Graphs are a highly expressive data structure, but it is often difficult for humans to find patterns from a complex graph. Hence, generating human-interpretable sequences from graphs have gained interest, called graph2seq learning. It is expected that the compositionality in a graph can be associated to the compositionality in the output sequence in many graph2seq tasks. Therefore, applying compositionality-aware GNN architecture would improve the model performance. In this study, we adopt the multi-level attention pooling (MLAP) architecture, that can aggregate graph representations from multiple levels of information localities. As a real-world example, we take up the extreme source code summarization task, where a model estimate the name of a program function from its source code. We demonstrate that the model having the MLAP architecture outperform the previous state-of-the-art model with more than seven times fewer parameters than it.
翻译:图表是一个高度清晰的数据结构, 但人类通常很难从复杂的图形中找到模式。 因此, 从图形中生成人类解释序列, 被称作图形2seq 学习。 图形中的构成性预计将与许多图形2seq 任务中产出序列的构成性相关。 因此, 应用配置性- 了解 GNN 架构将改善模型性能 。 在此研究中, 我们采用了多层次的集中关注结构, 它可以汇总多个层次的信息位置的图形表达方式 。 作为现实世界的一个例子, 我们采用极端源代码对齐任务, 模型从源代码中估算程序函数的名称 。 我们证明, 具有 MLAP 架构的模型比先前的状态艺术模型的参数要短七倍以上 。