paper-with-me

홈 › Papers

On the Robustness of Global Feature Effect Explanations

2024-06-13 · Hubert Baniecki, Giuseppe Casalicchio, Bernd Bischl, Przemyslaw Biecek

We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally.

📄 PDF Abstract BibTeX arXiv:2406.09069

Code (1)

hbaniecki/robust-feature-effects 공식 구현 pytorch

Tasks

Diagnosticscientific discovery

Similar Papers 제목 키워드 기반

Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration

2025-11-13 · Thomas Decker, Volker Tresp, Florian Buettner arxiv

Perturbation-based explanations are widely utilized to enhance the transparency of machine-learning models in practice. However, their reliability is often compromised by the unknown model behavior under the specific per…

Robust Explainable Recommendation

2024-05-03 · Sairamvinay Vijayaraghavan, Prasant Mohapatra

Explainable Recommender Systems is an important field of study which provides reasons behind the suggested recommendations. Explanations with recommender systems are useful for developers while debugging anomalies within…

Explainable RecommendationRecommendation Systems

The Pros and Cons of Adversarial Robustness

2023-12-18 · Yacine Izza, Joao Marques-Silva

Robustness is widely regarded as a fundamental problem in the analysis of machine learning (ML) models. Most often robustness equates with deciding the non-existence of adversarial examples, where adversarial examples de…

Adversarial Robustness

Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations

2025-10-09 · Jasmina Gajcin, Erik Miehling, Rahul Nair, Elizabeth Daly 외 arxiv

Using LLMs to evaluate text, that is, LLM-as-a-judge, is increasingly being used at scale to augment or even replace human annotations. As such, it is imperative that we understand the potential biases and risks of doing…

GLARE: A Natural Language Interface for Querying Global Explanations

2026-06-18 · Bhavan Vasu, Rajesh Mangannavar arxiv

While global explanations are crucial for understanding vision models across datasets, classes, and decision contexts, their complex and monolithic nature often hinders practical exploration. Because users typically seek…