14.2節 深い層を持つGNN
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning | Li et al | 2018b | arxiv | 1 |
| Spectral Graph Theory | Chung and Graham | 1997 | amazon | 2 |
| Graph Neural Networks Exponentially Lose Expressive Power for Node Classification | Oono and Suzuki | 2020 | arxiv | 3 |
| Representation Learning on Graphs with Jumping Knowledge Networks | Xu et al | 2018a | arxiv | 4 |
| DropEdge: Towards Deep Graph Convolutional Networks on Node Classification | Rong et al | 2020 | arxiv | 5 |
| PairNorm: Tackling Oversmoothing in GNNs | Zhao and Akoglu | 2019 | arxiv | 6 |
14.3節 自己教師あり学習
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| Rethinking the Inception Architecture for Computer Vision | Szegedy et al | 2016 | arxiv | 1 |
| Very Deep Convolutional Networks for Large-Scale Image Recognition | Simonyan and Zisserman | 2014 | arxiv | 2 |
| Language Models are Unsupervised Multitask Learners | Radford et al | 2019 | リンク | 3 |
| BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | Devlin et al | 2018 | arxiv | 4 |
| Self-supervised Learning on Graphs: Deep Insights and New Direction | Jin et al | 2020c | arxiv | 5 |
| Pre-Training graph neural networks for generic structural feature extraction | Hu et al | 2019 | arxiv | 6 |
| GPT-GNN: Generative Pre-Training of Graph Neural Networks | Hu et al | 2020a | arxiv | 7 |
| Self-Supervised Graph Representation Learning via Global Context Prediction | Peng et al | 2020 | arxiv | 8 |
| A fast and high quality multilevel scheme for partitioning irregular graphs | Karypis and Kumar | 1998 | リンク | 9 |
| Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels | Sun et al | 2019c | arxiv | 10 |
| When Does Self-Supervision Help Graph Convolutional Networks? | You et al | 2020 | arxiv | 11 |
| Semi-supervised learning using Gaussian fields and harmonic functions | Zhu et al | 2003 | リンク | 12 |
| Iterative Classification in Relational Data | Neville and Jensen | 2000 | リンク | 13 |
| Deep Self-Learning From Noisy Labels | Han et al | 2019 | arxiv | 14 |
| Strategies for Pre-training Graph Neural Networks | Hu et al | 2020b | arxiv | 15 |
| InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization | Sun et al | 2019b | arxiv | 16 |
14.4節 グラフニューラルネットワークの表現力
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| How Powerful are Graph Neural Networks? | Xu et al | 2019d | arxiv | 1 |
| The reduction of a graph to canonical form and the algebra which appears therein | Weisfeiler and Lehman | 1968 | 2 | |
| Computers and Intractability: A Guide to the Theory of Np-Completeness | Garey and Johnson | 1979 | amazon | 3 |
| Graph Isomorphism in Quasipolynomial Time | Babai | 2016 | arxiv | 4 |
| An Optimal Lower Bound on the Number of Variables for Graph Identification | Cai et al | 1992 | 5 | |
| Inductive Representation Learning on Large Graphs | Hamilton et al | 2017a | arxiv | 6 |
14.6節 参考文献
| タイトル | 著者名 | 年 | リンク | 登場順 |
|---|---|---|---|---|
| GNNExplainer: Generating Explanations for Graph Neural Networks | Ying et al | 2019 | arxiv | 1 |
| XGNN: Towards Model-Level Explanations of Graph Neural Networks | Yuan et al | 2020 | arxiv | 2 |
| Investigating and Mitigating Degree-Related Biases in Graph Convolutional Networks | Tang et al | 2020 | arxiv | 3 |
| Hyperbolic Graph Convolutional Neural Networks | Chami et al | 2019 | arxiv | 4 |
| Hyperbolic Graph Neural Networks | Liu et al | 2019a | arxiv | 5 |