Probabilistic Graph Circuits: Deep Generative Models for Tractable Probabilistic Inference over Graphs

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00389967" target="_blank" >RIV/68407700:21230/25:00389967 - isvavai.cz</a>

Result on the web

<a href="https://openreview.net/forum?id=lqNtJRjlT1" target="_blank" >https://openreview.net/forum?id=lqNtJRjlT1</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Probabilistic Graph Circuits: Deep Generative Models for Tractable Probabilistic Inference over Graphs

Original language description

Deep generative models (DGMs) have recently demonstrated remarkable success in capturing complex probability distributions over graphs. Although their excellent performance is attributed to powerful and scalable deep neural networks, it is, at the same time, exactly the presence of these highly non-linear transformations that makes DGMs intractable. Indeed, despite representing probability distributions, intractable DGMs deny probabilistic foundations by their inability to answer even the most basic inference queries without approximations or design choices specific to a very narrow range of queries. To address this limitation, we propose probabilistic graph circuits (PGCs), a framework of tractable DGMs that provide exact and efficient probabilistic inference over (arbitrary parts of) graphs. Nonetheless, achieving both exactness and efficiency is challenging in the permutation-invariant setting of graphs. We design PGCs that are inherently invariant and satisfy these two requirements, yet at the cost of low expressive power. Therefore, we investigate two alternative strategies to achieve the invariance: the first sacrifices the efficiency, and the second sacrifices the exactness. We demonstrate that ignoring the permutation invariance can have severe consequences in anomaly detection, and that the latter approach is competitive with, and sometimes better than, existing intractable DGMs in the context of molecular graph generation.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA22-32620S" target="_blank" >GA22-32620S: Unsupervised learning from heterogenous structured data</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of Machine Learning Research

ISBN

—

ISSN

2640-3498

e-ISSN

—

Number of pages

35

Pages from-to

3416-3450

Publisher name

ML Research Press

Place of publication

—

Event location

Rio de Janeiro

Event date

Jul 21, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001592914500147