Recurrent Neural Collective Classification

Monner D.D.; Reggia J.A.

首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Recurrent Neural Collective Classification

【24h】

Recurrent Neural Collective Classification

机译：递归神经集体分类

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

With the recent surge in availability of data sets containing not only individual attributes but also relationships, classification techniques that take advantage of predictive relationship information have gained in popularity. The most popular existing collective classification techniques have a number of limitations—some of them generate arbitrary and potentially lossy summaries of the relationship data, whereas others ignore directionality and strength of relationships. Popular existing techniques make use of only direct neighbor relationships when classifying a given entity, ignoring potentially useful information contained in expanded neighborhoods of radius greater than one. We present a new technique that we call recurrent neural collective classification (RNCC), which avoids arbitrary summarization, uses information about relationship directionality and strength, and through recursive encoding, learns to leverage larger relational neighborhoods around each entity. Experiments with synthetic data sets show that RNCC can make effective use of relationship data for both direct and expanded neighborhoods. Further experiments demonstrate that our technique outperforms previously published results of several collective classification methods on a number of real-world data sets.

机译：随着最近不仅包含单个属性而且还包含关系的数据集的可用性激增，利用预测性关系信息的分类技术日益普及。现有的最流行的集体分类技术有很多局限性-其中一些会生成关系数据的任意且可能有损的摘要，而另一些会忽略关系的方向性和强度。现有的流行技术在对给定实体进行分类时仅利用直接邻居关系，而忽略了半径大于1的扩展邻域中包含的潜在有用信息。我们提出了一种称为递归神经集体分类（RNCC）的新技术，该技术避免了任意汇总，使用了有关关系方向性和强度的信息，并通过递归编码学习了如何利用每个实体周围的较大关系邻域。使用综合数据集进行的实验表明，RNCC可以有效利用直接和扩展邻域的关系数据。进一步的实验表明，我们的技术在许多实际数据集上的性能优于先前发表的几种集体分类方法的结果。

著录项

来源
《Neural Networks and Learning Systems, IEEE Transactions on》 |2013年第12期|1932-1943|共12页
作者
Monner D.D.; Reggia J.A.;
展开▼
作者单位

Department of Computer Science, University of Maryland, College Park, MD, USA|c|;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Collective classification; expanded relational neighborhoods; long short-term memory architecture (LSTM); recurrent neural network;

机译：集体分类;扩展的关系邻域;长短期记忆架构（LSTM）;递归神经网络;

相似文献

外文文献
中文文献
专利

1. Combining attention-based bidirectional gated recurrent neural network and two-dimensional convolutional neural network for document-level sentiment classification [J] . Liu Fagui, Zheng Jingzhong, Zheng Lailei, Neurocomputing . 2020,第Jana2期

机译：结合基于注意力的双向门控递归神经网络和二维卷积神经网络进行文档级情感分类
2. Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification [J] . Banerjee Imon, Ling Yuan, Chen Matthew C., Artificial intelligence in medicine . 2019,第JUNa期

机译：卷积神经网络（CNN）和递归神经网络（RNN）架构在放射学文本报告分类中的比较有效性
3. Recurrent collective classification [J] . Fan Shuangfei, Huang Bert Knowledge and information systems . 2019,第2期

机译：经常性集体分类
4. Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning [C] . Mengge Xue, Weiming Cai, Jinsong Su, International Joint Conference on Artificial Intelligence . 2020

机译：基于经常性随机步行网络学习的神经集体实体联系
5. Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks [D] . Hassan, Abdalraouf. 2018

机译：基于卷积神经网络和递归神经网络的深度神经语言文本分类模型
6. Towards Lifespan Automation for Caenorhabditis elegans Based on Deep Learning: Analysing Convolutional and Recurrent Neural Networks for Dead or Live Classification [O] . Antonio García Garví, Joan Carles Puchalt, Pablo E. Layana Castro, 2021

机译：基于深度学习的Caenorhabditis的lefaliation自动化：分析死亡或实时分类的卷积和经常性神经网络
7. Human activity recognition and classification using of convolutional neural networks and recurrent neural networks [O] . Mohammed ALBABA, Alhakam QASSAB, Arif YILMAZ 2020

机译：人类活动认可与卷积神经网络和经常性神经网络的分类

Recurrent Neural Collective Classification

摘要

著录项

相似文献

相关主题

期刊订阅