# Handling missing data in summary and inference networks

**URL:** <https://discuss.bayesflow.org/t/handling-missing-data-in-summary-and-inference-networks/43>\
**Category:** General\
**Created:** [January 14, 2024, 3:29pm UTC](https://discuss.bayesflow.org/t/handling-missing-data-in-summary-and-inference-networks/43 "2024-01-14T15:29:22Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![marvinschmitt](https://yyz1.discourse-cdn.com/flex007/user_avatar/discuss.bayesflow.org/marvinschmitt/32/98_2.png) [@marvinschmitt](https://discuss.bayesflow.org/u/marvinschmitt)\
**Post date:** [January 15, 2024, 12:53am UTC](https://discuss.bayesflow.org/t/handling-missing-data-in-summary-and-inference-networks/43/2 "2024-01-15T00:53:15Z")

</div>

Hi,

Thanks for posting the question on the BayesFlow Forums, I appreciate it.

There has been scholar work on dealing with missing data for Neural Posterior Estimation (NPE): [https://www.biorxiv.org/content/10.1101/2023.01.09.523219v1](https://www.biorxiv.org/content/10.1101/2023.01.09.523219v1)

In a nutshell, they argue for encoding the missing data with some specific (impossible) value **and** adding a missingness mask. For instance, if your data is known to be positive real-valued, y\>0, y\in\mathbb{R}, you would encode missing data as y=-5 and additionally add a mask (additional data dimension) that contains m=0 for existing observations and m=1 for missing ones. To this end, it’s important that you also include missing data in the NN training phase. You can achieve this with a configurator – this way, your current simulator can remain as-is.

I have personally used this technique in the context of **multimodal NPE** , where we additionally want to integrate data from heterogeneous data sources. See Experiment 2 in the paper: [[2311.10671] Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inference](https://arxiv.org/abs/2311.10671)  
As described above, I use a normal simulator and handle all missing data in the configurator. The code is currently closed-source but we’ll release it in the future. In the meantime, you can reach out to me and I’m happy to share the code with you.

Cheers,  
Marvin

---

_[View the full topic](https://discuss.bayesflow.org/t/handling-missing-data-in-summary-and-inference-networks/43)._