检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Kang, Yanqin Liu, Jin Wu, Fan Wang, Kun Qiang, Jun Hu, Dianlin Zhang, Yikun College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

Purpose: Many deep learning-based methods have been applied in sparse view computed tomography (CT) imaging. However, most methods are built intuitively using state-of-the-art black-box convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields, neglecting nonlocal self-similarity prior information. How to obtain diagnostically useful images from sparsely sampled projections is a challenging, ill-posed ***: To address this issue, we propose a novel interpretable model based on a convolutional dictionary learning network and nonlocal group sparse prior, called DCDL-GS, for sparse view CT image reconstruction. We apply a statistical iterative reconstruction algorithm for a fixed number of iterations with a neural network to improve the image reconstruction quality. Inspired by a group sparsity prior, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Additionally, filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight convolutional dictionary learning network are integrated into our DCDL-GS model, improving model ***: The visual results based on the LDCT-P and UIH datasets show the efficiency of our proposed DCDL-GS model in edge preservation and feature recovery. The quantitative results show improvement over state-of-the-art methods, with improvements of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) based on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse ***: We developed a unified optimized mathematical model incorporating projection data and image prior knowled

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models

arXiv

引用

arXiv 2025年

作者： Zhang, Yanyue He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute

Personalized opinion summarization is crucial as it considers individual user interests while generating product summaries. Recent studies show that although large language models demonstrate powerful text summarization and evaluation capabilities without the need for training data, they face difficulties in personalized tasks involving long texts. To address this, Rehearsal, a personalized opinion summarization framework via LLMs-based role-playing is proposed. Having the model act as the user, the model can better understand the user’s personalized needs. Additionally, a role-playing supervisor and practice process are introduced to improve the role-playing ability of the LLMs, leading to a better expression of user needs. Furthermore, through suggestions from virtual users, the summary generation is intervened, ensuring that the generated summary includes information of interest to the user, thus achieving personalized summary generation. Experiment results demonstrate that our method can effectively improve the level of personalization in large model-generated summaries. Copyright © 2025, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

arXiv

引用

arXiv 2024年

作者： Zhou, Zi-Hao Fang, Siyuan Zhou, Zi-Jing Wei, Tong Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Parsing 29

DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Pa...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Li, Bin Gao, Miao Fan, Yunlong Sataer, Yikemaiti Gao, Zhiqiang Gui, Yaocheng School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education Nanjing210096 China School and Institute of Modern Posts Nanjing University of Posts and Telecommunications Nanjing210003 China

A recent success in semantic dependency parsing shows that graph neural networks can make significant accuracy improvements, owing to its powerful ability in learning expressive graph representations. However, this work learns graph representations based on a static graph constructed by an existing parser, suffering from two drawbacks: (1) the static graph might be error-prone (e.g., noisy or incomplete), and (2) graph construction stage and graph representation learning stage are disjoint, the errors introduced in the graph construction stage cannot be corrected and might be accumulated to later stages. To address these two drawbacks, we propose a dynamic graph learning framework and apply it to semantic dependency parsing, for jointly learning graph structure and graph representations. Experimental results show that our parser outperforms the previous parsers on the SemEval-2015 Task 18 dataset in three languages (English, Chinese, and Czech). © 2022 Proceedings - International Conference on Computational Linguistics, COLING. 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

Exploiting Conjugate Label information for Multi-Instance Partial-Label Learning

arXiv

引用

arXiv 2024年

作者： Tang, Wei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Lab. of Computer Network and Information Integration Southeast University MoE China School of Information and Physical Sciences The University of Newcastle NSW2308 Australia

Multi-instance partial-label learning (MIPL) addresses scenarios where each training sample is represented as a multi-instance bag associated with a candidate label set containing one true label and several false positives. Existing MIPL algorithms have primarily focused on mapping multi-instance bags to candidate label sets for disambiguation, disregarding the intrinsic properties of the label space and the supervised information provided by non-candidate label sets. In this paper, we propose an algorithm named ELIMIPL, i.e., Exploiting conjugate Label information for Multi-Instance Partial-Label learning, which exploits the conjugate label information to improve the disambiguation performance. To achieve this, we extract the label information embedded in both candidate and non-candidate label sets, incorporating the intrinsic properties of the label space. Experimental results obtained from benchmark and real-world datasets demonstrate the superiority of the proposed ELIMIPL over existing MIPL algorithms and other well-established partial-label learning algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

arXiv

引用

arXiv 2023年

作者： Ye, Bo Gan, Kai Wei, Tong Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing211189 China Key Lab. of Computer Network and Information Integration Southeast University MoE China

In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial learning gap between seen and novel categories, as the model learns the former faster due to accurate supervisory information. Moreover, capturing the semantics of unlabeled novel category samples is also challenging due to the missing label information. To address the above issues, we introduce 1) the adaptive synchronizing marginal loss which imposes class-specific negative margins to alleviate the model bias towards seen classes, and 2) the pseudo-label contrastive clustering which exploits pseudo-labels predicted by the model to group unlabeled data from the same category together in the output space. Extensive experiments on benchmark datasets demonstrate that previous approaches may significantly hinder novel class learning, whereas our method strikingly balances the learning pace between seen and novel classes, achieving a remarkable 3% average accuracy increase on the ImageNet dataset. Importantly, we find that fine-tuning the self-supervised pre-trained model significantly boosts the performance, which is overlooked in prior literature. Our code is available at https://***/yebo0216best/LPS-main. 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

Towards Few-Shot Learning in the Open World: A Review and Beyond

arXiv

引用

arXiv 2024年

作者： Xue, Hui An, Yuexuan Qin, Yongchun Li, Wenqian Wu, Yixin Che, Yongjuan Fang, Pengfei Zhang, Min-Ling The School of Computer Science and Engineering Southeast University Nanjing210096 China The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing211189 China The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

Human intelligence is characterized by our ability to absorb and apply knowledge from the world around us, especially in rapidly acquiring new concepts from minimal examples, underpinned by prior knowledge. Few-shot learning (FSL) aims to mimic this capacity by enabling significant generalizations and transferability. However, traditional FSL frameworks often rely on assumptions of clean, complete, and static data, conditions that are seldom met in real-world environments. Such assumptions falter in the inherently uncertain, incomplete, and dynamic contexts of the open world. This paper presents a comprehensive review of recent advancements designed to adapt FSL for use in open-world settings. We categorize existing methods into three distinct types of open-world few-shot learning: those involving varying instances, varying classes, and varying distributions. Each category is discussed in terms of its specific challenges and methods, as well as its strengths and weaknesses. We standardize experimental settings and metric benchmarks across scenarios, and provide a comparative analysis of the performance of various methods. In conclusion, we outline potential future research directions for this evolving field. It is our hope that this review will catalyze further development of effective solutions to these complex challenges, thereby advancing the field of artificial intelligence. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Topgformer: Topological-Based Graph Transformer for Mapping Brain Structural Connectivity to Functional Connectivity

Topgformer: Topological-Based Graph Transformer for Mapping ...

引用

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

作者： Dalu Guo Ke Zhang Jiaxing Li Youyong Kong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

Exploring the mapping between structural connectivity (SC) and functional connectivity (FC) is of essential importance to understanding the working mechanism of the human brain. Traditional methods are difficult to represent the complex relationship of high-order interaction between SC and FC. Recent learning-based methods can not well capture the important long-range interactions and edge information of brain connectivity. To address the issue, we propose a novel Topological-based Graph Transformer (TopGFormer) to generate functional connectivity from the structure connectivity with sufficient consideration of topological properties of brain connectivity. We propose a Topological Multi-Head Attention block that simultaneously uses centrality encoding and adjacency matrix to capture node and edge importance respectively. The centrality encoding reflects the importance of brain regions while the adjacency matrix captures the linking relationship of different regions. Experiments on HCP resting and emotion task datasets demonstrate the performance of the proposed method.

关键词： Learning systems Brain Correlation Signal processing Transformers Encoding Acoustics

来源：评论

学校读者我要写书评

暂无评论

Topology Uncertainty Modeling For Imbalanced Node Classification on Graphs

Topology Uncertainty Modeling For Imbalanced Node Classifica...

引用

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

作者： Jiayi Gao Jiaxing Li Ke Zhang Youyong Kong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Ministry of Education Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

Most existing graph neural networks work under a class-balanced assumption, while ignoring class-imbalanced scenarios that widely exist in real-world graphs. Although there are many methods in other fields that can alleviate this issue, they do not consider the special topology of the non-Euclidean graph. Hence, we propose Graph Topology Uncertainty (GraphTU), a novel probabilistic class-imbalanced solution specifically for graphs. Firstly, an invisible "uncertain gap" between under-represented minorities in training set and authentic minorities in unseen set is modeled by estimating statistical variances in topology. We extend the training distribution for minorities by sampling in this gap through a non-parametric way. Moreover, a gradient-guided mask is introduced to prevent biased statistics. Extensive experiments demonstrate the superior performance of GraphTU.

关键词： Training Uncertainty network topology Signal processing Probabilistic logic Graph neural networks Acoustics

来源：评论

学校读者我要写书评

暂无评论

Gradient sparsification for efficient wireless federated learning with differential privacy

引用

Science China(information Sciences) 2024年第4期67卷 272-288页

作者： Kang WEI Jun LI Chuan MA Ming DING Feng SHU Haitao ZHAO Wen CHEN Hongbo ZHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education Data61 Commonwealth Scientific and Industrial Research Organisation School of Information and Communication Engineering Hainan University School of Communications and Information Engineering Nanjing University of Posts and Telecommunications School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University

Federated learning(FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy(DP)protection. In this paper, we propose a gradient sparsification empowered FL framework with DP over wireless channels, to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client's local model, thereby mitigating the performance degradation induced by DP and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client's DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real-life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin, and delay-minimization algorithms.

关键词： federated learning differential privacy gradient sparsification Lyapunov drift convergence 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：