Player-Team Heterogeneous Interaction Graph Transformer for Soccer Outcome Prediction

2025-07-14

AI Summary

Existing football prediction methods often overlook the heterogeneity of player–team interactions, limiting their ability to capture authentic match dynamics. To address this, we propose HIGFormer: a model that constructs a two-tier heterogeneous interaction graph—comprising player-level and team-level subgraphs—to jointly model fine-grained individual behaviors and high-level collective coordination. HIGFormer introduces a graph-enhanced Transformer architecture integrating localized graph convolutions, multi-level attention mechanisms, and cross-layer feature alignment, enabling end-to-end learning of dynamic spatiotemporal representations. Evaluated on the large-scale WyScout dataset, HIGFormer achieves statistically significant improvements over state-of-the-art baselines in match outcome (win-draw-loss) prediction accuracy. Moreover, it delivers interpretable outputs—including player contribution scores and tactical association maps—facilitating scouting evaluation and data-informed tactical decision-making.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Feature Construction/Reformulation
• Multiagent Systems: Teamwork

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Predicting soccer match outcomes is a challenging task due to the inherently unpredictable nature of the game and the numerous dynamic factors influencing results. While it conventionally relies on meticulous feature engineering, deep learning techniques have recently shown a great promise in learning effective player and team representations directly for soccer outcome prediction. However, existing methods often overlook the heterogeneous nature of interactions among players and teams, which is crucial for accurately modeling match dynamics. To address this gap, we propose HIGFormer (Heterogeneous Interaction Graph Transformer), a novel graph-augmented transformer-based deep learning model for soccer outcome prediction. HIGFormer introduces a multi-level interaction framework that captures both fine-grained player dynamics and high-level team interactions. Specifically, it comprises (1) a Player Interaction Network, which encodes player performance through heterogeneous interaction graphs, combining local graph convolutions with a global graph-augmented transformer; (2) a Team Interaction Network, which constructs interaction graphs from a team-to-team perspective to model historical match relationships; and (3) a Match Comparison Transformer, which jointly analyzes both team and player-level information to predict match outcomes. Extensive experiments on the WyScout Open Access Dataset, a large-scale real-world soccer dataset, demonstrate that HIGFormer significantly outperforms existing methods in prediction accuracy. Furthermore, we provide valuable insights into leveraging our model for player performance evaluation, offering a new perspective on talent scouting and team strategy analysis.

Problem

• Predicting soccer match outcomes with dynamic factors
• Modeling heterogeneous player-team interactions accurately
• Improving prediction accuracy using graph-augmented transformers

Innovation

• Heterogeneous Interaction Graph Transformer model
• Multi-level player and team interaction framework
• Graph-augmented transformer for soccer prediction