DRGCN: Dynamic Evolving Initial Residual for Deep Graph Convolutional Networks

TL;DR

This paper introduces DRGCN, a novel deep graph convolutional network with dynamic and evolving residual mechanisms that effectively mitigate over-smoothing and outperform existing methods on multiple benchmarks, including large-scale datasets.

Contribution

The paper proposes DRGCN, which adaptively applies residuals through dynamic and evolving blocks, addressing dataset sensitivity and over-smoothing in deep GCNs.

Findings

DRGCN outperforms state-of-the-art methods on benchmark datasets.

The model effectively alleviates over-smoothing in deep GCNs.

A scalable mini-batch version of DRGCN achieves new SOTA on large-scale data.

Abstract

Graph convolutional networks (GCNs) have been proved to be very practical to handle various graph-related tasks. It has attracted considerable research interest to study deep GCNs, due to their potential superior performance compared with shallow ones. However, simply increasing network depth will, on the contrary, hurt the performance due to the over-smoothing problem. Adding residual connection is proved to be effective for learning deep convolutional neural networks (deep CNNs), it is not trivial when applied to deep GCNs. Recent works proposed an initial residual mechanism that did alleviate the over-smoothing problem in deep GCNs. However, according to our study, their algorithms are quite sensitive to different datasets. In their setting, the personalization (dynamic) and correlation (evolving) of how residual applies are ignored. To this end, we propose a novel model called Dynamic evolving initial Residual Graph Convolutional Network (DRGCN). Firstly, we use a dynamic block for each node to adaptively fetch information from the initial representation. Secondly, we use an evolving block to model the residual evolving pattern between layers. Our experimental results show that our model effectively relieves the problem of over-smoothing in deep GCNs and outperforms the state-of-the-art (SOTA) methods on various benchmark datasets. Moreover, we develop a mini-batch version of DRGCN which can be applied to large-scale data. Coupling with several fair training techniques, our model reaches new SOTA results on the large-scale ogbn-arxiv dataset of Open Graph Benchmark (OGB). Our reproducible code is available on GitHub.