深度图神经网络(GNN)论文
part1/经典款论文
1. KDD 2016，Node2vec 经典必读第一篇，平衡同质性和结构性
《node2vec: Scalable Feature Learning for Networks》
2. WWW2015，LINE 1阶+2阶相似度
《Line: Large-scale information network embedding》
3. KDD 2016，SDNE 多层自编码器
《Structural deep network embedding》
4. KDD 2017，metapath2vec 异构图网络
《metapath2vec: Scalable representation learning for heterogeneous networks》
5. NIPS 2013，TransE 知识图谱奠基
《Translating Embeddings for Modeling Multi-relational Data》
6. ICLR 2018，GAT attention机制
《Graph Attention Network》
7. NIPS 2017，GraphSAGE 归纳式学习框架
《Inductive Representation Learning on Large Graphs 》
8. ICLR 2017，GCN 图神经开山之作
《SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS》
9. ICLR 2016，GGNN 门控图神经网络
《Gated Graph Sequence Neural Networks》
10. ICML 2017，MPNN 空域卷积消息传递框架
《Neural Message Passing for Quantum Chemistry》
part2/热门款论文
2020年之前
11.[arXiv 2019]Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
重温图神经网络：我们只有低通滤波器
[论文]
https://arxiv.org/abs/1905.09550
12.[NeurIPS 2019]Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
打破天花板：更强的多尺度深度图卷积网络
[论文]
https://arxiv.org/abs/1906.02174
13.[ICLR 2019] Predict then Propagate: Graph Neural Networks meet Personalized PageRank
先预测后传播：图神经网络满足个性化 PageRank
[论文]
https://arxiv.org/abs/1810.05997
[代码]
https://github.com/klicperajo/ppnp
14.[ICCV 2019]DeepGCNs: Can GCNs Go as Deep as CNNs?
DeepGCN：GCN能像CNN一样深入吗？
[论文]
https://arxiv.org/abs/1904.03751
[代码(Pytorch)]
https://github.com/lightaime/deep_gcns_torch
[代码(TensorFlow)]
https://github.com/lightaime/deep_gcns
15.[ICML 2018]
Representation Learning on Graphs with Jumping Knowledge Networks
基于跳跃知识网络的图表征学习
[论文]
https://arxiv.org/abs/1806.03536
16.[AAAI 2018]Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
深入了解用于半监督学习的图卷积网络
[论文]
https://arxiv.org/abs/1801.07606
2020年
17.[arXiv 2020]Deep Graph Neural Networks with Shallow Subgraph Samplers
具有浅子图采样器的深图神经网络
[论文]
https://arxiv.org/abs/2012.01380
18.[arXiv 2020]Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
从优化的角度重新审视半监督节点分类的图卷积网络
[论文]
https://arxiv.org/abs/2009.11469
19.[arXiv 2020]
Tackling Over-Smoothing for General Graph Convolutional Networks
解决通用图卷积网络的过度平滑
[论文]
https://arxiv.org/abs/2008.09864
20.[arXiv 2020]DeeperGCN: All You Need to Train Deeper GCNs
DeeperGCN：训练更深的 GCN 所需的一切
[论文]
https://arxiv.org/abs/2006.07739
[代码]
https://github.com/lightaime/deep_gcns_torch
21.[arXiv 2020]Effective Training Strategies for Deep Graph Neural Networks
深度图神经网络的有效训练策略
[论文]
https://arxiv.org/abs/2006.07107
[代码]
https://github.com/miafei/NodeNorm
22.[arXiv 2020]Revisiting Over-smoothing in Deep GCNs
重新审视深度GCN中的过度平滑
[论文]
https://arxiv.org/abs/2003.13663
23.[NeurIPS 2020]Graph Random Neural Networks for Semi-Supervised Learning on Graphs
用于图上半监督学习的图随机神经网络
[论文]
https://proceedings.neurips.cc/paper/2020/hash/fb4c835feb0a65cc39739320d7a51c02-Abstract.html
[代码]
https://github.com/THUDM/GRAND
24.[NeurIPS 2020]Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
散射GCN：克服图卷积网络中的过度平滑
[论文]
https://proceedings.neurips.cc/paper/2020/hash/a6b964c0bb675116a15ef1325b01ff45-Abstract.html
[代码]
https://github.com/dms-net/scatteringGCN
25.[NeurIPS 2020]Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
Transduction through Gradient Boosting 的优化和泛化分析及其在多尺度图神经网络中的应用
[论文]
https://proceedings.neurips.cc/paper/2020/hash/dab49080d80c724aad5ebf158d63df41-Abstract.html
[代码]
https://github.com/delta2323/GB-GNN
26.[NeurIPS 2020]Towards Deeper Graph Neural Networks with Differentiable Group Normalization
迈向具有可微组归一化的更深图神经网络
[论文]
https://arxiv.org/abs/2006.06972
27.[ICML 2020 Workshop GRL+]A Note on Over-Smoothing for Graph Neural Networks
关于图神经网络过度平滑的说明
[论文]
https://arxiv.org/abs/2006.13318
28.[ICML 2020]Bayesian Graph Neural Networks with Adaptive Connection Sampling
具有自适应连接采样的贝叶斯图神经网络
[论文]
https://arxiv.org/abs/2006.04064
29.[ICML 2020]Continuous Graph Neural Networks连续图神经网络
[论文]
https://arxiv.org/abs/1912.00967
30.[ICML 2020]Simple and Deep Graph Convolutional Networks简单和深度图卷积网络
[论文]
https://arxiv.org/abs/2007.02133
[代码]
https://github.com/chennnM/GCNII
31.[KDD 2020] Towards Deeper Graph Neural Networks走向更深的图神经网络
[论文]
https://arxiv.org/abs/2007.09296
[代码]
https://github.com/mengliu1998/DeeperGNN
32.[ICLR 2020]Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
图神经网络对节点分类的表达能力呈指数级 下降
[论文]
https://arxiv.org/abs/1905.10947
[代码]
https://github.com/delta2323/gnn-asymptotics
33.[ICLR 2020] DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
DropEdge：迈向节点分类的深度图卷积网络
[Paper]
https://openreview.net/forum?id=Hkx1qkrKPr
[Code]
https://github.com/DropEdge/DropEdge
34.[ICLR 2020] PairNorm: Tackling Oversmoothing in GNNs
PairNorm：解决GNN中的过度平滑问题
[论文]
https://openreview.net/forum?id=rkecl1rtwB
[代码]
https://github.com/LingxiaoShawn/PairNorm
35.[ICLR 2020]Measuring and Improving the Use of Graph Information in Graph Neural Networks
测量和改进图神经网络中图信息的使用
[论文]
https://openreview.net/forum?id=rkeIIkHKvS
[代码]
https://github.com/yifan-h/CS-GNN
36.[AAAI 2020]Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
从拓扑角度测量和缓解图神经网络的过度平滑问题
[论文]
https://arxiv.org/abs/1909.03211
同学们是不是发现有些论文有代码，有些论文没有代码？学姐建议学概念读没代码的，然后再读有代码的，原因的话上周的文章有写，花几分钟看一下【学姐带你玩AI】公众号的——《图像识别深度学习研究方向没有导师带该怎么学习》
part3/最新款论文
37.[arXiv 2021]Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
同一枚硬币的两面：图卷积神经网络中的异质性和过度平滑
[论文]
https://arxiv.org/abs/2102.06462v2
38.[arXiv 2021]Graph Neural Networks Inspired by Classical Iterative Algorithms
受经典迭代算法启发的图神经网络
[论文]
https://arxiv.org/abs/2103.06064
39.[ICML 2021]Training Graph Neural Networks with 1000 Layers
训练 1000 层图神经网络
[论文]
https://arxiv.org/abs/2106.07476
[代码]
https://github.com/lightaime/deep_gcns_torch
40.[ICML 2021] Directional Graph Networks 方向图网络
[论文]
https://arxiv.org/abs/2010.02863
[代码]
https://github.com/Saro00/DGN
41.[ICLR 2021]On the Bottleneck of Graph Neural Networks and its Practical Implications
关于图神经网络的瓶颈及其实际意义
[论文]
https://openreview.net/forum?id=i80OPhOCVH2
[代码] https://github.com/tech-srl/bottleneck/
42.[ICLR 2021] Adaptive Universal Generalized PageRank Graph Neural Network
[论文]
https://openreview.net/forum?id=n6jl7fLxrP
[代码]
https://github.com/jianhao2016/GPRGNN
43.[ICLR 2021]Simple Spectral Graph Convolution
简单的谱图卷积
[论文]
https://openreview.net/forum?id=CYO5T-YjWZV
地址：https://github.com/mengliu1998/awesome-deep-gnn
因上求缘，果上努力~~~~ 作者：图神经网络，转载请注明原文链接：https://www.cnblogs.com/BlairGrowing/p/15704611.html
