Domain Generalization -- A Causal Perspective

no code implementations • 30 Sep 2022 • Paras Sheth, Raha Moraffah, K. Selçuk Candan, Adrienne Raglin, Huan Liu

As a result models that rely on this assumption exhibit poor generalization capabilities.

Data Augmentation Domain Generalization +1

Causal Disentanglement with Network Information for Debiased Recommendations

no code implementations • 14 Apr 2022 • Paras Sheth, Ruocheng Guo, Lu Cheng, Huan Liu, K. Selçuk Candan

Aside from the user conformity, aspects of confounding such as item popularity present in the network information is also captured in our method with the aid of \textit{causal disentanglement} which unravels the learned representations into independent factors that are responsible for (a) modeling the exposure of an item to the user, (b) predicting the ratings, and (c) controlling the hidden confounders.

Causal Inference Disentanglement +1