Multi-source Hierarchical Prediction Consolidation

TL;DR

This paper introduces a novel method for consolidating predictions from multiple sources within hierarchical label structures, effectively handling noisy, conflicting data in complex real-world applications like healthcare.

Contribution

It proposes a new hierarchical prediction consolidation approach with a closed-form solution, leveraging label hierarchies to improve aggregation accuracy in noisy multi-source environments.

Findings

Outperforms existing methods on synthetic datasets.

Effective in real-world healthcare data scenarios.

Handles noisy, conflicting multi-source predictions efficiently.

Abstract

In big data applications such as healthcare data mining, due to privacy concerns, it is necessary to collect predictions from multiple information sources for the same instance, with raw features being discarded or withheld when aggregating multiple predictions. Besides, crowd-sourced labels need to be aggregated to estimate the ground truth of the data. Because of the imperfect predictive models or human crowdsourcing workers, noisy and conflicting information is ubiquitous and inevitable. Although state-of-the-art aggregation methods have been proposed to handle label spaces with flat structures, as the label space is becoming more and more complicated, aggregation under a label hierarchical structure becomes necessary but has been largely ignored. These label hierarchies can be quite informative as they are usually created by domain experts to make sense of highly complex label correlations for many real-world cases like protein functionality interactions or disease relationships. We propose a novel multi-source hierarchical prediction consolidation method to effectively exploits the complicated hierarchical label structures to resolve the noisy and conflicting information that inherently originates from multiple imperfect sources. We formulate the problem as an optimization problem with a closed-form solution. The proposed method captures the smoothness overall information sources as well as penalizing any consolidation result that violates the constraints derived from the label hierarchy. The hierarchical instance similarity, as well as the consolidation result, are inferred in a totally unsupervised, iterative fashion. Experimental results on both synthetic and real-world datasets show the effectiveness of the proposed method over existing alternatives.