值得借鉴的论文语句
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs CVPR
- We applied our approach to point cloud classification in a novel way, setting a new state of the art performance on Sydney dataset. Furthermore, we have outperformed other deep learning-based approaches on graph classification dataset NCI1.
- On the other hand, in many other tasks the data naturally lie on irregular or generally non-Euclidean domains, which can be structured as graphs in many cases.
- it is meaningful to consider a hierarchical CNN-like architecture for processing it.
- However, a generalization of CNNs from grids to general graphs is not straightforward and has recently become a topic of increased interest. We identify that the current formulations of graph convolution do not exploit edge labels, which results in an overly homogeneous view of local graph neighborhoods, with an effect similar to enforcing rotational invariance of filters in regular convolutions on images.
- Automated Machine Learning on Graphs: A Survey
前人工作
收到启发的语句
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs CVPR
- In feature work we would like to handle meshes as graphs instead of point clouds. Moreover, we plan to address the currently higher level of GPU memory consumption in case of large graphs with continuous edge labels, for example by randomized clustering, which could also serve as additional regularization through data augmentation.
