Timezone: »
Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability. To assess the role of individual input features in a global sense, we explore the perspective of defining feature importance through the predictive power associated with each feature. We introduce two notions of predictive power (model-based and universal) and formalize this approach with a framework of additive importance measures, which unifies numerous methods in the literature. We then propose SAGE, a model-agnostic method that quantifies predictive power while accounting for feature interactions. Our experiments show that SAGE can be calculated efficiently and that it assigns more accurate importance values than other methods.
Author Information
Ian Covert (University of Washington)
Scott Lundberg (Microsoft Research)
Su-In Lee (University of Washington)
More from the Same Authors
-
2023 : A deep generative model of single-cell methylomic data »
Ethan Weinberger · Su-In Lee -
2023 Poster: On the Robustness of Removal-Based Feature Attributions »
Chris Lin · Ian Covert · Su-In Lee -
2023 Poster: Feature Selection in the Contrastive Analysis Setting »
Ethan Weinberger · Ian Covert · Su-In Lee -
2020 : Feature Removal Is a Unifying Principle For Model Explanation Methods »
Ian Covert -
2020 Poster: Learning Deep Attribution Priors Based On Prior Knowledge »
Ethan Weinberger · Joseph Janizek · Su-In Lee -
2018 : Lunch »
Hong Yu · Bhanu Pratap Singh Rawat · Arijit Ukil · Waheeda Saib · Jekaterina Novikova · John Hughes · Yuhui Zhang · Rahul V · Mi Jung Kim · Babak Taati · Hariharan Ravishankar · Harry Clifford · Hirofumi Kobayashi · Babak Taati · Keyang Xu · Yen-Chi Cheng · Timothy Cannings · Jayashree Kalpathy-Cramer · Jayashree Kalpathy-Cramer · Parinaz Sobhani · Kimis Perros · Wei-Hung Weng · Yordan Raykov · Lars Lorch · Mengqi Jin · Xue Teng · Michael Ferlaino · Marek Rei · Cédric Beaulac · Aman Verma · Sebastian Keller · Edmond Cunningham · Luc Evers · Victor Rodriguez · Vipul Satone · Dianbo Liu · Angeline Yasodhara · Geoff Tison · Ligin Solamen · Bryan He · Rahul Ladhania · Yipeng Shi · Md Nafiz Hamid · Pouria Mashouri · Woochan Hwang · Sejin Park · Xu Chen · Rachneet Kaur · Davis Blalock · Holly Wiberg · Parminder Bhatia · Kezi Yu · RUMENG LI · Jun Sakuma · Charles Ding · Aaron Babier · Yong Cai · A Pratap · Luke O'Connor · Allen Nie · Martin Kang · Ian Covert · Xun Wang · Zelun Luo · Serena Yeung · William Boag · Kazuki Tachikawa · Mary Saltz · Owen Lahav · Edward Lee · Eric Teasley · Michael Kamp · Nirmesh Patel · Vishwali Mhasawade · Maxim Samarin · Ryo Uchimido · Farzad Khalvati · Francisco Cruz · Laura Symul · Zaid Nabulsi · Mads Mihailescu · Rosalind Picard -
2017 : Poster Session »
Jaleh Zand · Kun Tu · Michael (Tao-Yi) Lee · Ian Covert · Daniel Hernandez · Zahra Ebrahimzadeh · Joanna Slawinska · Akara Supratak · Miao Lu · John Alberg · Dennis Shen · Serene Yeo · Hsing-Kuo K Pao · Kian Ming Adam Chai · Anish Agarwal · Dimitrios Giannakis · Muhammad Amjad -
2017 Poster: A Unified Approach to Interpreting Model Predictions »
Scott M Lundberg · Su-In Lee -
2017 Oral: A unified approach to interpreting model predictions »
Scott M Lundberg · Su-In Lee -
2016 Poster: Learning Sparse Gaussian Graphical Models with Overlapping Blocks »
Mohammad Javad Hosseini · Su-In Lee -
2014 Workshop: Machine Learning in Computational Biology »
Oliver Stegle · Sara Mostafavi · Anna Goldenberg · Su-In Lee · Michael Leung · Anshul Kundaje · Mark B Gerstein · Martin Renqiang Min · Hannes Bretschneider · Francesco Paolo Casale · Loïc Schwaller · Amit G Deshwar · Benjamin A Logsdon · Yuanyang Zhang · Ali Punjani · Derek C Aguiar · Samuel Kaski