DeepFL: integrating multiple fault diagnosis dimensions for deep fault localization

By Xia Li, Yuqun Zhang, Lingming Zhang. International Symposium on Software Testing and Analysis, 2019

341 citations recorded by the source corpus.

Learning-based fault localization has been intensively studied recently. Prior studies have shown that traditional Learning-to-Rank techniques can help precisely diagnose fault locations using various dimensions of fault-diagnosis features, such as suspiciousness values computed by various off-the-shelf fault localization techniques. However, with the increasing dimensions of features considered by advanced fault localization techniques, it can be quite challenging for the traditional Learning-to-Rank algorithms to automatically identify effective existing/latent features. In this work, we propose DeepFL, a deep learning approach to automatically learn the most effective existing/latent features for precise fault localization. Although the approach is general, in this work, we collect various suspiciousness-value-based, fault-proneness-based and textual-similarity-based features from the fault localization, defect prediction and information retrieval areas, respectively. DeepFL has been studied on 395 real bugs from the widely used Defects4J benchmark. The experimental results show DeepFL can significantly outperform state-of-the-art TraPT/FLUCCS (e.g., localizing 50+ more faults within Top-1). We also investigate the impacts of deep model configurations (e.g., loss functions and epoch settings) and features. Furthermore, DeepFL is also surprisingly effective for cross-project prediction.

Subfields: Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/6fbc0f7544fc9ca7cd29c9811c4cbf6acf5ab981

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

1. Yinlin Deng
2. Chun Xia
3. Soren Dunn
4. Lingming Zhang
5. Sungmin Kang
6. Juyeon Yoon
7. Shin Yoo

In Software

1. Yinlin Deng
2. Chun Xia
3. Soren Dunn
4. Lingming Zhang
5. Sungmin Kang
6. Juyeon Yoon
7. Shin Yoo

Citations in the corpus

• Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction (2022, background): “Consequently, it may be difficult to utilize the state-of-the-art automated debugging techniques, which are often evaluated on Defects4J, when a bug is first reported because they rely on bug reproducing tests [9], [10].”
• Agentless: Demystifying LLM-based Software Engineering Agents (2024, methodology): “Moreover, learning-based techniques have also been proposed to leverage machine learning to combine multiple sources of dynamic/static information, including DeepFL [54], FLUCCS [86], and TRANSFER [67].”
• Less training, more repairing please: revisiting automated program repair via zero-shot learning (2022, background): “To start off, fault localization [3, 40, 41, 58, 75, 79] is often used to reduce the search space by computing the suspicious program locations that likely caused the bug.”
• SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization (2025, unknown): “Learning-based meth-ods such as DeepFL (Li et al., 2019) extended these ideas by integrating multiple fault signals using deep representations.”
• SHERLOC: Structured Diagnostic Localization for Code Repair Agents (2026, unknown): “For repository-level repair, this granularity is not always aligned with the target edit: patches may modify class-level declarations, imports, configuration logic, or coordinated regions across functions.”