Lasagne: A Multi-Layer Graph Convolutional Network Framework via Node-Aware Deep Architecture

doi:10.1109/TKDE.2021.3103984

Lasagne: A Multi-Layer Graph Convolutional Network Framework via Node-Aware Deep Architecture

2021-01-01

13

PRE

AI

DOI：10.1109/TKDE.2021.3103984

Original

Original request for help

Save

Abstract

En 中文

Graph convolutional networks (GCNs) have been successfully applied in many different real-world tasks. However, most of the existing methods are based on shallow GCN, because multiple layers involve long-distance neighborhood information but lead to the over-smoothing problem. Actually, a similar challenge exists in the depth limitation for primitive convolutional neural networks (CNNs). As the multi-layer architecture can increase the representation ability of GCN, we study and learn from the recent progress in CNN and propose Lasagne, a novel multi-layer GCN framework, empowered by node-aware layer aggregators and factorization-based layer interactions to overcome the over-smoothing problem and realize the full potentials of the GCN model. We analyze how the node locality affects the information propagation in GCN and propose a novel node aggregation mechanism in an adaptive manner. We further demystify Lasagne from a mutual information view and evaluate it on both real-world benchmark data sets and large-scale industrial production data sets. Lasagne shows strong empirical performance on the semi-supervised node classification task and outperforms the state-of-the-art methods without considering the node locality.

Keywords:

Deep learning

graph convolutional neural network

over-smoothing

information loss

node locality

Lasagne: A Multi-Layer Graph Convolutional Network Framework via Node-Aware Deep Architecture

Abstract

AI Summary

Journal

Organization