Neural Markov Logic Networks

05/31/2019
by   Giuseppe Marra, et al.
0

We introduce Neural Markov Logic Networks (NMLNs), a statistical relational learning system that borrows ideas from Markov logic. Like Markov Logic Networks (MLNs), NMLNs are an exponential-family model for modelling distributions over possible worlds, but unlike MLNs, they do not rely on explicitly specified first-order logic rules. Instead, NMLNs learn an implicit representation of such rules as a neural network that acts as a potential function on fragments of the relational structure. Interestingly, any MLN can be represented as an NMLN. Similarly to recently proposed Neural theorem provers (NTPs) [Rocktäschel and Riedel, 2017], NMLNs can exploit embeddings of constants but, unlike NTPs, NMLNs work well also in their absence. This is extremely important for predicting in settings other than the transductive one. We showcase the potential of NMLNs on knowledge-base completion tasks and on generation of molecular (graph) data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/23/2023

Enhancing Embedding Representations of Biomedical Data using Logic Knowledge

Knowledge Graph Embeddings (KGE) have become a quite popular class of mo...
research
03/07/2019

Lifted Weight Learning of Markov Logic Networks Revisited

We study lifted weight learning of Markov logic networks. We show that t...
research
04/21/2015

Reasoning about Unmodelled Concepts - Incorporating Class Taxonomies in Probabilistic Relational Models

A key problem in the application of first-order probabilistic methods is...
research
06/14/2016

Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge

We propose Logic Tensor Networks: a uniform framework for integrating au...
research
02/27/2018

Relational Reasoning for Markov Chains in a Probabilistic Guarded Lambda Calculus

We extend the simply-typed guarded λ-calculus with discrete probabilitie...
research
07/03/2018

Domain Aware Markov Logic Networks

Combining logic and probability has been a long standing goal of AI. Mar...
research
02/19/2020

A Generalizable Knowledge Framework for Semantic Indoor Mapping Based on Markov Logic Networks and Data Driven MCMC

In this paper, we propose a generalizable knowledge framework for data a...

Please sign up or login with your details

Forgot password? Click here to reset