图深度学习论文笔记整理活动 | ApacheCN

整体进度：https://github.com/apachecn/graph-emb-dl-notes/issues/1

贡献指南：https://github.com/apachecn/graph-emb-dl-notes/blob/master/CONTRIBUTING.md

项目仓库：https://github.com/apachecn/graph-emb-dl-notes

---

贡献指南

请您勇敢地去翻译和改进翻译。虽然我们追求卓越，但我们并不要求您做到十全十美，因此请不要担心因为翻译上犯错——在大部分情况下，我们的服务器已经记录所有的翻译，因此您不必担心会因为您的失误遭到无法挽回的破坏。（改编自维基百科）

负责人：

• 飞龙：562826179

章节列表

• GCN
  • A new model for learning in graph domains
  • The graph neural network model
  • Spectral networks and locally connected networks on graphs
  • Convolutional networks on graphs for learning molecular fingerprints
  • Gated graph sequence neural networks
  • Accelerated filtering on graphs using lanczos method
  • Deep convolutional networks on graph-structured data
  • Convolutional neural networks on graphs with fast localized spectral filtering
  • Diffusion-convolutional neural networks
  • Learning convolutional neural networks for graphs
  • Molecular graph convolutions: moving beyond fingerprints
  • Inductive representation learning on large graphs
  • Neural message passing for quantum chemistry
  • Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
  • Geometric deep learning on graphs and manifolds using mixture model cnns
  • Semi-supervised classification with graph convolutional networks
  • Robust spatial filtering with graph convolutional neural networks
  • Cayleynets: graph convolutional neural networks with complex rational spectral filters
  • Hierarchical graph representation learning with differentiable pooling
  • Structure-Aware Convolutional Neural Networks
  • Adaptive graph convolutional neural networks
  • Deeper insights into graph convolutional networks for semi-supervised learning
  • Large-Scale Learnable Graph Convolutional Networks
  • FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
  • Learning steady-states of iterative algorithms over graphs
  • Representation learning on graphs with jumping knowledge networks
  • Stochastic Training of Graph Convolutional Networks with Variance Reduction
  • Dual graph convolutional networks for graph-based semi-supervised classification
  • Graph capsule convolutional neural networks
  • How powerful are graph neural networks?
  • Modeling relational data with graph convolutional networks
  • Multidimensional graph convolutional networks
  • Signed graph convolutional network
  • Capsule Graph Neural Network
  • Combining Neural Networks with Personalized PageRank for Classification on Graphs
  • DIFFUSION SCATTERING TRANSFORMS ON GRAPHS
  • Graph Wavelet Neural Network
  • LanczosNet: Multi-Scale Deep Graph Convolutional Networks
  • Bayesian Graph Convolutional Neural Networks for Semi-supervised Classification
  • Geniepath: Graph neural networks with adaptive receptive paths
  • Hypergraph Neural Networks
  • Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
  • Can GCNs Go as Deep as CNNs?
• Graph Attention
  • Graph Attention Networks
  • Gaan: Gated attention networks for learning on large and spatiotemporal graphs
  • Watch your step: Learning node embeddings via graph attention
  • Graph classification using structural attention
• GAE
  • Structural deep network embedding
  • Deep neural networks for learning graph representations
  • Variational graph auto-encoders
  • Mgae: Marginalized graph autoencoder for graph clustering
  • Link Prediction Based on Graph Neural Networks
  • SpectralNet: Spectral Clustering using Deep Neural Networks
  • Deep Recursive Network Embedding with Regular Equivalence
  • Learning Deep Network Representations with Adversarially Regularized Autoencoders
  • Adversarially Regularized Graph Autoencoder for Graph Embedding
  • Deep graph infomax

流程

一、认领

首先查看整体进度，确认没有人认领了你想认领的章节。

然后回复 ISSUE，注明“章节 + QQ 号”。

二、整理笔记

阅读论文，填写以下内容：

• 模型架构
• 输入类型：同构图/二分图
• 嵌入类型：节点/边/子图/整图
• 任务类型：无监督/半监督
• 和 baseline 相比的创新点
• （有/无）理论解释

三、提交

• fork Github 项目
• 将文档（Markdown 格式）放在docs中。
• push
• pull request

请见 Github 入门指南。

来源：oschina

链接：https://my.oschina.net/u/1777350/blog/3078199