CMVAE: Causal Meta VAE for Unsupervised Meta-Learning
This addresses bias removal in unsupervised meta-learning for few-shot learning applications, representing an incremental advance with a novel causal approach.
The paper tackles the problem of context-bias in unsupervised meta-learning by modeling it as a Structural Causal Model and proposing CMVAE to remove hidden confounders, resulting in improved performance on few-shot image classification tasks compared to state-of-the-art methods.
Unsupervised meta-learning aims to learn the meta knowledge from unlabeled data and rapidly adapt to novel tasks. However, existing approaches may be misled by the context-bias (e.g. background) from the training data. In this paper, we abstract the unsupervised meta-learning problem into a Structural Causal Model (SCM) and point out that such bias arises due to hidden confounders. To eliminate the confounders, we define the priors are \textit{conditionally} independent, learn the relationships between priors and intervene on them with casual factorization. Furthermore, we propose Causal Meta VAE (CMVAE) that encodes the priors into latent codes in the causal space and learns their relationships simultaneously to achieve the downstream few-shot image classification task. Results on toy datasets and three benchmark datasets demonstrate that our method can remove the context-bias and it outperforms other state-of-the-art unsupervised meta-learning algorithms because of bias-removal. Code is available at \url{https://github.com/GuodongQi/CMVAE}