Neural Bradley-Terry Rating: Quantifying Properties from Comparisons
This addresses the challenge of learning unobservable properties for applications like item evaluation, but it appears incremental as it builds on existing Bradley-Terry models with neural network integration.
The paper tackles the problem of quantifying properties that lack metrics by introducing Neural Bradley-Terry Rating (NBTR), a framework that integrates the Bradley-Terry model into neural networks to estimate properties from comparisons, and it demonstrates successful quantification in experiments.
Many properties in the real world don't have metrics and can't be numerically observed, making them difficult to learn. To deal with this challenging problem, prior works have primarily focused on estimating those properties by using graded human scores as the target label in the training. Meanwhile, rating algorithms based on the Bradley-Terry model are extensively studied to evaluate the competitiveness of players based on their match history. In this paper, we introduce the Neural Bradley-Terry Rating (NBTR), a novel machine learning framework designed to quantify and evaluate properties of unknown items. Our method seamlessly integrates the Bradley-Terry model into the neural network structure. Moreover, we generalize this architecture further to asymmetric environments with unfairness, a condition more commonly encountered in real-world settings. Through experimental analysis, we demonstrate that NBTR successfully learns to quantify and estimate desired properties.