PriorProbe: Recovering Individual-Level Priors for Personalizing Neural Networks in Facial Expression Recognition

2026-02-03

AI Summary

Existing approaches struggle to obtain unbiased and accurate individual cognitive priors for personalizing neural networks. To address this challenge, this work proposes PriorProbe, a novel framework that introduces, for the first time, a human-in-the-loop Markov Chain Monte Carlo (MCMCP) method to recover fine-grained, uniquely identifiable cognitive priors from individual behavioral responses. These priors are then integrated into a facial expression recognition network, providing deep models with a generalizable and interpretable personalization mechanism. Empirical results demonstrate that PriorProbe significantly improves individual prediction accuracy under ambiguous stimuli, outperforming existing baselines and alternative prior sources, while preserving strong discriminative performance on standard categorical labels.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Incorporating individual-level cognitive priors offers an important route to personalizing neural networks, yet accurately eliciting such priors remains challenging: existing methods either fail to uniquely identify them or introduce systematic biases. Here, we introduce PriorProbe, a novel elicitation approach grounded in Markov Chain Monte Carlo with People that recovers fine-grained, individual-specific priors. Focusing on a facial expression recognition task, we apply PriorProbe to individual participants and test whether integrating the recovered priors with a state-of-the-art neural network improves its ability to predict an individual's classification on ambiguous stimuli. The PriorProbe-derived priors yield substantial performance gains, outperforming both the neural network alone and alternative sources of priors, while preserving the network's inference on ground-truth labels. Together, these results demonstrate that PriorProbe provides a general and interpretable framework for personalizing deep neural networks.

Problem

• individual-level priors
• personalization
• facial expression recognition
• cognitive priors
• neural networks

Innovation

• PriorProbe
• individual-level priors
• personalized neural networks
• Markov Chain Monte Carlo with People
• facial expression recognition