15 papers
Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies
Dennis Gross, Quentin Mazouni, Helge Spieker +1
Reinforcement learning (RL) policies can be unsafe and vulnerable to attacks. Ensuring their reliability is often a pain point as existing automated testing methods target only sel…
Metamorphic Testing with the Rashomon Set: Explanation Faithfulness in Machine Learning
Helge Spieker, Jørn Eirik Betten, Arnaud Gotlieb
Multiple machine learning models can achieve near-equivalent predictive performance on the same task, yet provide divergent feature-based explanations. This is called the Rashomon…
Semi-supervised CAPP Transformer Learning via Pseudo-labeling
Dennis Gross, Helge Spieker, Arnaud Gotlieb +3
High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing…
Context-Aware Autoencoders for Anomaly Detection in Maritime Surveillance
Divya Acharya, Pierre Bernab'e, Antoine Chevrot +3
The detection of anomalies is crucial to ensuring the safety and security of maritime vessel traffic surveillance. Although autoencoders are popular for anomaly detection, their ef…
Efficiently Ranking Software Variants with Minimal Benchmarks
Théo Matricon, Mathieu Acher, Helge Spieker +1
Benchmarking is a common practice in software engineering to assess the qualities and performance of software variants, coming from multiple competing systems or from configuration…
Translating the Rashomon Effect to Sequential Decision-Making Tasks
Dennis Gross, Jørn Eirik Betten, Helge Spieker
The Rashomon effect describes the phenomenon where multiple models trained on the same data produce identical predictions while differing in which features they rely on internally.…