CMVAE: Causal Meta VAE for Unsupervised Meta-Learning
Not on the map. Why?
Abstract (arXiv)
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 textitconditionally 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 urlhttps://github.com/GuodongQi/CMVAE
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 20 Feb 2023.
Builds on
32 of 45 references.
References · 32
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
- 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
- 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
- 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
- 2016Adversarial Feature Learningcited by 350
- 2019Learning Sparse Nonparametric DAGscited by 207
20 more
- 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
- 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 153
- 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 126
- 2020Interventional Few-Shot Learningcited by 112
- 2021Causal Attention for Vision-Language Taskscited by 111
- 2020Visual Commonsense R-CNNcited by 106
- 2018The Blessings of Multiple Causescited by 104
- 2020On Disentangled Representations Learned From Correlated Datacited by 94
- 2018Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizercited by 88
- 2018Unsupervised Learning via Meta-Learningcited by 82
- 2016Discovering Causal Signals in Imagescited by 79
- 2018Unsupervised Meta-Learning For Few-Shot Image Classificationcited by 75
- 2022Differentiable DAG Samplingcited by 47
- 2020Counterfactual Fairness with Disentangled Causal Effect Variational Autoencodercited by 45
- 2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41
- 2020Towards Scalable Bayesian Learning of Causal DAGscited by 33
- 2022On Implicit Bias in Overparameterized Bilevel Optimizationcited by 30
- 2019Ordering-Based Causal Structure Learning in the Presence of Latent Variablescited by 26
- 2020Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Modelscited by 26
- 2021Unsupervised Foreground Extraction via Deep Region Competitioncited by 26
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.