.png){kind=icon}
返回
Graph representation learning via simple jumping knowledge networks
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-021-02889-z.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent graph neural networks for graph representation learning depend on a neighborhood aggregation process. Several works focus on simplifying the neighborhood aggregation process and model structures. However, as the depth of the models increases, the simplified models will encounter oversmoothing, resulting in a decrease in model performance. Several works leverage sophisticated learnable neighborhood aggregation algorithms to learn more accurate graph representations. However, the high computational cost limits the depth of these models and the ability to tackle large graphs. In this paper, we propose simple jumping knowledge networks (SJK-Nets), which first leverage a simple no-learning method to complete the neighborhood aggregation process, and then utilize a jumping architecture to combine the different neighborhood ranges of each node to achieve a better structure-aware representation. Under such circumstances, first, we use a simple neighborhood aggregation algorithm to reduce computational complexity of the model. Then, we aggregate the features of high-order neighboring nodes to learn more informative node feature representations. Finally, by combining the above methods, the oversmoothing problem of the deep graph neural networks is alleviated. Our experimental evaluation demonstrates that SJK-Nets achieve or match state-of-the-art results in node classification tasks, text classification tasks, and community prediction tasks. Moreover, since SJK-Nets' neighborhood aggregation is a no-learning process, SJK-Nets are successfully extended to node clustering tasks.
Keyword:
Graph neural networks
Graph representation learning
Neighborhood aggregation
Simple jumping knowledge networks
No-learning
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
A prospective study of surgical margin status in oral squamous cell carcinoma: A preliminary report
PREAI
分享收藏
Accelerometer-assessed sedentary work, leisure time and cardio-metabolic biomarkers during one year: Effectiveness of a cluster randomized controlled trial in parents with a sedentary occupation and young children.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容