AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Generative causal explanations of black-box classifiers

Matthew O'Shaughnessy, Gregory Canal, Marissa Connor, Christopher Rozell, Mark Davenport

NeurIPS 2020 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the learned causal factor α to vary generated inputsCNN trained on MNIST 3 and 8 · MNIST 3 and 8classifier outputImproved
Vary noncausal factors β instead of causal factorsCNN trained on MNIST 3 and 8 · MNIST 3 and 8classifier outputNo clear effect
Replace the joint unconditional causal objective with the independent unconditional objective C_iu (ablation)Linear-Gaussian explainer for the and classifier · Synthetic and classifiercausal objectiveHurt
Increase λ to give data fidelity more weight (ablation)Linear-Gaussian explainer for the and classifier · Synthetic and classifierdata representationImproved
Increase λ to give data fidelity more weight (ablation)Linear-Gaussian explainer for the and classifier · Synthetic and classifiercausal alignmentHurt
Use the joint conditional objective C_jc instead of the joint unconditional objective (ablation)Linear-Gaussian explainer for the and classifier · Synthetic and classifiercausal objectiveMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy