Boosting Team Modeling through Tempo-Relational Representation Learning

2025-07-17

AI Summary

Team modeling faces the challenge of jointly capturing temporal dynamics and relational structure, with existing methods failing to unify multi-construct prediction (e.g., leadership emergence, collaboration patterns) and deliver interpretable, actionable recommendations. To address this, we propose TRENN—a Temporal Relational Evolutional Neural Network—and its multi-task extension, MT-TRENN. TRENN is the first framework to jointly integrate automated temporal graph construction, spatiotemporal graph neural encoding, multi-task joint prediction, and a dual-path interpretability module. It unifies relational encoding, dynamic graph learning, and social embedding to jointly model time-evolving interactions and structural dependencies in team communication. Evaluated on multiple real-world team datasets, TRENN significantly outperforms unidimensional baselines (average improvement of 12.7% in predictive accuracy) and generates operationally actionable insights—particularly for high-risk collaborative scenarios—along with concrete team efficacy optimization suggestions. This work establishes a novel paradigm for intelligent, interpretable team decision support.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Teamwork
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Team modeling remains a fundamental challenge at the intersection of Artificial Intelligence and the Social Sciences. Social Science research emphasizes the need to jointly model dynamics and relations, while practical applications demand unified models capable of inferring multiple team constructs simultaneously, providing interpretable insights and actionable recommendations to enhance team performance. However, existing works do not meet these practical demands. To bridge this gap, we present TRENN, a novel tempo-relational architecture that integrates: (i) an automatic temporal graph extractor, (ii) a tempo-relational encoder, (iii) a decoder for team construct prediction, and (iv) two complementary explainability modules. TRENN jointly captures relational and temporal team dynamics, providing a solid foundation for MT-TRENN, which extends TReNN by replacing the decoder with a multi-task head, enabling the model to learn shared Social Embeddings and simultaneously predict multiple team constructs, including Emergent Leadership, Leadership Style, and Teamwork components. Experimental results demonstrate that our approach significantly outperforms approaches that rely exclusively on temporal or relational information. Additionally, experimental evaluation has shown that the explainability modules integrated in MT-TRENN yield interpretable insights and actionable suggestions to support team improvement. These capabilities make our approach particularly well-suited for Human-Centered AI applications, such as intelligent decision-support systems in high-stakes collaborative environments.

Problem

• Modeling team dynamics and relations jointly
• Predicting multiple team constructs simultaneously
• Providing interpretable insights for team improvement

Innovation

• TRENN integrates temporal graph extractor and encoder
• MT-TRENN uses multi-task head for shared embeddings
• Explainability modules provide actionable team insights