Reference Paper

papers/RefPaperByMarkyan04/Topic5 Graph or heterogeneous graph priors/Graph Attention Networks/Graph Attention Networks.bib

@@ -0,0 +1,9 @@
+@misc{veličković2018graphattentionnetworks,
+      title={Graph Attention Networks}, 
+      author={Petar Veličković and Guillem Cucurull and Arantxa Casanova and Adriana Romero and Pietro Liò and Yoshua Bengio},
+      year={2018},
+      eprint={1710.10903},
+      archivePrefix={arXiv},
+      primaryClass={stat.ML},
+      url={https://arxiv.org/abs/1710.10903}, 
+}

papers/RefPaperByMarkyan04/Topic5 Graph or heterogeneous graph priors/GraphMAE Self-Supervised Masked Graph Autoencoders/GraphMAE Self-Supervised Masked Graph Autoencoders.bib

@@ -0,0 +1,9 @@
+@misc{hou2022graphmaeselfsupervisedmaskedgraph,
+      title={GraphMAE: Self-Supervised Masked Graph Autoencoders}, 
+      author={Zhenyu Hou and Xiao Liu and Yukuo Cen and Yuxiao Dong and Hongxia Yang and Chunjie Wang and Jie Tang},
+      year={2022},
+      eprint={2205.10803},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2205.10803}, 
+}

papers/RefPaperByMarkyan04/Topic5 Graph or heterogeneous graph priors/Heterogeneous Graph Transformer/Heterogeneous Graph Transformer.bib

@@ -0,0 +1,9 @@
+@misc{hu2020heterogeneousgraphtransformer,
+      title={Heterogeneous Graph Transformer}, 
+      author={Ziniu Hu and Yuxiao Dong and Kuansan Wang and Yizhou Sun},
+      year={2020},
+      eprint={2003.01332},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2003.01332}, 
+}

papers/RefPaperByMarkyan04/Topic5 Graph or heterogeneous graph priors/How Powerful are Graph Neural Networks/How Powerful are Graph Neural Networks.bib

@@ -0,0 +1,9 @@
+@misc{xu2019powerfulgraphneuralnetworks,
+      title={How Powerful are Graph Neural Networks?}, 
+      author={Keyulu Xu and Weihua Hu and Jure Leskovec and Stefanie Jegelka},
+      year={2019},
+      eprint={1810.00826},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/1810.00826}, 
+}

papers/RefPaperByMarkyan04/Topic5 Graph or heterogeneous graph priors/Intro.txt

@@ -0,0 +1,21 @@
+图表示学习/异构图（直接对应你选的(设备,寄存器)结构）
+
+你明确了节点是 (设备,寄存器)，这天然是二部图/异构图（Device 与 Register 两类实体）。STOUTER 用的是 base station graph；你这里更建议引用异构图建模经典方法，解释为什么要用二部图结构做“空间先验”。
+
+Kipf & Welling. Semi-Supervised Classification with Graph Convolutional Networks (GCN). ICLR 2017.
+用途：基础 GCN；你做拓扑表征学习的常用基线引用。
+
+Veličković et al. Graph Attention Networks (GAT). ICLR 2018.
+用途：注意力聚合，适合“不同邻边权重不同”（例如不同设备之间依赖强弱不同）。
+
+Xu et al. How Powerful are Graph Neural Networks? (GIN). ICLR 2019.
+用途：强调结构表达能力；如果你需要强结构区分能力，可引用。
+
+Schlichtkrull et al. Modeling Relational Data with Graph Convolutional Networks (R-GCN). ESWC 2018.
+用途：关系类型图卷积；很适合你在(设备,寄存器)图里加入多种边：read、write、same-device、process-link 等关系类型。
+
+Hu et al. Heterogeneous Graph Transformer (HGT). WWW 2020.
+用途：异构图 Transformer；如果你后续把“设备类型/寄存器类型/功能码”都纳入异构建模，HGT 是很强的参考。
+
+Hou et al. GraphMAE: Self-Supervised Masked Graph Autoencoders. KDD/相关会议 2022.
+用途：图自监督预训练；对应 STOUTER 的图 autoencoder 预训练思想，你可以用它支撑“先学图嵌入，再用于生成”。

papers/RefPaperByMarkyan04/Topic5 Graph or heterogeneous graph priors/Modeling Relational Data with Graph Convolutional Networks/Modeling Relational Data with Graph Convolutional Networks.bib

@@ -0,0 +1,9 @@
+@misc{schlichtkrull2017modelingrelationaldatagraph,
+      title={Modeling Relational Data with Graph Convolutional Networks}, 
+      author={Michael Schlichtkrull and Thomas N. Kipf and Peter Bloem and Rianne van den Berg and Ivan Titov and Max Welling},
+      year={2017},
+      eprint={1703.06103},
+      archivePrefix={arXiv},
+      primaryClass={stat.ML},
+      url={https://arxiv.org/abs/1703.06103}, 
+}

papers/RefPaperByMarkyan04/Topic5 Graph or heterogeneous graph priors/Semi-Supervised Classification with Graph Convolutional Networks/Semi-Supervised Classification with Graph Convolutional Networks.bib

@@ -0,0 +1,9 @@
+@misc{kipf2017semisupervisedclassificationgraphconvolutional,
+      title={Semi-Supervised Classification with Graph Convolutional Networks}, 
+      author={Thomas N. Kipf and Max Welling},
+      year={2017},
+      eprint={1609.02907},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/1609.02907}, 
+}