A simple baseline that flags a suspect model whenever it repeats a victim model's mistakes performs as well as or better than complex state-of-the-art model fingerprints on existing benchmarks, exposing those benchmarks as too easy.
Dynamic Interpretability for Model Comparison via Decision Rules
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Explainable AI (XAI) methods have mostly been built to investigate and shed light on single machine learning models and are not designed to capture and explain differences between multiple models effectively. This paper addresses the challenge of understanding and explaining differences between machine learning models, which is crucial for model selection, monitoring and lifecycle management in real-world applications. We propose DeltaXplainer, a model-agnostic method for generating rule-based explanations describing the differences between two binary classifiers. To assess the effectiveness of DeltaXplainer, we conduct experiments on synthetic and real-world datasets, covering various model comparison scenarios involving different types of concept drift.
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes
A simple baseline that flags a suspect model whenever it repeats a victim model's mistakes performs as well as or better than complex state-of-the-art model fingerprints on existing benchmarks, exposing those benchmarks as too easy.