network embedding 需读论文

Must-read papers on NRL/NE.

github: https://github.com/nate-russell/Network-Embedding-Resources

NRL: network representation learning. NE: network embedding.

Contributed by Cunchao Tu and Yuan Yao.

  1. DeepWalk: Online Learning of Social Representations. Bryan Perozzi, Rami Al-Rfou, Steven Skiena. KDD 2014. papercode
  2. Learning Latent Representations of Nodes for Classifying in Heterogeneous Social Networks. Yann Jacob, Ludovic Denoyer, Patrick Gallinar. WSDM 2014. paper
  3. Non-transitive Hashing with Latent Similarity Componets. Mingdong Ou, Peng Cui, Fei Wang, Jun Wang, Wenwu Zhu.KDD 2015. paper
  4. GraRep: Learning Graph Representations with Global Structural Information. Shaosheng Cao, Wei Lu, Qiongkai Xu.CIKM 2015. paper code
  5. LINE: Large-scale Information Network Embedding. Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, Qiaozhu Me. WWW 2015. paper code
  6. Network Representation Learning with Rich Text Information. Cheng Yang, Zhiyuan Liu, Deli Zhao, Maosong Sun, Edward Y. Chang. IJCAI 2015. paper code
  7. PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks. Jian Tang, Meng Qu, Qiaozhu Mei.KDD 2015. paper code
  8. Heterogeneous Network Embedding via Deep Architectures. Shiyu Chang, Wei Han, Jiliang Tang, Guo-Jun Qi, Charu C. Aggarwal, Thomas S. Huang. KDD 2015. paper
  9. Deep Neural Networks for Learning Graph Representations. Shaosheng Cao, Wei Lu, Xiongkai Xu. AAAI 2016. papercode
  10. Asymmetric Transitivity Preserving Graph Embedding. Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, Wenwu Zhu. KDD 2016. paper
  11. Revisiting Semi-supervised Learning with Graph Embeddings. Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov.ICML 2016. paper
  12. node2vec: Scalable Feature Learning for Networks. Aditya Grover, Jure Leskovec. KDD 2016. paper code
  13. Max-Margin DeepWalk: Discriminative Learning of Network Representation. Cunchao Tu, Weicheng Zhang, Zhiyuan Liu, Maosong Sun. IJCAI 2016. paper code
  14. Structural Deep Network Embedding. Daixin Wang, Peng Cui, Wenwu Zhu. KDD 2016. paper
  15. Community Preserving Network Embedding. Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, Shiqiang Yang.AAAI 2017. paper
  16. Semi-supervised Classification with Graph Convolutional Networks. Thomas N. Kipf, Max Welling. ICLR 2017. papercode
  17. CANE: Context-Aware Network Embedding for Relation Modeling. Cunchao Tu, Han Liu, Zhiyuan Liu, Maosong Sun. ACL 2017. paper code
  18. Fast Network Embedding Enhancement via High Order Proximity Approximation. Cheng Yang, Maosong Sun, Zhiyuan Liu, Cunchao Tu. IJCAI 2017. paper code
  19. TransNet: Translation-Based Network Representation Learning for Social Relation Extraction. Cunchao Tu, Zhengyan Zhang, Zhiyuan Liu, Maosong Sun. IJCAI 2017. paper code
  20. metapath2vec: Scalable Representation Learning for Heterogeneous Networks. Yuxiao Dong, Nitesh V. Chawla, Ananthram Swami. KDD 2017. paper code
  21. Learning from Labeled and Unlabeled Vertices in Networks. Wei Ye, Linfei Zhou, Dominik Mautz, Claudia Plant, Christian Böhm. KDD 2017.
  22. Unsupervised Feature Selection in Signed Social Networks. Kewei Cheng, Jundong Li, Huan Liu. KDD 2017. paper
  23. struc2vec: Learning Node Representations from Structural Identity. Leonardo F. R. Ribeiro, Pedro H. P. Saverese, Daniel R. Figueiredo. KDD 2017. paper code
  24. Inductive Representation Learning on Large Graphs. William L. Hamilton, Rex Ying, Jure Leskovec. Submitted to NIPS 2017. paper code
  25. Variation Autoencoder Based Network Representation Learning for Classification. Hang Li, Haozheng Wang, Zhenglu Yang, Masato Odagaki. ACL 2017. paper
时间： 2024-10-29 19:08:22

network embedding 需读论文的相关文章

Network Embedding 论文小览

Network Embedding 论文小览 转自:http://blog.csdn.net/Dark_Scope/article/details/74279582,感谢分享! 自从word2vec横空出世,似乎一切东西都在被embedding,今天我们要关注的这个领域是Network Embedding,也就是基于一个Graph,将节点或者边投影到低维向量空间中,再用于后续的机器学习或者数据挖掘任务,对于复杂网络来说这是比较新的尝试,而且取得了一些效果. 本文大概梳理了最近几年流行的一些方法和

读论文笔记

最近开始认真的去读论文了,而且慢慢读出了一点味道,首先最基本的读的速度变快了,可能是因为读的这几篇论文里重复的单词比较多,,,,害怕读的论文,过了一段时间又给忘了,所以一点一点记下来. 我做的毕设是彩色水果图像的分割嘛,所以先读的论文自然都是和水果有关的,去那些数据库搜索文献,关键词就是 fruit image segmentation. 1      <Object Segmentation For Fruit Image Using OHTA Color Space and Cascade

（读论文）推荐系统之ctr预估-Wide＆Deep模型解析

在读了FM和FNN/PNN的论文后,来学习一下16年的一篇Google的论文,文章将传统的LR和DNN组合构成一个wide&deep模型(并行结构),既保留了LR的拟合能力,又具有DNN的泛化能力,并且不需要单独训练模型,可以方便模型的迭代,一起来看下吧. 更好的阅读体验请点击这里. 原文:Wide & Deep Learning for Recommender Systems 地址: [https://arxiv.org/pdf/1606.07792.pdf](https://arxiv

读论文Machine Learning for Improved Diagnosis and Prognosis in Healthcare

这是我读的第一篇英文论文,连着读了两遍,做了一些笔记,是一个接收的过程. 文章主要讲了机器学习的一些方法,以及两个实际应用.

读论文BinarizedNormedGradientsforObjectnessEstimationat300fps

关于论文 这两天翻了翻cvpr2014的论文,发现程明明老师关于Objectness Detecting的论文,于是拜读了一番.论文贡献了两个观点: 目标有closed boundary,因此将窗口resize到8x8也能进行目标和背景的识别,这实际上降低了窗口的分辨率,resize到8x8目的是加速计算.这就相当于我们看路上走的人一样,在很远的地方即使我们没看清楚脸,只是看到一个轮廓也能识别出是不是我们认识的人,反而,如果脸贴着脸去看一个人可能会认不出来.作者还使用了最简单的梯度特征,运算量非

Deep Learning 23：dropout理解_之读论文“Improving neural networks by preventing co-adaptation of feature detectors”

理论知识:Deep learning:四十一(Dropout简单理解).深度学习(二十二)Dropout浅层理解与实现.“Improving neural networks by preventing co-adaptation of feature detectors” 感觉没什么好说的了,该说的在引用的这两篇博客里已经说得很清楚了,直接做试验吧 注意: 1.在模型的测试阶段,使用”mean network(均值网络)”来得到隐含层的输出,其实就是在网络前向传播到输出层前时隐含层节点的输出值都

读论文系列：Object Detection SPP-net

本文为您解读SPP-net: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition Motivation 神经网络在计算机视觉方面的成功得益于卷积神经网络,然而,现有的许多成功的神经网络结构都要求输入为一个固定的尺寸(比如224x224,299x299),传入一张图像,需要对它做拉伸或者裁剪,再输入到网络中进行运算. 然而,裁剪可能会丢失信息,拉伸会使得图像变形,这些因素都提高了视觉任务的门槛,

读论文系列：Object Detection ECCV2016 SSD

转载请注明作者:梦里茶 Single Shot MultiBox Detector Introduction 一句话概括:SSD就是关于类别的多尺度RPN网络 基本思路: 基础网络后接多层feature map 多层feature map分别对应不同尺度的固定anchor 回归所有anchor对应的class和bounding box Model 输入:300x300 经过VGG-16(只到conv4_3这一层) 经过几层卷积,得到多层尺寸逐渐减小的feature map 每层feature m

【Network Architecture】SegNet论文解析（转）

文章来源: https://blog.csdn.net/fate_fjh/article/details/53467948 Introduction 自己制作国内高速公路label,使用SegNet训练高速公路模型,测试效果 参考:http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html SegNet是Cambridge提出旨在解决自动驾驶或者智能机器人的图像语义分割深度网络,开放源码,基于caffe框架.SegNet基于FCN,修改VGG-16