GCN现有变体不完全汇总（在时空数据挖掘中的应用）

GCN现有变体汇总（应用篇）

Mix Hop（高阶多跳的图特征）融合

文献：

ICML_2019

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

                                            

AAAI_20: Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting

2. 两路并行，同时对节点和边的关系建模，形成以边为中心的图网络和以节点为中心的图网络

NodeNet

EdgeNet

AAAI_20: Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting （同上）

TKDE_20: Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning

IJCAI_19: MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

两路并行 将GCN的卷积结果和S-LSTM(summary)和I-LSTM（interaction）

1. weighted graph convolution

2. graph-gather layers 经过一层全连接再加起来得到全图的全部信息（和）是表示graph-level的信息

3. 对gt做 graph-state的S-LSTM 也就是对summary graph-gate做 graph-level的LSTM

4. 对gXt和gYt进行连接，再对其做LSTM 就是interaction

5. 最后把得到的结果都concantenate起来 经过全连接 得到1*k的向量 k表示标注交集的label数。

这个工作得到的都是graph-level的结果，我们也可以拓展到node-level去

 

3. Multi-step Prediction: GCN+Seq2Seq

IJCAI_19: STG2Seq: Spatial-Temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting

 

IJCAI_19: GSTNet: Global Spatial-Temporal Network for Traffic Flow Prediction

                          

STSGCN https://github.com/Davidham3/STSGCN AAAI_20 【Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting】

It is designed for spatio-temporal network data forecasting, which captures complex localized spatial-temporal correlations and heterogeneity with a Spatial-Temporal Synchronous Graph Convolutional Network.

                              

 

4. 异质GCN：Hetero-GCN

KDD_19:  Heterogeneous Graph Neural Network

                                              

AAAI_20: An Attention-based Graph Neural Network for Heterogeneous Structural Learning

推荐系统里建模异质网络IntentGC

IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation

 

vector-wise/bit-wise

                             

 

5. MaskGCN:

IJCAI_19: STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems

                       

IJCAI_19: Masked Graph Convolutional Network

                                       

 

Network embedding就是通过训练特征表示representation来使得图中相邻的节点表征尽可能小，而较远的节点表征尽可能大。或者使得特征表示满足其他的task相关的要求。

Network embedding aims to represent graph nodes in a low dimensional space where the network structure and properties are preserved.