GraphiT: Encoding Graph Structure in Transformers

arxiv(2021)

引用 69|浏览116
暂无评分
摘要
We show that viewing graphs as sets of node features and incorporating structural and positional information into a transformer architecture is able to outperform representations learned with classical graph neural networks (GNNs). Our model, GraphiT, encodes such information by (i) leveraging relative positional encoding strategies in self-attention scores based on positive definite kernels on graphs, and (ii) enumerating and encoding local sub-structures such as paths of short length. We thoroughly evaluate these two ideas on many classification and regression tasks, demonstrating the effectiveness of each of them independently, as well as their combination. In addition to performing well on standard benchmarks, our model also admits natural visualization mechanisms for interpreting graph motifs explaining the predictions, making it a potentially strong candidate for scientific applications where interpretation is important. Code available at https://github.com/inria-thoth/GraphiT.
更多
查看译文
关键词
graphit structure,transformers
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络