DeeperGCN: Training Deeper GCNs with Generalized Aggregation Functions

Guohao Li, Chenxin Xiong, Ali Thabet, Bernard Ghanem

Keywords: Graph Neural Networks, Graph Representation Learning

Abstract: Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs. Recent works developed frameworks to train deep GCNs. Such works show impressive results in tasks like point cloud classification and segmentation, and protein interaction prediction. In this work, we study the performance of such deep models in large scale graph datasets from the Open Graph Benchmark (OGB). In particular, we look at the effect of adequately choosing an aggregation function, and its effect on final performance. Common choices of aggregation are mean, max, and sum. It has shown that GCNs are sensitive to such aggregations when applied to different datasets. We further validate this point and propose to alleviate it by introducing a novel Generalized Aggregation Function. Our new aggregation not only covers all commonly used ones, but also can be tuned to learn customized functions for different tasks. Our generalized aggregation is fully differentiable, and thus its parameters can be learned in an end-to-end fashion. We add our generalized aggregation into a deep GCN framework and show it achieves state-of-the-art results in six benchmarks from OGB.

One-sentence Summary: This paper proposes DeeperGCN that is capable of successfully and reliably training very deep GCNs. We define differentiable generalized aggregation functions to unify different message aggregation operations (e.g. mean, max and sum).

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=lkdw4N2bzx