.png){kind=icon}
返回
Rationalizing Graph Neural Networks with Data Augmentation
.png){kind=icon}
PRE
AI
DOI：10.1145/3638781.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph rationales are representative subgraph structures that best explain and support the graph neural network (GNN) predictions. Graph rationalization involves the joint identification of these subgraphs during GNN training, resulting in improved interpretability and generalization. GNN is widely used for node-level tasks such as paper classification and graph-level tasks such as molecular property prediction. However, on both levels, little attention has been given to GNN rationalization and the lack of training examples makes it difficult to identify the optimal graph rationales. In this work, we address the problem by proposing a unified data augmentation framework with two novel operations on environment subgraphs to rationalize GNN prediction. We define the environment subgraph as the remaining subgraph after rationale identification and separation. The framework efficiently performs rationale-environment separation in the representation space for a node's neighborhood graph or a graph's complete structure to avoid the high complexity of explicit graph decoding and encoding. We conduct experiments on 17 datasets spanning node classification, graph classification, and graph regression. Results demonstrate that our framework is effective and efficient in rationalizing and enhancing GNNs for different levels of tasks on graphs.
Keyword:
Graph neural network
node classification
graph property prediction
data augmentation
rationalization
期刊
IF:
4.8
论文数:
1.3K
被引数:
4.4K
机构
引用论文
分享收藏
分享收藏Biochemical Purification of a Mammalian Slit Protein as a Positive Regulator of Sensory Axon Elongation and Branching.png)
Cell
OAAI
CellIF0
OAAI分享收藏分享收藏
查看更多内容