DeepAI AI Chat
Log In Sign Up

iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams

by   Maximilian Muschalik, et al.

Explainable Artificial Intelligence (XAI) focuses mainly on batch learning scenarios. In the static learning tasks, various XAI methods, like SAGE, have been proposed that distribute the importance of a model on its input features. However, models are often applied in ever-changing dynamic environments like incremental learning. As a result, we propose iSAGE as a direct incrementalization of SAGE suited for dynamic learning environments. We further provide an efficient approximation method to model feature removal based on the conditional data distribution in an incremental setting. We formally analyze our explanation method to show that it is an unbiased estimator and construct confidence bounds for the point estimates. Lastly, we evaluate our approach in a thorough experimental analysis based on well-established data sets and concept drift streams.


Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams

Explainable Artificial Intelligence (XAI) has mainly focused on static l...

iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios

Post-hoc explanation techniques such as the well-established partial dep...

Incremental Slow Feature Analysis: Adaptive and Episodic Learning from High-Dimensional Input Streams

Slow Feature Analysis (SFA) extracts features representing the underlyin...

A Novel Incremental Clustering Technique with Concept Drift Detection

Data are being collected from various aspects of life. These data can of...

Incremental RANSAC for Online Relocation in Large Dynamic Environments

Vehicle relocation is the problem in which a mobile robot has to estimat...

On the Connection between Concept Drift and Uncertainty in Industrial Artificial Intelligence

AI-based digital twins are at the leading edge of the Industry 4.0 revol...

Lambda Learner: Fast Incremental Learning on Data Streams

One of the most well-established applications of machine learning is in ...