GNN概念
GNN全稱Graph Neural Network(圖神經網絡),它是一種直接在圖結構上運行的神經網絡。
更多關於GNN的介紹:
GNN應用
計算機視覺
- 視覺問答任務: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視覺
- 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.
自然語言處理
- 在Ding M , Zhou C , Chen Q , et al. Cognitive Graph for Multi-Hop Reading Comprehension at Scale[J]. 2019.一文中,作者基於 BERT 和 GNN 的實現可有效處理 HotPotQA 數據集中有關多跳閱讀問題的數百萬份文檔,在排行榜上的聯合 F1 得分為 34.9,而第二名的得分只有 23.6
知識圖譜
由於知識圖譜本身就是一種圖數據,因此知識圖譜 +GNN 的組合自然就成了解決各類知識圖譜問題的新手段。
- 用 GNN 對知識圖譜進行建模: Nathani D , Chauhan J , Sharma C , et al. Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs[J]. 2019.
- 實體對齊: Cao Y , Liu Z , Li C , et al. Multi-Channel Graph Neural Network for Entity Alignment[J]. 2019.
- 業務圖譜: Park N , Kan A , Dong X L , et al. Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks[J]. 2019.
推薦系統
- 論證多層 GNN 所帶來的“Deep”與“High order”效益對推薦質量的有效提升: Wang X , He X , Wang M , et al. Neural Graph Collaborative Filtering[J]. 2019.
- 結合知識圖譜和GNN進行推薦建模:
反欺詐
- 運用 GNN 對支付寶欺詐用戶進行識別檢測: 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.
- 運用 GNN 對咸魚上的評論進行欺詐識別: 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 開源項目
- 阿里媽媽工業級圖深度學習框架 Euler:https://github.com/alibaba/euler
- Pytorch Geometric: https://github.com/rusty1s/pytorch_geometric
- 支持億級規模的著名圖學習框架 DGL: https://github.com/dmlc/dgl
- 論文歸納:
參考: