2020/7/9，第一次更新，本文將總結筆者的研究方向一"多組學智能醫療"的子方向"網絡生物學與人工智能"的分支——圖神經網絡（Graph Neural Networks, GNNs）方向學習過程中發現的優質資源，包括國自然、paper和應用方向、codes、開源框架、國際會議、期刊等。其中的部分文章將會新開辟文章分析。

一、目錄

1 論文

1.1 綜述

• Zhang Z, Cui P, Zhu W. Deep learning on graphs: A survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2020.
• Bronstein M M, Bruna J, LeCun Y, et al. Geometric deep learning: going beyond euclidean data[J]. IEEE Signal Processing Magazine, 2017, 34(4): 18-42.
• Wu Z, Pan S, Chen F, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020.
• Hamilton W L, Ying R, Leskovec J. Representation learning on graphs: Methods and applications[J]. arXiv preprint arXiv:1709.05584, 2017.

1.2 圖神經網絡架構

• GGNN: Gated Graph Neural Networks (Li et al., 2015).
• RGCN: Relational Graph Convolutional Networks (Schlichtkrull et al., 2017).
• RGAT: Relational Graph Attention Networks (Veli?kovi? et al., 2018).
• RGIN: Relational Graph Isomorphism Networks (Xu et al., 2019).
• GNN-Edge-MLP: Graph Neural Network with Edge MLPs - a variant of RGCN in which messages on edges are computed using full MLPs, not just a single layer applied to the source state.
• RGDCN: Relational Graph Dynamic Convolution Networks - a new variant of RGCN in which the weights of convolutional layers are dynamically computed.
• GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation - a new extension of RGCN with FiLM layers.

1.3 GNN表征學習

• Hu W, Liu B, Gomes J, et al. Strategies for Pre-training Graph Neural Networks[C]. ICLR. 2020.

1.4 應用

1.4.1 視覺與自然語言（VQA）

• Narasimhan M, Lazebnik S, Schwing A. Out of the box: Reasoning with graph convolution nets for factual visual question answering[C]//NeurIPS. 2018: 2654-2665.
• Norcliffe-Brown W, Vafeias S, Parisot S. Learning conditioned graph structures for interpretable visual question answering[C]//NeurIPS. 2018: 8334-8343.
• Zhou Y, Ji R, Sun X, et al. Plenty Is Plague: Fine-Grained Learning for Visual Question Answering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.

1.4.2 醫療健康和生物化學（高通量組學）

• Shang J, Xiao C, Ma T, et al. Gamenet: Graph augmented memory networks for recommending medication combination[C]//AAAI. 2019, 33: 1126-1133.
• Yu E Y, Wang Y P, Fu Y, et al. Identifying critical nodes in complex networks via graph convolutional networks[J]. Knowledge-Based Systems, 2020: 105893.
• Zitnik M, Leskovec J. Predicting multicellular function through multi-layer tissue networks[J]. Bioinformatics, 2017, 33(14): i190-i198.
• Chereda H, Bleckmann A, Kramer F, et al. Utilizing Molecular Network Information via Graph Convolutional Neural Networks to Predict Metastatic Event in Breast Cancer[C]//GMDS. 2019: 181-186.
• Wang C, Guo J, Zhao N, et al. A Cancer Survival Prediction Method Based on Graph Convolutional Network[J]. IEEE Transactions on NanoBioscience, 2019, 19(1): 117-126.
• Zhang J, Hu X, Jiang Z, et al. Predicting Disease-related RNA Associations based on Graph Convolutional Attention Network[C]//BIBM. IEEE, 2019: 177-182.
• Pan X, Shen H B. Inferring disease-associated microRNAs using semi-supervised multi-label graph convolutional networks[J]. Iscience, 2019, 20: 265-277.
• Wang M, Wang H, Zheng H, et al. A knowledge-driven network-based analytical framework for the identification of rumen metabolites[J]. IEEE Transactions on NanoBioscience, 2020.
• Liu H, Guan J, Li H, et al. Predicting the Disease Genes of Multiple Sclerosis Based on Network Representation Learning[J]. Frontiers in Genetics, 2020, 11.
• Dai H, Li L, Zeng T, et al. Cell-specific network constructed by single-cell RNA sequencing data[J]. Nucleic acids research, 2019, 47(11): e62-e62.
• Liu X, Chang X, Leng S, et al. Detection for disease tipping points by landscape dynamic network biomarkers[J]. National Science Review, 2019, 6(4): 775-785.
• Yu X, Zeng T, Wang X, et al. Unravelling personalized dysfunctional gene network of complex diseases based on differential network model[J]. Journal of translational medicine, 2015, 13(1): 189.
• Moon K R, Stanley III J S, Burkhardt D, et al. Manifold learning-based methods for analyzing single-cell RNA-sequencing data[J]. Current Opinion in Systems Biology, 2018, 7: 36-46.
• Rhee S, Seo S, Kim S. Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification[J]. arXiv preprint arXiv:1711.05859, 2017.

2 開源框架

• (斯坦福大學,復雜網絡, python2.7+)SNAP：A General-Purpose Network Analysis and Graph-Mining Library
• (紐約大學, GNN, python3.5+, PyTorch 1.2.0+, TensorFlow2.1.0+)DEEP GRAPH LIBRARY(DGL): TOWARDS EFFICIENT AND SCALABLE DEEP LEARNING ON GRAPHS
• (DeepMind, GNN, python3.4+,TensorFlow2.1.0+) Graph Nets
• (多特蒙德大學, GNN,PyTorch 1.5.0+) Pytorch Geometric: FAST GRAPH REPRESENTATION LEARNING WITH PYTORCH GEOMETRIC
• (微軟, GNN, Python 3.6, TensorFlow 1.13.1/ 2.0+)TF Graph Neural Network, Graph Neural Networks in TF2
• (阿里巴巴, GNN, Python 3.6, Tensorflow==1.12.0)AliGraph: a comprehensive graph neural network platform