Taxonomy grounded aggregation of classifiers with different label sets

TL;DR

This paper introduces a method for aggregating classifier predictions across different label sets by grounding them into a shared taxonomy, using a heuristic and a graphical model to improve consistency and accuracy.

Contribution

It proposes a novel approach combining heuristics and graphical models to unify diverse classifier outputs within a hierarchical taxonomy.

Findings

Effective aggregation of classifiers with different label sets.

Improved consistency in hierarchical classification.

Validated on image and text classification tasks.

Abstract

We describe the problem of aggregating the label predictions of diverse classifiers using a class taxonomy. Such a taxonomy may not have been available or referenced when the individual classifiers were designed and trained, yet mapping the output labels into the taxonomy is desirable to integrate the effort spent in training the constituent classifiers. A hierarchical taxonomy representing some domain knowledge may be different from, but partially mappable to, the label sets of the individual classifiers. We present a heuristic approach and a principled graphical model to aggregate the label predictions by grounding them into the available taxonomy. Our model aggregates the labels using the taxonomy structure as constraints to find the most likely hierarchically consistent class. We experimentally validate our proposed method on image and text classification tasks.