期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 44, 期 12, 页码 10270-10276出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3134200
关键词
Sorting; Task analysis; Graph neural networks; Convolution; Aggregates; Nonhomogeneous media; Calibration; Graph neural networks; non-local aggregation; attention mechanism; disassortative graphs
资金
- National Science Foundation [IIS-1908198, DBI-1922969]
In this work, a simple yet effective non-local aggregation framework with efficient attention-guided sorting is proposed for tasks on disassortative graphs. Thorough experiments show that the proposed method significantly outperforms previous state-of-the-art methods in terms of both model performance and efficiency on various benchmark datasets.
Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs. However, tasks on disassortative graphs usually require non-local aggregation. In addition, we find that local aggregation is even harmful for some disassortative graphs. In this work, we propose a simple yet effective non-local aggregation framework with an efficient attention-guided sorting for GNNs. Based on it, we develop various non-local GNNs. We perform thorough experiments to analyze disassortative graph datasets and evaluate our non-local GNNs. Experimental results demonstrate that our non-local GNNs significantly outperform previous state-of-the-art methods on seven benchmark datasets of disassortative graphs, in terms of both model performance and efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据