with Heterogeneous Graph Attention network

Integrating Syntactic and Semantic Knowledge in AMR Parsing ...

引用

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

作者： Yikemaiti Sataer Chuanqi Shi Miao Gao Yunlong Fan Bin Li Zhiqiang Gao School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Nanjing China

Abstract Meaning Representation (AMR) parsing is the task of translating a sentence to an AMR semantic graph which captures the basic meaning of the sentence, and is empowered by pre-trained Transformer models recently. These models encode the syntactic and semantic knowledge implicitly through self-supervised pre-trained tasks. We argue that encoding the syntactic and semantic knowledge explicitly is beneficial to AMR parsing and can improve data efficiency. Specifically, syntactic dependency and semantic role labeling (SRL) have similar sub-structures with AMR. In this work, we propose a novel linguistic knowledge-enhanced AMR parsing model, which augments the pre-trained Transformer with syntactic dependency and semantic role labeling structures of sentences. By applying a heterogeneous graph attention network, we can obtain syntactically and semantically augmented word representation, which can be integrated using an attentive integration layer and gating mechanism. Experimental results show that our model achieves state-of-the-art performance on different benchmarks, especially in out-of-domain and low-resource scenarios.

关键词： Knowledge engineering Semantics Syntactics Linguistics Benchmark testing Signal processing Transformers

来源：评论

学校读者我要写书评

暂无评论

BWG: An IOC Identification Method for Imbalanced Threat Intelligence Datasets

BWG: An IOC Identification Method for Imbalanced Threat Inte...

引用

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

作者： Juncheng Lu Yiyang Zhao Yan Wang Jiyuan Cui Sanfeng Zhang School of Cyber Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

APT attacks are becoming increasingly complex and stealthy. To effectively counter APT attacks, modelling threat intelligence data based on graphs, identifying Indicators of Compromise (IOC) nodes, and providing early warnings have become new research hotspots. However, the problem of node category imbalance in such graph datasets restricts the identification capabilities of these methods. Therefore, this paper proposes a supervised graph data augmentation method. In the training phase, graph disentangled representation learning is utilized to perform feature embedding for minority class nodes, effectively alleviating the sparsity problem faced by traditional methods and effectively integrating neighbourhood information of minority class nodes at a higher semantic level. Additionally, two loss functions designed based on link prediction and prototype constraints enhance node type consistency and semantic consistency, respectively. Experimental results on the APT and PDNS datasets demonstrate that the proposed method outperforms other baseline models in identification performance; even in highly imbalanced scenarios, it surpasses the second-best model.

关键词： Training Data privacy Computational modeling Semantics Disentangled representation learning Prototypes Data augmentation Data models Security

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：