mlsanityData to 14 Oct 2026

DAPDAG: Domain Adaptation via Perturbed DAG Reconstruction

arXiv 2208.01373 ↗First posted 2 Aug 2022cs.LG cs.AI stat.MLcited by 0

Not on the map. Why?

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.

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

29 of 45 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  3. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  4. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  5. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  6. 2018Meta-Learning: A Surveycited by 256
  7. 2019Gradient-Based Neural DAG Learningcited by 227
  8. 2019Learning Sparse Nonparametric DAGscited by 207
  9. 2018Statistical Aspects of Wasserstein Distancescited by 203
  10. 2018Multi-Adversarial Domain Adaptationcited by 196
  11. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  12. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 126
17 more
  1. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  2. 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 100
  3. 2019D-VAE: A Variational Autoencoder for Directed Acyclic Graphscited by 98
  4. 2020Deep Visual Domain Adaptationcited by 91
  5. 2016PAC-Bayesian Theory Meets Bayesian Inferencecited by 88
  6. 2019Cluster Alignment with a Teacher for Unsupervised Domain Adaptationcited by 88
  7. 2019Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptationcited by 62
  8. 2020Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptationcited by 60
  9. 2020CausalVAE: Structured Causal Disentanglement in Variational Autoencodercited by 48
  10. 2021Unsuitability of NOTEARS for Causal Graph Discoverycited by 47
  11. 2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41
  12. 2020Domain Adaptation as a Problem of Inference on Graphical Modelscited by 36
  13. 2019Causal Induction from Visual Observations for Goal Directed Taskscited by 31
  14. 2019Multi-Domain Adversarial Learningcited by 19
  15. 2020Amortized learning of neural causal representationscited by 14
  16. 2019Improving Model Robustness Using Causal Knowledgecited by 7
  17. 2020Meta Learning as Bayes Risk Minimizationcited by 1

Built on by

Not cited yet.