all AI news
Generative multitask learning mitigates target-causing confounding. (arXiv:2202.04136v3 [cs.LG] UPDATED)
Oct. 25, 2022, 1:12 a.m. | Taro Makino, Krzysztof J. Geras, Kyunghyun Cho
cs.LG updates on arXiv.org arxiv.org
We propose generative multitask learning (GMTL), a simple and scalable
approach to causal representation learning for multitask learning. Our approach
makes a minor change to the conventional multitask inference objective, and
improves robustness to target shift. Since GMTL only modifies the inference
objective, it can be used with existing multitask learning methods without
requiring additional training. The improvement in robustness comes from
mitigating unobserved confounders that cause the targets, but not the input. We
refer to them as \emph{target-causing confounders}. …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead Data Engineer
@ WorkMoney | New York City, United States - Remote