FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping
arXiv:2110.11464
Abstract
While Graph Neural Networks have gained popularity in multiple domains, graph-structured input remains a major challenge due to (a) over-smoothing, (b) noisy neighbours (heterophily), and (c) the suspended animation problem. To address all these problems simultaneously, we propose a novel graph neural network FDGATII, inspired by attention mechanism's ability to focus on selective information supplemented with two feature preserving mechanisms. FDGATII combines Initial Residuals and Identity Mapping with the more expressive dynamic self-attention to handle noise prevalent from the neighbourhoods in heterophilic data sets. By using sparse dynamic attention, FDGATII is inherently parallelizable in design, whist efficient in operation; thus theoretically able to scale to arbitrary graphs with ease. Our approach has been extensively evaluated on 7 datasets. We show that FDGATII outperforms GAT and GCN based benchmarks in accuracy and performance on fully supervised tasks, obtaining state-of-the-art results on Chameleon and Cornell datasets with zero domain-specific graph pre-processing, and demonstrate its versatility and fairness.
arXiv comment10 pages, 4 figures. Reworded section 2.1 with references. Reworded argument in section 2.3 para 2
References in corpus (10)
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Geometric deep learning: going beyond Euclidean data
- Simplifying Graph Convolutional Networks
- Simple and Deep Graph Convolutional Networks
- Geom-GCN: Geometric Graph Convolutional Networks
- On the Bottleneck of Graph Neural Networks and its Practical Implications
- How Attentive are Graph Attention Networks?
- Non-Local Graph Neural Networks
- Improving Graph Neural Networks with Simple Architecture Design