Shadow Datasets, New challenging datasets for Causal Representation Learning. (arXiv:2308.05707v1 [cs.LG])

Discovering causal relations among semantic factors is an emergent topic in
representation learning. Most causal representation learning (CRL) methods are
fully supervised, which is impractical due to costly labeling. To resolve this
restriction, weakly supervised CRL methods were introduced. To evaluate CRL
performance, four existing datasets, Pendulum, Flow, CelebA(BEARD) and
CelebA(SMILE), are utilized. However, existing CRL datasets are limited to
simple graphs with few generative factors. Thus we propose two new datasets
with a larger number of diverse generative factors …

arxiv datasets flow labeling performance relations representation representation learning semantic shadow