arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.06218cs.LGcs.AIcs.SI
收藏

Graph Transformer Networks:学习元路径图以改进GNN

Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs

Korea University(高丽大学)

Seongjun Yun, Minbyul Jeong, Sungdong Yoo, Seunghun Lee, Sean S. Yi, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim

摘要:

图神经网络(GNN)由于其对图结构数据的强大表示能力,已被广泛应用于各个领域。尽管GNN取得了成功,但大多数现有的GNN都被设计为学习固定和同构图上的节点表示。当在错误指定的图或由各种类型的节点和边组成的异构图上学习表示时,这些限制尤其成问题。为了解决这一限制,我们提出了能够生成新的图结构的图Transformer网络(GTN),其排除了噪声连接并包括有用的连接(例如,元路径),同时以端到端的方式学习新图形上的有效节点表示。我们进一步提出了GTN的增强版本,快速图Transformer网络(FastGTN),提高了图变换的可扩展性。与GTN相比,FastGTN的速度快230倍,使用的内存少100倍,同时允许与GTN相同的图形转换。此外,我们扩展图变换的语义接近的节点,允许非本地操作超越元路径。在同构图和异构图上的大量实验表明,具有非局部操作的GTN和FastGTN实现了节点分类任务的最新性能。代码可在以下网址获得:https://github.com/seongjunyun/Graph_Transformer_Networks

英文摘要:

Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. To address this limitations, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which preclude noisy connections and include useful connections (e.g., meta-paths) for tasks, while learning effective node representations on the new graphs in an end-to-end fashion. We further propose enhanced version of GTNs, Fast Graph Transformer Networks (FastGTNs), that improve scalability of graph transformations. Compared to GTNs, FastGTNs are 230x faster and use 100x less memory while allowing the identical graph transformations as GTNs. In addition, we extend graph transformations to the semantic proximity of nodes allowing non-local operations beyond meta-paths. Extensive experiments on both homogeneous graphs and heterogeneous graphs show that GTNs and FastGTNs with non-local operations achieve the state-of-the-art performance for node classification tasks. The code is available: https://github.com/seongjunyun/Graph_Transformer_Networks

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑