How powerful are graph neural networks?
How powerful are graph neural networks? ICLR 2019 背景 1.图神经网络 图神经网络及其应用 2.Weisfeiler-Lehman test 同构：如果图G1和G2的顶点和边的数目相同，并且边的连通性相同，则这两个图可以说是同构的，如下图所示。也可以认为G2的顶点是从G1的顶点映射而来的。这是一个具有挑战性的问题：目前还没有已知的多项式时间算法。图
相关文章
- 1. HOW POWERFUL ARE GRAPH NEURAL NETWORKS?
- 2. How Powerful are Graph Neural Networks？ GIN 图同构网络 ICLR 2019 论文详解
- 3. How to Implement Neural Networks with TensorFlow
- 4. CS224W-08-Graph Neural Networks
- 5. How convolution neural networks work
- 6. How transferable are features in deep neural networks?
- 7. How are neural networks related to Fourier transforms
- 8. Applications of Graph Neural Networks
- 9. Graph Neural Networks for Social Recommendation
- 10. GMNN: Graph Markov Neural Networks
- 更多相关文章...
- • ASP Line 属性 - ASP 教程
- • ASP WriteBlankLines 方法 - ASP 教程
- • Kotlin学习（二）基本类型
- • Java 8 Stream 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. HOW POWERFUL ARE GRAPH NEURAL NETWORKS?
- 2. How Powerful are Graph Neural Networks？ GIN 图同构网络 ICLR 2019 论文详解
- 3. How to Implement Neural Networks with TensorFlow
- 4. CS224W-08-Graph Neural Networks
- 5. How convolution neural networks work
- 6. How transferable are features in deep neural networks?
- 7. How are neural networks related to Fourier transforms
- 8. Applications of Graph Neural Networks
- 9. Graph Neural Networks for Social Recommendation
- 10. GMNN: Graph Markov Neural Networks