Graph collaborative filtering-based bug triaging

Published: 2023, Last Modified: 06 Aug 2024J. Syst. Softw. 2023EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Bug-developer correlations are modeled as a bipartite graph.•Natural language processing-based pre-training is implemented on bug reports to initialize bug nodes.•Spatial–temporal graph convolution strategy is designed to learn the representation of developer nodes.•Information retrieval-based classifier is proposed to match bugs and developers.•Extensive experiments across mainstream datasets show the competence of our GCBT.
Loading