# Neural Graph Revealers

arXiv: https://arxiv.org/abs/2302.13582 · HTML: https://mlsanity.com/paper/2302.13582/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 65 references that are in the map.
- First posted on arXiv 27 Feb 2023.

## Builds on (most cited first, 25 of 25)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Stochastic Video Generation with a Learned Prior](https://mlsanity.com/paper/1802.07687/) (2018)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Learning Sparse Nonparametric DAGs](https://mlsanity.com/paper/1909.13189/) (2019)
- [Learning Bayesian Networks: The Combination of Knowledge and Statistical Data](https://mlsanity.com/paper/1302.6815/) (2013)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [A Review on Deep Learning Techniques for Video Prediction](https://mlsanity.com/paper/2004.05214/) (2020)
- [D-VAE: A Variational Autoencoder for Directed Acyclic Graphs](https://mlsanity.com/paper/1904.11088/) (2019)
- [Network Inference via the Time-Varying Graphical Lasso](https://mlsanity.com/paper/1703.01958/) (2017)
- [Deep Randomized Neural Networks](https://mlsanity.com/paper/2002.12287/) (2020)
- [Learning to Learn Graph Topologies](https://mlsanity.com/paper/2110.09807/) (2021)
- [GLAD: Learning Sparse Graph Recovery](https://mlsanity.com/paper/1906.00271/) (2019)
- [Diverse Video Generation using a Gaussian Process Trigger](https://mlsanity.com/paper/2107.04619/) (2021)
- [Tensor Graphical Lasso (TeraLasso)](https://mlsanity.com/paper/1705.03983/) (2017)
- [Learning to Discover Sparse Graphical Models](https://mlsanity.com/paper/1605.06359/) (2016)
- [Echo State Speech Recognition](https://mlsanity.com/paper/2102.09114/) (2021)
- [Neural Graphical Models](https://mlsanity.com/paper/2210.00453/) (2022)
- [The Sylvester Graphical Lasso (SyGlasso)](https://mlsanity.com/paper/2002.00288/) (2020)
- [Methods for Recovering Conditional Independence Graphs: A Survey](https://mlsanity.com/paper/2211.06829/) (2022)
- [Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification](https://mlsanity.com/paper/1906.00291/) (2019)
- [uGLAD: Sparse graph recovery by optimizing deep unrolled networks](https://mlsanity.com/paper/2205.11610/) (2022)
- [An Algorithm for the Construction of Bayesian Network Structures from Data](https://mlsanity.com/paper/1303.1485/) (2013)
- [AntMan: Sparse Low-Rank Compression to Accelerate RNN inference](https://mlsanity.com/paper/1910.01740/) (2019)

## Built on by (most cited first, 3 of 3)

- [Federated Learning with Neural Graphical Models](https://mlsanity.com/paper/2309.11680/) (2023)
- [Are uGLAD? Time will tell!](https://mlsanity.com/paper/2303.11647/) (2023)
- [Knowledge Propagation over Conditional Independence Graphs](https://mlsanity.com/paper/2308.05857/) (2023)

## Abstract (arXiv)

Sparse graph recovery methods work well where the data follows their assumptions but often they are not designed for doing downstream probabilistic queries. This limits their adoption to only identifying connections among the input variables. On the other hand, the Probabilistic Graphical Models (PGMs) assume an underlying base graph between variables and learns a distribution over them. PGM design choices are carefully made such that the inference & sampling algorithms are efficient. This brings in certain restrictions and often simplifying assumptions. In this work, we propose Neural Graph Revealers (NGRs), that are an attempt to efficiently merge the sparse graph recovery methods with PGMs into a single flow. The problem setting consists of an input data X with D features and M samples and the task is to recover a sparse graph showing connection between the features and jointly learn a probability distribution over them. NGRs view the neural networks as a `glass box' or more specifically as a multitask learning framework. We introduce `Graph-constrained path norm' that NGRs leverage to learn a graphical model that captures complex non-linear functional dependencies between the features in the form of an undirected sparse graph. Furthermore, NGRs can handle multimodal inputs like images, text, categorical data, embeddings etc. which is not straightforward to incorporate in the existing methods. We show experimental results of doing sparse graph recovery and probabilistic inference on data from Gaussian graphical models and a multimodal infant mortality dataset by Centers for Disease Control and Prevention.