Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 44, Issue 12, Pages 10270-10276Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3134200
Keywords
Sorting; Task analysis; Graph neural networks; Convolution; Aggregates; Nonhomogeneous media; Calibration; Graph neural networks; non-local aggregation; attention mechanism; disassortative graphs
Funding
- National Science Foundation [IIS-1908198, DBI-1922969]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available