Spatio-temporal graph neural networks for human–AI collaborative decision-making

Le résumé fourni par la source

Collaborative decision-making (CDM) is essential in different domains where integrating diverse perspectives improves classification accuracy. Traditional aggregation methods, such as majority voting (MV), are static and fail to capture the dynamic, real-time interactions among decision-makers. We propose a task- and label-independent framework based on spatio-temporal graph neural networks (STGNNs) to model CDM as an evolving process. The framework represents participants and classification options as nodes in graph sequences, capturing relational dependencies ( e.g. , agreement clusters) and temporal patterns ( e.g. , convergence to consensus). It integrates a graph neural network with a gated recurrent unit to jointly model spatial and temporal dynamics, and introduces an auxiliary loss that reinforces agreement structure and option alignment in the embedding space. We evaluated the framework on five expert-driven image classification tasks in biology and pathology using a web-based collaborative platform. In human-only settings, STGNNs achieved a global accuracy of 77.6% ( Δ = + 4 . 3 % over MV, p < 0 . 001 ). When extended to mixed human-AI teams, a meta-learning aggregator combining STGNN and AI agent predictions achieved a global accuracy of 81.4%, outperforming both human-only models and MV. These findings demonstrate the utility of STGNNs for modeling latent decision dynamics and enhancing collaborative performance in complex, ambiguous settings. The task- and label-independence of the framework suggests broad applicability across domains. • Propose spatio-temporal GNNs to model real-time collaborative decision-making tasks. • Improves classification accuracy by 4.3% over majority voting in human-only settings. • Meta-learning aggregation of human-AI input lifts accuracy to 81.4%, beating baseline. • Framework generalizes across domains due to its task- and label-agnostic architecture.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.