arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.12113cs.LGcs.SE
收藏

HEAT:超边缘注意力网络

HEAT: Hyperedge Attention Networks

University of Cambridge(剑桥大学);Microsoft Research(微软研究院);Google Research(谷歌研究院)

Dobrik Georgiev, Marc Brockschmidt, Miltiadis Allamanis

摘要:

从结构化数据中学习是机器学习的核心任务。通常,这样的数据被表示为图,其通常仅考虑节点对之间的(类型化的)二进制关系。这对于许多具有高度结构化数据的领域来说是一个实质性的限制。一个重要的领域是源代码,其中基于超图的表示可以更好地捕捉代码的语义丰富和结构化的本质。在这项工作中,我们提出了HEAT,一个能够表示类型和合格超图的神经模型,其中每个超边明确限定参与节点的贡献。它可以被看作是消息传递神经网络和Transformers的推广。我们评估热知识库的完成和错误检测和修复使用一种新的超图表示的程序。在这两种情况下,它的表现都优于强基线,表明了它的力量和通用性。

英文摘要:

Learning from structured data is a core machine learning task. Commonly, such data is represented as graphs, which normally only consider (typed) binary relationships between pairs of nodes. This is a substantial limitation for many domains with highly-structured data. One important such domain is source code, where hypergraph-based representations can better capture the semantically rich and structured nature of code. In this work, we present HEAT, a neural model capable of representing typed and qualified hypergraphs, where each hyperedge explicitly qualifies how participating nodes contribute. It can be viewed as a generalization of both message passing neural networks and Transformers. We evaluate HEAT on knowledge base completion and on bug detection and repair using a novel hypergraph representation of programs. In both settings, it outperforms strong baselines, indicating its power and generality.

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。

↑