# OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation

arXiv: https://arxiv.org/abs/2105.00397 · HTML: https://mlsanity.com/paper/2105.00397/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 2 May 2021.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Neural Processes](https://mlsanity.com/paper/1807.01622/) (2018)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Towards a Neural Statistician](https://mlsanity.com/paper/1606.02185/) (2016)
- [One-shot Learning with Memory-Augmented Neural Networks](https://mlsanity.com/paper/1605.06065/) (2016)
- [The Variational Homoencoder: Learning to learn high capacity generative models from few examples](https://mlsanity.com/paper/1807.08919/) (2018)
- [Polarization Human Shape and Pose Dataset](https://mlsanity.com/paper/2004.14899/) (2020)
- [VFunc: a Deep Generative Model for Functions](https://mlsanity.com/paper/1807.04106/) (2018)

## Abstract (arXiv)

Contemporary data-driven methods are typically fed with full supervision on large-scale datasets which limits their applicability. However, in the actual systems with limitations such as measurement error and data acquisition problems, people usually obtain incomplete data. Although data completion has attracted wide attention, the underlying data pattern and relativity are still under-developed. Currently, the family of latent variable models allows learning deep latent variables over observed variables by fitting the marginal distribution. As far as we know, current methods fail to perceive the data relativity under partial observation. Aiming at modeling incomplete data, this work uses relational inference to fill in the incomplete data. Specifically, we expect to approximate the real joint distribution over the partial observation and latent variables, thus infer the unseen targets respectively. To this end, we propose Omni-Relational Network (OR-Net) to model the pointwise relativity in two aspects: (i) On one hand, the inner relationship is built among the context points in the partial observation; (ii) On the other hand, the unseen targets are inferred by learning the cross-relationship with the observed data points. It is further discovered that the proposed method can be generalized to different scenarios regardless of whether the physical structure can be observed or not. It is demonstrated that the proposed OR-Net can be well generalized for data completion tasks of various modalities, including function regression, image completion on MNIST and CelebA datasets, and also sequential motion generation conditioned on the observed poses.