Self-supervised Training of Graph Convolutional Networks
动机： GCNs需要邻接矩阵作为输入来定义这些非网格数据之间的关系，这就导致所有的数据，包括训练数据、验证数据和测试数据，通常只形成一个用于训练的图结构数据。此外，邻接矩阵通常是预定义的且平稳的，这使得数据增强策略不能在构造的图结构数据上使用来增加训练数据的数量。为了进一步提高有限训练数据下的学习能力和模型性能 贡献： 提出从输入图结构数据本身中挖掘可用信息，以提高基于图的模型的学习识别能力和性能
相关文章
- 1. Modification of Graph Convolutional Networks in PyTorch
- 2. HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs--论文笔记
- 3. Applications of Graph Neural Networks
- 4. MuchGCN：Multi-Channel Graph Convolutional Networks
- 5. Emotion Recognition Using Graph Convolutional Networks
- 6. Adaptive Graph Convolutional Neural Networks
- 7. 《Large-Scale Learnable Graph Convolutional Networks》
- 8. Semi-Supervised Classification With Graph Convolutional Networks
- 9. STRATEGIES FOR PRE-TRAINING GRAPH NEURAL NETWORKS
- 10. Strategies For Pre-Training Graph Neural Networks
- 更多相关文章...
- • XSLT
- • XSLT
- • JDK13 GA发布：5大特性解读
- • 使用Rxjava计算圆周率
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. Modification of Graph Convolutional Networks in PyTorch
- 2. HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs--论文笔记
- 3. Applications of Graph Neural Networks
- 4. MuchGCN：Multi-Channel Graph Convolutional Networks
- 5. Emotion Recognition Using Graph Convolutional Networks
- 6. Adaptive Graph Convolutional Neural Networks
- 7. 《Large-Scale Learnable Graph Convolutional Networks》
- 8. Semi-Supervised Classification With Graph Convolutional Networks
- 9. STRATEGIES FOR PRE-TRAINING GRAPH NEURAL NETWORKS
- 10. Strategies For Pre-Training Graph Neural Networks