Better Knowledge Enhancement for Privacy-Preserving Cross-Project Defect Prediction

TL;DR

This paper introduces FedDP, a federated learning framework for privacy-preserving cross-project defect prediction that effectively handles data heterogeneity through local awareness and global knowledge distillation, improving prediction accuracy.

Contribution

The paper proposes a novel federated learning approach with heterogeneity-aware local models and global knowledge distillation for CPDP, addressing privacy and data heterogeneity challenges.

Findings

FedDP outperforms baseline methods on 19 projects.

Incorporates heterogeneity awareness for better model ensemble.

Uses open-source data for effective knowledge distillation.

Abstract

Cross-Project Defect Prediction (CPDP) poses a non-trivial challenge to construct a reliable defect predictor by leveraging data from other projects, particularly when data owners are concerned about data privacy. In recent years, Federated Learning (FL) has become an emerging paradigm to guarantee privacy information by collaborative training a global model among multiple parties without sharing raw data. While the direct application of FL to the CPDP task offers a promising solution to address privacy concerns, the data heterogeneity arising from proprietary projects across different companies or organizations will bring troubles for model training. In this paper, we study the privacy-preserving cross-project defect prediction with data heterogeneity under the federated learning framework. To address this problem, we propose a novel knowledge enhancement approach named FedDP with two simple but effective solutions: 1. Local Heterogeneity Awareness and 2. Global Knowledge Distillation. Specifically, we employ open-source project data as the distillation dataset and optimize the global model with the heterogeneity-aware local model ensemble via knowledge distillation. Experimental results on 19 projects from two datasets demonstrate that our method significantly outperforms baselines.