Search Results for author: Chris Lin

Found 3 papers, 0 papers with code

Contrastive Corpus Attribution for Explaining Representations

no code implementations30 Sep 2022 Chris Lin, Hugh Chen, Chanwoo Kim, Su-In Lee

To address this, we propose contrastive corpus similarity, a novel and semantically meaningful scalar explanation output based on a reference corpus and a contrasting foil set of samples.

Contrastive Learning Object Localization

Graph Neural Networks Including Sparse Interpretability

no code implementations30 Jun 2020 Chris Lin, Gerald J. Sun, Krishna C. Bulusu, Jonathan R. Dry, Marylens Hernandez

Through a single self-attention layer, a GISST model learns an importance probability for each node feature and edge in the input graph.

Feature Importance Representation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.