Machine Learning Explainability Frameworks
Published:
This project focuses on developing frameworks for explaining and interpreting machine learning model predictions.
Key Components
ShaRP (Shapley for Rankings and Preferences)
A framework that explains the contributions of features to different aspects of ranked outcomes, based on Shapley values. This approach is particularly useful for understanding how different features influence ranking decisions in recommendation systems, search results, and other ranked outputs.
See the paper for more details: ShaRP: Explaining Rankings with Shapley Values.
ExplainerPFN
A model-agnostic framework for interpreting model predictions using a probabilistic approach. This method provides robust explanations that can be applied across different types of machine learning models without requiring access to the internal model structure.
This framework is currently under development. More details will be available soon.
Funding
This research is supported by the National Science Foundation (NSF) under grant numbers 2326193 and 2312930.