GCN現有變體不完全彙總（在時空數據挖掘中的應用）

GCN現有變體彙總（應用篇）

Mix Hop（高階多跳的圖特徵）融合

文獻：

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. 兩路並行，同時對節點和邊的關係建模，形成以邊爲中心的圖網絡和以節點爲中心的圖網絡

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

兩路並行 將GCN的卷積結果和S-LSTM(summary)和I-LSTM（interaction）

1. weighted graph convolution

2. graph-gather layers 經過一層全連接再加起來得到全圖的全部信息（和）是表示graph-level的信息

3. 對gt做 graph-state的S-LSTM 也就是對summary graph-gate做 graph-level的LSTM

4. 對gXt和gYt進行連接，再對其做LSTM 就是interaction

5. 最後把得到的結果都concantenate起來 經過全連接 得到1*k的向量 k表示標註交集的label數。

這個工作得到的都是graph-level的結果，我們也可以拓展到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. 異質GCN：Hetero-GCN

KDD_19:  Heterogeneous Graph Neural Network

                                              

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

推薦系統裏建模異質網絡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就是通過訓練特徵表示representation來使得圖中相鄰的節點表徵儘可能小，而較遠的節點表徵儘可能大。或者使得特徵表示滿足其他的task相關的要求。

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