ML Anthology

AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism

Jingjia Huang, Zhangheng Li, Nannan Li, Shan Liu, Ge Li
ICCV 2019
doi:10.1109/ICCV.2019.00658 /iccv/2019/huang2019iccv-attpool/

Abstract

Graph convolutional networks (GCNs) are potentially short of the ability to learn hierarchical representation for graph embedding, which holds them back in the graph classification task. Here, we propose AttPool, which is a novel graph pooling module based on attention mechanism, to remedy the problem. It is able to select nodes that are significant for graph representation adaptively, and generate hierarchical features via aggregating the attention-weighted information in nodes. Additionally, we devise a hierarchical prediction architecture to sufficiently leverage the hierarchical representation and facilitate the model learning. The AttPool module together with the entire training structure can be integrated into existing GCNs, and is trained in an end-to-end fashion conveniently. The experimental results on several graph-classification benchmark datasets with various scales demonstrate the effectiveness of our method.

PDF ICCV Semantic Scholar

Cite

Text

Huang et al. "AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00658

Markdown

[Huang et al. "AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/huang2019iccv-attpool/) doi:10.1109/ICCV.2019.00658

BibTeX

@inproceedings{huang2019iccv-attpool,
  title     = {{AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism}},
  author    = {Huang, Jingjia and Li, Zhangheng and Li, Nannan and Liu, Shan and Li, Ge},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00658},
  url       = {https://mlanthology.org/iccv/2019/huang2019iccv-attpool/}
}