arXiv Open Access 2022

Explanation Shift: Detecting distribution shifts on tabular data via the explanation space

Carlos Mougan Klaus Broelemann Gjergji Kasneci Thanassis Tiropanis Steffen Staab
Lihat Sumber

Abstrak

As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In the past, predictive performance was considered the key indicator to monitor. However, explanation aspects have come to attention within the last years. In this work, we investigate how model predictive performance and model explanation characteristics are affected under distribution shifts and how these key indicators are related to each other for tabular data. We find that the modeling of explanation shifts can be a better indicator for the detection of predictive performance changes than state-of-the-art techniques based on representations of distribution shifts. We provide a mathematical analysis of different types of distribution shifts as well as synthetic experimental examples.

Topik & Kata Kunci

Penulis (5)

C

Carlos Mougan

K

Klaus Broelemann

G

Gjergji Kasneci

T

Thanassis Tiropanis

S

Steffen Staab

Format Sitasi

Mougan, C., Broelemann, K., Kasneci, G., Tiropanis, T., Staab, S. (2022). Explanation Shift: Detecting distribution shifts on tabular data via the explanation space. https://arxiv.org/abs/2210.12369

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓