ARFT-Transformer: Modeling Metric Dependencies for Cross-Project Aging-Related Bug Prediction

TL;DR

This paper introduces ARFT-Transformer, a novel transformer-based framework that models metric dependencies and handles class imbalance to improve cross-project aging-related bug prediction, outperforming existing methods.

Contribution

It proposes a metric-level multi-head attention mechanism and Focal Loss to better capture metric interactions and address class imbalance in cross-project ARB prediction.

Findings

ARFT-Transformer outperforms state-of-the-art methods by up to 29.54% in Balance metric.

It effectively captures inter-metric dependencies using multi-head attention.

The approach demonstrates significant improvements on large-scale open-source projects.

Abstract

Software systems that run for long periods often suffer from software aging, which is typically caused by Aging-Related Bugs (ARBs). To mitigate the risk of ARBs early in the development phase, ARB prediction has been introduced into software aging research. However, due to the difficulty of collecting ARBs, within-project ARB prediction faces the challenge of data scarcity, leading to the proposal of cross-project ARB prediction. This task faces two major challenges: 1) domain adaptation issue caused by distribution difference between source and target projects; and 2) severe class imbalance between ARB-prone and ARB-free samples. Although various methods have been proposed for cross-project ARB prediction, existing approaches treat the input metrics independently and often neglect the rich inter-metric dependencies, which can lead to overlapping information and misjudgment of metric importance, potentially affecting the model's performance. Moreover, they typically use cross-entropy as the loss function during training, which cannot distinguish the difficulty of sample classification. To overcome these limitations, we propose ARFT-Transformer, a transformer-based cross-project ARB prediction framework that introduces a metric-level multi-head attention mechanism to capture metric interactions and incorporates Focal Loss function to effectively handle class imbalance. Experiments conducted on three large-scale open-source projects demonstrate that ARFT-Transformer on average outperforms state-of-the-art cross-project ARB prediction methods in both single-source and multi-source cases, achieving up to a 29.54% and 19.92% improvement in Balance metric.