Towards Deeper Graph Neural Networks
问题： 一层的GCN layer只考虑直接邻域，加深模型层数可获得更大的感受野receptive fields，但性能却会变坏。 以前认为是over-smoothing问题导致的。 本文 增加层性能变坏是因为GCN模型里两个关键部分——representation transformation和propagation——的纠缠导致的。 分离这两个部分可以解决该问题。 模型： 进行特征变换， 堆叠层
相关文章
- 1. 图神经网络论文阅读(二十) Towards Deeper Graph Neural Networks
- 2. Applications of Graph Neural Networks
- 3. Inceptionism: Going Deeper into Neural Networks[译]
- 4. GMNN: Graph Markov Neural Networks
- 5. CS224W-08-Graph Neural Networks
- 6. Adaptive Graph Convolutional Neural Networks
- 7. 笔记《Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels》-NeurIPS 2019
- 8. Few-shot Learning with Graph Neural Networks
- 9. Few-Shot Learning with Graph Neural Networks
- 10. Overlapping Community Detection with Graph Neural Networks
- 更多相关文章...
- • Git 标签 - Git 教程
- • Git 查看提交历史 - Git 教程
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 图神经网络论文阅读(二十) Towards Deeper Graph Neural Networks
- 2. Applications of Graph Neural Networks
- 3. Inceptionism: Going Deeper into Neural Networks[译]
- 4. GMNN: Graph Markov Neural Networks
- 5. CS224W-08-Graph Neural Networks
- 6. Adaptive Graph Convolutional Neural Networks
- 7. 笔记《Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels》-NeurIPS 2019
- 8. Few-shot Learning with Graph Neural Networks
- 9. Few-Shot Learning with Graph Neural Networks
- 10. Overlapping Community Detection with Graph Neural Networks