Learning Distributional Programs for Relational Autocompletion

TL;DR

This paper introduces DiceML, a novel method for relational autocompletion that learns distributional logic programs from data, effectively handling missing data and both discrete and continuous distributions within a probabilistic logic framework.

Contribution

DiceML is the first approach to learn distributional clauses with statistical models for relational autocompletion, integrating rule learning with probabilistic modeling.

Findings

Effective autocompletion with missing data demonstrated

Handles both discrete and continuous distributions

Shows promising empirical results

Abstract

Relational autocompletion is the problem of automatically filling out some missing values in multi-relational data. We tackle this problem within the probabilistic logic programming framework of Distributional Clauses (DC), which supports both discrete and continuous probability distributions. Within this framework, we introduce DiceML { an approach to learn both the structure and the parameters of DC programs from relational data (with possibly missing data). To realize this, DiceML integrates statistical modeling and distributional clauses with rule learning. The distinguishing features of DiceML are that it 1) tackles autocompletion in relational data, 2) learns distributional clauses extended with statistical models, 3) deals with both discrete and continuous distributions, 4) can exploit background knowledge, and 5) uses an expectation-maximization based algorithm to cope with missing data. The empirical results show the promise of the approach, even when there is missing data.