Neural Graph Revealers
Harsh Shrivastava, Urszula Chajewska

TL;DR
Neural Graph Revealers (NGRs) integrate sparse graph recovery with probabilistic graphical models, enabling efficient learning of complex, non-linear, and multimodal feature dependencies for probabilistic inference.
Contribution
NGRs introduce a novel framework that combines sparse graph recovery with probabilistic modeling using neural networks and a graph-constrained path norm.
Findings
Effective sparse graph recovery demonstrated on Gaussian data.
Successful probabilistic inference on multimodal infant mortality data.
Handles diverse data types beyond traditional methods.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBayesian Modeling and Causal Inference · Machine Learning and Data Classification · Neural Networks and Applications
MethodsBalanced Selection · Probability Guided Maxout
