# Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder

arXiv: https://arxiv.org/abs/2210.09959 · HTML: https://mlsanity.com/paper/2210.09959/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 18 Oct 2022.

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

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Weakly-Supervised Disentanglement Without Compromises](https://mlsanity.com/paper/2002.02886/) (2020)
- [Logic Tensor Networks](https://mlsanity.com/paper/2012.13635/) (2020)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations](https://mlsanity.com/paper/1705.08841/) (2017)
- [Weakly Supervised Disentanglement with Guarantees](https://mlsanity.com/paper/1910.09772/) (2019)
- [q-Space Novelty Detection with Variational Autoencoders](https://mlsanity.com/paper/1806.02997/) (2018)
- [Weakly Supervised Disentanglement by Pairwise Similarities](https://mlsanity.com/paper/1906.01044/) (2019)
- [Learning Deep Latent Spaces for Multi-Label Classification](https://mlsanity.com/paper/1707.00418/) (2017)
- [Efficient Out-of-Distribution Detection Using Latent Space of β-VAE for Cyber-Physical Systems](https://mlsanity.com/paper/2108.11800/) (2021)
- [Interpretable Latent Spaces for Learning from Demonstration](https://mlsanity.com/paper/1807.06583/) (2018)
- [Learning from Demonstration with Weakly Supervised Disentanglement](https://mlsanity.com/paper/2006.09107/) (2020)
- [Towards Safe Machine Learning for CPS: Infer Uncertainty from Training Data](https://mlsanity.com/paper/1909.04886/) (2019)
- [Constraint-Based Visual Generation](https://mlsanity.com/paper/1807.09202/) (2018)
- [Design Methodology for Deep Out-of-Distribution Detectors in Real-Time Cyber-Physical Systems](https://mlsanity.com/paper/2207.14694/) (2022)
- [Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice](https://mlsanity.com/paper/1911.06515/) (2019)
- [On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision](https://mlsanity.com/paper/2011.07137/) (2020)

## Built on by (most cited first, 2 of 2)

- [Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation](https://mlsanity.com/paper/2503.05238/) (2025)
- [Disentangled and Distilled Encoder for Out-of-Distribution Reasoning with Rademacher Guarantees](https://mlsanity.com/paper/2512.10522/) (2025)

## Abstract (arXiv)

Out-of-distribution (OOD) detection, i.e., finding test samples derived from a different distribution than the training set, as well as reasoning about such samples (OOD reasoning), are necessary to ensure the safety of results generated by machine learning models. Recently there have been promising results for OOD detection in the latent space of variational autoencoders (VAEs). However, without disentanglement, VAEs cannot perform OOD reasoning. Disentanglement ensures a one- to-many mapping between generative factors of OOD (e.g., rain in image data) and the latent variables to which they are encoded. Although previous literature has focused on weakly-supervised disentanglement on simple datasets with known and independent generative factors. In practice, achieving full disentanglement through weak supervision is impossible for complex datasets, such as Carla, with unknown and abstract generative factors. As a result, we propose an OOD reasoning framework that learns a partially disentangled VAE to reason about complex datasets. Our framework consists of three steps: partitioning data based on observed generative factors, training a VAE as a logic tensor network that satisfies disentanglement rules, and run-time OOD reasoning. We evaluate our approach on the Carla dataset and compare the results against three state-of-the-art methods. We found that our framework outperformed these methods in terms of disentanglement and end-to-end OOD reasoning.