# Unsupervised domain adaptation with non-stochastic missing data

arXiv: https://arxiv.org/abs/2109.09505 · HTML: https://mlsanity.com/paper/2109.09505/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 57 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/1901.08211/) (2019)
- [Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge](https://mlsanity.com/paper/1711.07970/) (2017)
- [Support and Invertibility in Domain-Invariant Representations](https://mlsanity.com/paper/1903.03448/) (2019)
- [MisGAN: Learning from Incomplete Data with Generative Adversarial Networks](https://mlsanity.com/paper/1902.09599/) (2019)
- [On Learning Invariant Representation for Domain Adaptation](https://mlsanity.com/paper/1901.09453/) (2019)
- [MIWAE: Deep Generative Modelling and Imputation of Incomplete Data](https://mlsanity.com/paper/1812.02633/) (2018)
- [LRMM: Learning to Recommend with Missing Modalities](https://mlsanity.com/paper/1808.06791/) (2018)
- [Context-Aware Zero-Shot Learning for Object Recognition](https://mlsanity.com/paper/1904.12638/) (2019)
- [Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views](https://mlsanity.com/paper/1911.01861/) (2019)

## Built on by (most cited first, 1 of 1)

- [Mapping conditional distributions for domain adaptation under generalized target shift](https://mlsanity.com/paper/2110.15057/) (2021)

## Abstract (arXiv)

We consider unsupervised domain adaptation (UDA) for classification problems in the presence of missing data in the unlabelled target domain. More precisely, motivated by practical applications, we analyze situations where distribution shift exists between domains and where some components are systematically absent on the target domain without available supervision for imputing the missing target components. We propose a generative approach for imputation. Imputation is performed in a domain-invariant latent space and leverages indirect supervision from a complete source domain. We introduce a single model performing joint adaptation, imputation and classification which, under our assumptions, minimizes an upper bound of its target generalization error and performs well under various representative divergence families (H-divergence, Optimal Transport). Moreover, we compare the target error of our Adaptation-imputation framework and the "ideal" target error of a UDA classifier without missing target components. Our model is further improved with self-training, to bring the learned source and target class posterior distributions closer. We perform experiments on three families of datasets of different modalities: a classical digit classification benchmark, the Amazon product reviews dataset both commonly used in UDA and real-world digital advertising datasets. We show the benefits of jointly performing adaptation, classification and imputation on these datasets.