GCN現(xiàn)有變體匯總（應(yīng)用篇）
Mix Hop（高階多跳的圖特征）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. 兩路并行，同時對節(jié)點和邊的關(guān)系建模，形成以邊為中心的圖網(wǎng)絡(luò)和以節(jié)點為中心的圖網(wǎng)絡(luò)
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
兩路并行 將GCN的卷積結(jié)果和S-LSTM(summary)和I-LSTM（interaction）
1. weighted graph convolution
2. graph-gather layers 經(jīng)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. 最后把得到的結(jié)果都concantenate起來 經(jīng)過全連接 得到1*k的向量 k表示標(biāo)注交集的label數(shù)。
這個工作得到的都是graph-level的結(jié)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(zhì)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(tǒng)里建模異質(zhì)網(wǎng)絡(luò)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(xùn)練特征表示representation來使得圖中相鄰的節(jié)點表征盡可能小，而較遠的節(jié)點表征盡可能大。或者使得特征表示滿足其他的task相關(guān)的要求。
Network embedding aims to represent graph nodes in a low dimensional space where the network structure and properties are preserved.
