Graph Representation

最新推荐文章于 2024-08-08 17:45:51 发布

_森罗万象

最新推荐文章于 2024-08-08 17:45:51 发布

阅读量127

点赞数

分类专栏：读书笔记文章标签：深度学习神经网络人工智能

本文链接：https://blog.csdn.net/weixin_52812620/article/details/128978059

版权

33 篇文章 5 订阅

订阅专栏

reading notes of《Molecular Graph Representation Learning and Generation for Drug Discovery》

The typical GNN architecture that relies on local aggregation operations can often miss higher-order graph information. In the context of molecular problems, locality can prove myopic, as longer-range dependencies are important for many biological prediction targets. To remedy this, we propose Path-Augmented Graph Transformer Networks (PAGTN) that are explicitly built on longer-range dependencies in graph-structured data.
For large enough graphs, GCNs may fail to capture these long-range dependencies entirely. Our PAGTN model can more easily capture these dependencies because every node attends to all other nodes in the graph.
GCN models necessitate several layers to propagate information and learn these substructures. The advantage of our model is that this interaction can be learned within a single layer.