This collection is initiated in 2018.
A curated list of awesome deep causal learning methods - when causaliy deep meets deep neural network.
Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers, awesome-architecture-search, awesome-deep-neuroevolution (nice idea for the code index) and awesome-self-supervised-learning.
Learning to inference and disentangle is the next big challenge of Deep Learning.
Welcome to commit and pull request. I will update some guideline on causal software, which could be found out here.
| Title | Authors | Code | Year |
|---|---|---|---|
| Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect | Tang et al. | code | NeurIPS 2020 |
| Causal Intervention for Weakly-Supervised Semantic Segmentation | Zhang et al. | code | NeurIPS 2020 |
| A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms | Yoshua Bengio et al. | code | ICLR 2020 |
| Causal Induction from Visual Observations for Goal Directed Tasks | Suraj Nair, et al. | - | arxiv 2019 |
| Granger-causal attentive mixtures of experts: Learning important features with neural networks | Patrick Schwab, et al. | - | AAAI 2019 |
| Causal bandits: Learning good interventions via causal inference | Finnian Lattimore et al. | - | NeurIPS, 2016 |
| Learning granger causality for hawkes processes | Xu ,et al. | - | ICML 2016 |
| One-shot learning by inverting a compositional causal process | Brenden M. Lake, et al. | - | NeurIPS 2013 |
| Title | Authors | Code | Year |
|---|---|---|---|
| Training a Resilient Q-network against Observational Interference | CHH Yang et al. | code | AAAI 2022 |
| Off-policyevaluation in infinite-horizon reinforcement learning with latent confounders | Andrew Bennett et al. | - | AISTATS 2021 |
| Title | Authors | Code | Year |
|---|---|---|---|
| Estimating identifiable causal effects through double machine learning | Y Jung et al. | - | AAAI 2021 |
| Causal effect inference with deep latent-variable models | Louizos, et al. | code | NIPS 2017 |
| Estimating individual treatment effect: generalization bounds and algorithms | Uri Shalit, et al. | code | ICML 2017 |
| Towards a learning theory of cause-effect inference | Lopez Paz, et al. | - | ICML 2015 |
| Title | Authors | Code | Year |
|---|---|---|---|
| Interventional Few-Shot Learning | Yue et al. | code | NeurIPS 2020 |
| Counterfactual Vision and Language Learning | Abbasnejad et al. | - | CVPR 2020 |
| Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing | Agarwal et al. | code | CVPR 2020 |
| Two Causal Principles for Improving Visual Dialog | Qi et al. | code | CVPR 2020 |
| Unbiased Scene Graph Generation from Biased Training | Tang et al. | code | CVPR 2020 |
| When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks | CHH Yang, et al | code | ICIP 2019 |
| Discovering causal signals in images | Lopez-Paz et al. | code withdrawn from author | CVPR 2017 |
| Causal graph-based video segmentation | Couprie,et al. | - | ICIP 2013 |
C.-H. Huck Yang, Georgia Tech and welcome to all!
2022 May 1st updated.
2021 updated.
2018 updated.