AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Generative multitask learning mitigates target-causing confounding

Taro Makino, Krzysztof J. Geras, Kyunghyun Cho

NeurIPS 2022 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 3 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 GMTL inference with an optimal α instead of conventional DMTL inferenceFour multitask learning methods · Attributes of People and Taskonomy, simulated target shiftsaccuracyImproved
Increase α as target shift becomes more severe (ablation)GMTL · Attributes of People and Taskonomy, simulated target shiftsaccuracyImproved
Increase α, removing more of the empirical joint-target prior (ablation)GMTL · In-distribution test setsaccuracyHurt
Use the target-shift severity metric and α selection on long sleeves as the main task and hat as auxiliaryGMTL · Attributes of People: long sleeves (main), hat (auxiliary), simulated target shiftsaccuracyMixed
Replace shared-trunk multitask learning with no parameter sharingTaskonomy · Object and scene classification, ID testtop-1 accuracy: 0.710 ± 0.001 -> 0.749 ± 0.001; 0.719 ± 0.001 -> 0.730 ± 0.001Improved
Use Cross-stitch Networks instead of single-task-equivalent NPSAttributes of People · Hat (main), long sleeves (auxiliary), ID testaccuracy: 0.917 ± 0.003 -> 0.920 ± 0.001Improved
Use Cross-stitch Networks instead of single-task-equivalent NPSTaskonomy · Scene classification (main), object classification (auxiliary), ID testtop-1 accuracy: 0.730 ± 0.001 -> 0.737 ± 0.001Improved

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