Aggregating Learned Probabilistic Beliefs

TL;DR

This paper introduces a framework for aggregating probabilistic beliefs from multiple experts, proposing a LinOP-based learning algorithm that effectively combines Bayesian network representations and performs well in preliminary tests.

Contribution

It presents a novel framework for belief aggregation considering data generation and introduces a LinOP-based algorithm for combining expert distributions.

Findings

LinOP is well-suited for belief aggregation tasks.

The proposed algorithm performs well in preliminary experiments.

The framework effectively measures aggregation accuracy based on data samples.

Abstract

We consider the task of aggregating beliefs of severalexperts. We assume that these beliefs are represented as probabilitydistributions. We argue that the evaluation of any aggregationtechnique depends on the semantic context of this task. We propose aframework, in which we assume that nature generates samples from a`true' distribution and different experts form their beliefs based onthe subsets of the data they have a chance to observe. Naturally, theideal aggregate distribution would be the one learned from thecombined sample sets. Such a formulation leads to a natural way tomeasure the accuracy of the aggregation mechanism.We show that the well-known aggregation operator LinOP is ideallysuited for that task. We propose a LinOP-based learning algorithm,inspired by the techniques developed for Bayesian learning, whichaggregates the experts' distributions represented as Bayesiannetworks. Our preliminary experiments show that this algorithmperforms well in practice.