IEEE transactions on neural networks and learning systems最新文献_第9页

Self-Organizing Stacked Type-2 Fuzzy Neural Network With Rule Generalization 具有规则泛化功能的自组织堆叠式 2 型模糊神经网络

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-04-01 DOI: 10.1109/tnnls.2025.3544495

Honggui Han, Chenxuan Sun, Xiaolong Wu, Hongyan Yang, Dezheng Zhao

引用次数: 0

Responding to News Sensitively in Stock Attention Networks via Prompt-Adaptive Trimodal Model 基于提示-自适应三模态模型的存量注意网络对新闻的敏感响应

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-29 DOI: 10.1109/tnnls.2025.3547141

Haotian Liu, Bowen Hu, Yadong Zhou, Yuxun Zhou

引用次数: 0

Diversify and Conquer: Open-Set Disagreement for Robust Semi-Supervised Learning With Outliers 多样化与征服：具有异常值的鲁棒半监督学习的开集分歧

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-29 DOI: 10.1109/tnnls.2025.3547801

Heejo Kong, Sung-Jin Kim, Gunho Jung, Seong-Whan Lee

引用次数: 0

Boundary-Based Active Domain Adaptation for Semantic Segmentation Under Adverse Conditions 不利条件下基于边界的主动域自适应语义分割

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-28 DOI: 10.1109/tnnls.2025.3544204

Xianzhe Xu, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Wenqi Ren, Lu Sheng, Yang Tang

引用次数: 0

EGVD: Event-Guided Video Deraining EGVD：事件导向视频培训

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-28 DOI: 10.1109/tnnls.2025.3543381

Yueyi Zhang, Jin Wang, Wenming Weng, Xiaoyan Sun, Zhiwei Xiong

引用次数: 0

A Framework for Large-Scale Synthetic Graph Dataset Generation 大规模合成图数据集生成框架

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-28 DOI: 10.1109/tnnls.2025.3540392

Sajad Darabi, Piotr Bigaj, Dawid Majchrowski, Artur Kasymov, Pawel Morkisz, Alex Fit-Florea

引用次数: 0

Inverse RL Scene Dynamics Learning for Nonlinear Predictive Control in Autonomous Vehicles 用于自动驾驶车辆非线性预测控制的逆RL场景动态学习

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-28 DOI: 10.1109/tnnls.2025.3549816

Sorin M. Grigorescu, Mihai V. Zaha

引用次数: 0

A UHD Aerial Photograph Categorization System by Learning a Noise-Tolerant Topology Kernel 基于容噪拓扑核的超高清航拍图像分类系统

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-26 DOI: 10.1109/tnnls.2024.3355928

Luming Zhang, Guifeng Wang, Ming Chen, Ling Shao

引用次数: 0

Confidence-Based PU Learning With Instance-Dependent Label Noise. 基于置信度的PU学习与实例相关的标签噪声。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-24 DOI: 10.1109/TNNLS.2025.3549510

Xijia Tang, Chao Xu, Hong Tao, Xiaoyu Ma, Chenping Hou

{"title":"Confidence-Based PU Learning With Instance-Dependent Label Noise.","authors":"Xijia Tang, Chao Xu, Hong Tao, Xiaoyu Ma, Chenping Hou","doi":"10.1109/TNNLS.2025.3549510","DOIUrl":"10.1109/TNNLS.2025.3549510","url":null,"abstract":"Positive and unlabeled (PU) learning, which trains binary classifiers using only PU data, has gained vast attentions in recent years. Traditional PU learning often assumes that all the positive samples are labeled accurately. Nevertheless, due to the reasons such as sample ambiguity and insufficient algorithms, label noise is almost unavoidable in this scenario. Current PU algorithms neglect the label noise issue in the positive set, which is often biased toward certain instances rather than being uniformly distributed in practical applications. We define this important but understudied problem as PU learning with instance-dependent label noise (PUIDN). To eliminate the adverse impact of IDN, we leverage confidence scores for each instance in the positive set, which establish the connection between samples and labels without any assumption on noise distribution. Then, we propose an unbiased estimator for classification risk considering both label and confidence information, which can be computed immediately from PUIDN data along with their confidence scores. Moreover, our classification framework integrates an optimization strategy of alternating iteration based on the correlation between different confidence information, thereby alleviating the additional requirement for training data. Theoretically, we derive a generalization error bound for our proposed method. Experimentally, the effectiveness of our approach is demonstrated through various types of numerical results.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143700270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Time-Aware Graph Learning for Link Prediction on Temporal Networks. 时序网络链路预测的时间感知图学习。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-03-24 DOI: 10.1109/TNNLS.2025.3545021

Zhiqiang Pan, Honghui Chen, Wanyu Chen, Fei Cai, Xinwang Liu

{"title":"Time-Aware Graph Learning for Link Prediction on Temporal Networks.","authors":"Zhiqiang Pan, Honghui Chen, Wanyu Chen, Fei Cai, Xinwang Liu","doi":"10.1109/TNNLS.2025.3545021","DOIUrl":"https://doi.org/10.1109/TNNLS.2025.3545021","url":null,"abstract":"Link prediction on temporal networks aims to predict the future edges by modeling the dynamic evolution involved in the graph data. Previous methods relying on the node/edge attributes or the distance on the graph structure are not practical due to the deficiency of the attributes and the limitation of the explicit distance estimation, respectively. Moreover, the existing graph representation learning methods mostly rely on graph neural networks (GNNs), which cannot adequately take the dynamic correlations between nodes into consideration, leading to the generating of inferior node embeddings. Thus, we propose a time-aware graph (TAG) learning method for link prediction on temporal networks. We first conduct a theoretical causal analysis proving that the correlations between nodes are required to be unchanged for the temporal graph representation learning using GNNs. Then, we model the recent dynamic node correlations by designing an edge-dropping (ED) module and adopting a recent neighbor sampling (RNS) strategy so as to approximate the above condition. Besides, we also preserve the long-term stable node correlations by introducing additional self-supervisions using the contrastive learning. Comprehensive experiments were conducted on four public temporal network datasets, i.e., MathOverflow, StackOverflow, AskUbuntu, and SuperUser, demonstrate that TAG can achieve state-of-the-art performance in terms of average precision (AP) and area under the ROC curve (AUC). In addition, TAG can ensure high computational efficiency by making the temporal graph lightweight, letting it be practical in real-world applications.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143700277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0