# DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction

arXiv: https://arxiv.org/abs/2208.01373 · HTML: https://mlsanity.com/paper/2208.01373/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 2 Aug 2022.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Gradient-Based Neural DAG Learning](https://mlsanity.com/paper/1906.02226/) (2019)
- [Learning Sparse Nonparametric DAGs](https://mlsanity.com/paper/1909.13189/) (2019)
- [Statistical Aspects of Wasserstein Distances](https://mlsanity.com/paper/1806.05500/) (2018)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms](https://mlsanity.com/paper/1901.10912/) (2019)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Learning Neural Causal Models from Unknown Interventions](https://mlsanity.com/paper/1910.01075/) (2019)
- [Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data](https://mlsanity.com/paper/2006.10833/) (2020)
- [D-VAE: A Variational Autoencoder for Directed Acyclic Graphs](https://mlsanity.com/paper/1904.11088/) (2019)
- [Deep Visual Domain Adaptation](https://mlsanity.com/paper/2012.14176/) (2020)
- [PAC-Bayesian Theory Meets Bayesian Inference](https://mlsanity.com/paper/1605.08636/) (2016)
- [Cluster Alignment with a Teacher for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.09980/) (2019)
- [Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1910.05562/) (2019)
- [Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2006.04996/) (2020)
- [CausalVAE: Structured Causal Disentanglement in Variational Autoencoder](https://mlsanity.com/paper/2004.08697/) (2020)
- [Unsuitability of NOTEARS for Causal Graph Discovery](https://mlsanity.com/paper/2104.05441/) (2021)
- [CASTLE: Regularization via Auxiliary Causal Graph Discovery](https://mlsanity.com/paper/2009.13180/) (2020)
- [Domain Adaptation as a Problem of Inference on Graphical Models](https://mlsanity.com/paper/2002.03278/) (2020)
- [Causal Induction from Visual Observations for Goal Directed Tasks](https://mlsanity.com/paper/1910.01751/) (2019)
- [Multi-Domain Adversarial Learning](https://mlsanity.com/paper/1903.09239/) (2019)
- [Amortized learning of neural causal representations](https://mlsanity.com/paper/2008.09301/) (2020)
- [Improving Model Robustness Using Causal Knowledge](https://mlsanity.com/paper/1911.12441/) (2019)
- [Meta Learning as Bayes Risk Minimization](https://mlsanity.com/paper/2006.01488/) (2020)

## Abstract (arXiv)

Leveraging labelled data from multiple domains to enable prediction in another domain without labels is a significant, yet challenging problem. To address this problem, we introduce the framework DAPDAG (Domain Adaptation via Perturbed DAG Reconstruction) and propose to learn an auto-encoder that undertakes inference on population statistics given features and reconstructing a directed acyclic graph (DAG) as an auxiliary task. The underlying DAG structure is assumed invariant among observed variables whose conditional distributions are allowed to vary across domains led by a latent environmental variable E. The encoder is designed to serve as an inference device on E while the decoder reconstructs each observed variable conditioned on its graphical parents in the DAG and the inferred E. We train the encoder and decoder jointly in an end-to-end manner and conduct experiments on synthetic and real datasets with mixed variables. Empirical results demonstrate that reconstructing the DAG benefits the approximate inference. Furthermore, our approach can achieve competitive performance against other benchmarks in prediction tasks, with better adaptation ability, especially in the target domain significantly different from the source domains.