# Explanation Shift: How Did the Distribution Shift Impact the Model? Source: [Explanation Shift: How Did the Distribution Shift Impact the Model?]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:43:00.780Z Authors: Carlos Mougan, Klaus Broelemann, David Masip, Gjergji Kasneci, Thanassis Thiropanis, Steffen Staab Published: 2023-03-14T17:13:01.000Z ## Abstract As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In practice, new input data tend to come without target labels. Then, state-of-the-art techniques model input data distributions or model prediction distributions and try to understand issues regarding the interactions between learned models and shifting distributions. We suggest a novel approach that models how explanation characteristics shift when affected by distribution shifts. We find that the modeling of explanation shifts can be a better indicator for detecting out-of-distribution model behaviour than state-of-the-art techniques. We analyze different types of distribution shifts using synthetic examples and real-world data sets. We provide an algorithmic method that allows us to inspect the interaction between data set features and learned models and compare them to the state-of-the-art. We release our methods in an open-source Python package, as well as the code used to reproduce our experiments. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Identifying shifted features on COVID-19 Dense Simulation (AUC)](): Identifying shifted features; COVID-19 Dense Simulation; AUC: 86. - [Identifying shifted features on COVID-19 Sparse Simulation](): Identifying shifted features; COVID-19 Sparse Simulation; AUC: 81. - [Identifying Shifted Features on Diabetes Readmission Sparse Simulation (AUC)](): Identifying shifted features; Diabetes Readmission Sparse Simulation; AUC: 77. - [Identifying shifted features on Diabetes Readmission Dense Simulation (AUC)](): Identifying shifted features; Diabetes Readmission Dense Simulation; AUC: 64. - [Identifying shifted features on SUPPORT2 Sparse Simulation (AUC)](): Identifying shifted features; SUPPORT2 Sparse Simulation; AUC: 82. - [Identifying shifted features on SUPPORT2 Dense Simulation (AUC)](): Identifying shifted features; SUPPORT2 Dense Simulation; AUC: 70. ## Original sources and implementation [Original paper]() [PDF]()