LGAug 7, 2021

Global Self-Attention as a Replacement for Graph Convolution

arXiv:2108.03348v3186 citations
AI Analysis

This work addresses graph learning for researchers and practitioners by introducing a novel architecture that challenges the necessity of convolutional inductive biases, showing incremental improvements over existing methods.

The authors tackled the problem of graph learning by proposing Edge-augmented Graph Transformer (EGT), which uses global self-attention instead of graph convolution, and it outperformed Convolutional/Message-Passing Graph Neural Networks, setting a new state-of-the-art on the OGB-LSC PCQM4Mv2 dataset with 3.8 million molecular graphs.

We propose an extension to the transformer neural network architecture for general-purpose graph learning by adding a dedicated pathway for pairwise structural information, called edge channels. The resultant framework - which we call Edge-augmented Graph Transformer (EGT) - can directly accept, process and output structural information of arbitrary form, which is important for effective learning on graph-structured data. Our model exclusively uses global self-attention as an aggregation mechanism rather than static localized convolutional aggregation. This allows for unconstrained long-range dynamic interactions between nodes. Moreover, the edge channels allow the structural information to evolve from layer to layer, and prediction tasks on edges/links can be performed directly from the output embeddings of these channels. We verify the performance of EGT in a wide range of graph-learning experiments on benchmark datasets, in which it outperforms Convolutional/Message-Passing Graph Neural Networks. EGT sets a new state-of-the-art for the quantum-chemical regression task on the OGB-LSC PCQM4Mv2 dataset containing 3.8 million molecular graphs. Our findings indicate that global self-attention based aggregation can serve as a flexible, adaptive and effective replacement of graph convolution for general-purpose graph learning. Therefore, convolutional local neighborhood aggregation is not an essential inductive bias.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes