Lasagne: A Multi-Layer Graph Convolutional Network Framework via Node-aware Deep Architecture
Metadata only
Date
2022Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
In this paper, we propose Lasagne, a novel multilayer graph convolutional network (GCN) framework to overcome the over-smoothing problem and realize the full potentials of deep GCNs. We analyze how node localities affect the information propagation in GCN, propose an adaptive novel node aggregation mechanism and further demystify from a mutual information view. Evaluation results on both real-world benchmark data sets and large-scale industrial production data sets show Lasagne significantly outperforms the state-of-theart methods without considering the node locality. Show more
Publication status
publishedExternal links
Book title
2022 IEEE 38th International Conference on Data Engineering (ICDE)Pages / Article No.
Publisher
IEEEEvent
More
Show all metadata
ETH Bibliography
yes
Altmetrics