Multimodal Learning for Just-In-Time Software Defect Prediction in Autonomous Driving Systems

2025-02-28

AI Summary

To address the challenges of Just-In-Time Software Defect Prediction (JIT-SDP) in autonomous driving software systems, this paper proposes the first multimodal Transformer model specifically designed for JIT-SDP. Methodologically, it unifies heterogeneous features—including code text, change metrics, and contextual information—through a novel cross-modal attention fusion mechanism, overcoming limitations of unimodal representation learning. The architecture comprises a CodeBERT-based code encoder, a multimodal fusion module, cross-modal attention layers, and a lightweight prediction head, enabling end-to-end training. Evaluated on three real-world autonomous driving projects—Apollo, CARLA, and Donkeycar—the model achieves an average 12.7% improvement in F1-score and an AUC of 0.912, significantly outperforming existing state-of-the-art approaches.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In recent years, the rise of autonomous driving technologies has highlighted the critical importance of reliable software for ensuring safety and performance. This paper proposes a novel approach for just-in-time software defect prediction (JIT-SDP) in autonomous driving software systems using multimodal learning. The proposed model leverages the multimodal transformers in which the pre-trained transformers and a combining module deal with the multiple data modalities of the software system datasets such as code features, change metrics, and contextual information. The key point for adapting multimodal learning is to utilize the attention mechanism between the different data modalities such as text, numerical, and categorical. In the combining module, the output of a transformer model on text data and tabular features containing categorical and numerical data are combined to produce the predictions using the fully connected layers. Experiments conducted on three open-source autonomous driving system software projects collected from the GitHub repository (Apollo, Carla, and Donkeycar) demonstrate that the proposed approach significantly outperforms state-of-the-art deep learning and machine learning models regarding evaluation metrics. Our findings highlight the potential of multimodal learning to enhance the reliability and safety of autonomous driving software through improved defect prediction.

Problem

• Predict software defects in autonomous driving systems.
• Use multimodal learning with transformers for defect prediction.
• Combine text, numerical, and categorical data for accurate predictions.

Innovation

• Multimodal transformers for defect prediction
• Attention mechanism across text, numerical, categorical data
• Combining module with fully connected layers