HEAT: Hyperedge Attention Networks
This work addresses the problem of representing highly-structured data like source code for researchers and practitioners in machine learning and software engineering, offering a novel approach but with incremental improvements over existing methods.
The authors tackled the limitation of graph-based models in capturing complex structured data by introducing HEAT, a neural model for typed and qualified hypergraphs, which outperformed strong baselines in knowledge base completion and bug detection and repair tasks.
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.