Speaker |
Siu Lun (Alan) Chau |
|---|---|
Affiliation |
Oxford University |
Date |
Friday, 29 April 2022 |
Time |
12:00-13:00 |
Location |
Ground Floor Lecture Theatre, UCL Gatsby Computational Neuroscience Unit, 25 Howland St, London W1T 4JG |
Link |
https://ucl.zoom.us/j/97245943682 |
Event series |
DeepMind/ELLIS CSML Seminar Series |
Abstract |
Feature attribution for kernel methods is often heuristic and not individualised for each prediction. To address this, we turn to the concept of Shapley values, a coalition game theoretical framework that has previously been applied to different machine learning model interpretation tasks. By analysing Shapley values from a functional perspective, we propose RKHS-SHAP, an attribution method for kernel machines that can efficiently compute both Interventional and Observational Shapley values using kernel mean embeddings of distributions. In this talk, we will start by introducing Shapley values, and how they are used to interpret models such as linear models, trees and deep nets, and finally we will present RKHS-SHAP as the latest member to this family of model-specific SHAP methods. |
Biography |