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 2111.11523cs.LGcs.AI
收藏

用于图分类的可学习结构语义读出

Learnable Structural Semantic Readout for Graph Classification

University of Illinois at Urbana-Champaign (UIUC)(伊利诺伊大学厄巴纳-香槟分校 (UIUC));Pohang University of Science and Technology (POSTECH)(浦项科技大学 (POSTECH));Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院 (KAIST))

Dongha Lee, Su Kim, Seonghyeon Lee, Chanyoung Park, Hwanjo Yu

摘要:

随着深度学习在各个领域的巨大成功,图神经网络(GNN)也成为图分类的主要方法。通过简单地聚合所有节点(或节点簇)表示的全局读出操作的帮助,现有的GNN分类器获得输入图的图级表示,并使用该表示来预测其类标签。然而,这种全局聚合没有考虑每个节点的结构信息,这导致全局结构上的信息丢失。特别是,它通过对所有节点表示强制执行相同的分类器权重参数来限制区分能力;在实践中,每个节点表示都根据其结构语义对目标类做出不同的贡献。在这项工作中,我们提出了结构化语义读出(SSRead),总结节点表示在位置级别,这使得模型的位置特定的权重参数分类,以及有效地捕捉图形语义相关的全球结构。给定一个输入图,SSRead的目标是通过使用其节点和结构原型之间的语义对齐来识别结构上有意义的位置,结构原型对每个位置的原型特征进行编码。结构原型被优化以最小化所有训练图的对齐成本,而其他GNN参数被训练以预测类标签。我们的实验结果表明,SSRead显着提高了GNN分类器的分类性能和可解释性,同时与各种聚合函数,GNN架构和学习框架兼容。

英文摘要:

With the great success of deep learning in various domains, graph neural networks (GNNs) also become a dominant approach to graph classification. By the help of a global readout operation that simply aggregates all node (or node-cluster) representations, existing GNN classifiers obtain a graph-level representation of an input graph and predict its class label using the representation. However, such global aggregation does not consider the structural information of each node, which results in information loss on the global structure. Particularly, it limits the discrimination power by enforcing the same weight parameters of the classifier for all the node representations; in practice, each of them contributes to target classes differently depending on its structural semantic. In this work, we propose structural semantic readout (SSRead) to summarize the node representations at the position-level, which allows to model the position-specific weight parameters for classification as well as to effectively capture the graph semantic relevant to the global structure. Given an input graph, SSRead aims to identify structurally-meaningful positions by using the semantic alignment between its nodes and structural prototypes, which encode the prototypical features of each position. The structural prototypes are optimized to minimize the alignment cost for all training graphs, while the other GNN parameters are trained to predict the class labels. Our experimental results demonstrate that SSRead significantly improves the classification performance and interpretability of GNN classifiers while being compatible with a variety of aggregation functions, GNN architectures, and learning frameworks.

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。

↑