GNN归纳

GNN概念

GNN全称Graph Neural Network（图神经网络），它是一种直接在图结构上运行的神经网络。

更多关于GNN的介绍：

• Graph Neural Network Review
• 图神经网络（Graph neural networks）综述

GNN应用

计算机视觉

• 视觉问答任务：Li L , Gan Z , Cheng Y , et al. Relation-Aware Graph Attention Network for Visual Question Answering[J]. 2019.
• Kampffmeyer M, Chen Y, Liang X, et al. Rethinking knowledge graph propagation for zero-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 11487-11496.
• Kim J , Kim T , Kim S , et al. Edge-labeling Graph Neural Network for Few-shot Learning[J]. 2019.

3D视觉

• Wang L, Huang Y, Hou Y, et al. Graph Attention Convolution for Point Cloud Semantic Segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 10296-10305.
• Zhao L, Peng X, Tian Y, et al. Semantic Graph Convolutional Networks for 3D Human Pose Regression[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 3425-3435.

自然语言处理

• 在Ding M , Zhou C , Chen Q , et al. Cognitive Graph for Multi-Hop Reading Comprehension at Scale[J]. 2019.一文中，作者基于 BERT 和 GNN 的实现可有效处理 HotPotQA 数据集中有关多跳阅读问题的数百万份文档，在排行榜上的联合 F1 得分为 34.9，而第二名的得分只有 23.6

知识图谱

由于知识图谱本身就是一种图数据，因此知识图谱 +GNN 的组合自然就成了解决各类知识图谱问题的新手段。

• 用 GNN 对知识图谱进行建模:Nathani D , Chauhan J , Sharma C , et al. Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs[J]. 2019.
• 实体对齐:Cao Y , Liu Z , Li C , et al. Multi-Channel Graph Neural Network for Entity Alignment[J]. 2019.
• 业务图谱:Park N , Kan A , Dong X L , et al. Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks[J]. 2019.

推荐系统

• 论证多层 GNN 所带来的“Deep”与“High order”效益对推荐质量的有效提升:Wang X , He X , Wang M , et al. Neural Graph Collaborative Filtering[J]. 2019.
• 结合知识图谱和GNN进行推荐建模：
  • Wang X , He X , Cao Y , et al. KGAT: Knowledge Graph Attention Network for Recommendation[J]. 2019.
  • Song W , Xiao Z , Wang Y , et al. Session-based Social Recommendation via Dynamic Graph Attention Networks[J]. 2019.

反欺诈

• 运用 GNN 对支付宝欺诈用户进行识别检测: Liu Z, Chen C, Yang X, et al. Heterogeneous graph neural networks for malicious account detection[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ACM, 2018: 2077-2085.
• 运用 GNN 对咸鱼上的评论进行欺诈识别: Li A, Qin Z, Liu R, et al. Spam Review Detection with Graph Convolutional Networks[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2019: 2703-2711.

GNN 开源项目

• 阿里妈妈工业级图深度学习框架 Euler：https://github.com/alibaba/euler
• Pytorch Geometric: https://github.com/rusty1s/pytorch_geometric
• 支持亿级规模的著名图学习框架 DGL: https://github.com/dmlc/dgl
• 论文归纳：
  • https://github.com/naganandy/graph-based-deep-learning-literature
  • https://github.com/DeepGraphLearning/LiteratureDL4Graph

参考：

1. 人工智能的下一个拐点：图神经网络迎来快速爆发期
2. Graph Neural Network Review
3. 图神经网络（Graph neural networks）综述

GNN归纳

原文：https://www.cnblogs.com/lokvahkoor/p/12203072.html