DeepLSH: Deep Locality-Sensitive Hash Learning for Fast and Efficient Near-Duplicate Crash Report Detection

Automatic crash bucketing is a crucial phase in the software de-velopment process for efficiently triaging bug reports. It generally consists in grouping similar reports through clustering techniques. However, with real-time streaming bug collection, systems are needed to quickly answer the question...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / International Conference on Software Engineering pp. 2445 - 2456
Main Authors: Remil, Youcef, Bendimerad, Anes, Mathonat, Romain, Raissi, Chedy, Kaytoue, Mehdi
Format: Conference Proceeding
Language:English
Published: ACM 14.04.2024
Subjects:
Approximate nearest neighbors
Computer bugs
Crash deduplication
Hash functions
Locality-sensitive hashing
Measurement
Nearest neighbor methods
Neural networks
Search problems
Siamese neural networks
Software
Stack trace similarity
ISSN:1558-1225
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatic crash bucketing is a crucial phase in the software de-velopment process for efficiently triaging bug reports. It generally consists in grouping similar reports through clustering techniques. However, with real-time streaming bug collection, systems are needed to quickly answer the question: What are the most similar bugs to a new one?, that is, efficiently find near-duplicates. It is thus natural to consider nearest neighbors search to tackle this problem and especially the well-known locality-sensitive hashing (LSH) to deal with large datasets due to its sublinear performance and theoretical guarantees on the similarity search accuracy. Surprisingly, LSH has not been considered in the crash bucketing literature. It is indeed not trivial to derive hash functions that satisfy the so-called locality-sensitive property for the most advanced crash bucketing metrics. Consequently, we study in this paper how to leverage LSH for this task. To be able to consider the most relevant metrics used in the literature, we introduce DeepLsh, a Siamese DNN architecture with an original loss function, that perfectly approximates the locality-sensitivity property even for Jaccard and Cosine metrics for which exact LSH solutions exist. We support this claim with a series of experiments on an original dataset, which we make available.
ISSN:1558-1225
DOI:10.1145/3597503.3639146