xReceiver: a GNN approach to the evaluation of the decision-making process of passing options in football
summary
xReceiver is a Message‑Passing GNN that models teammates as nodes and potential passes as weighted edges (distance, angle, opponent pressure), trained on synchronized tracking + event data from professional matches including UEFA Nations League 2024 and World Cup qualifiers. Implemented with PyTorch Geometric MPNN, it achieves 65.22% top‑1 accuracy and 95.65% top‑3 accuracy, uses a star‑graph pass encoding for efficiency, leverages data.pie synchronization (≈20s/match on 8 cores), and evaluates over 1,000 passes in seconds.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 3:16Problem statement
- 6:09Data pipeline
- 11:46Passes to graphs
- 14:17Graph neural networks fundamentals
- 18:32GNNs in sports analytics
- 20:37Pass graph design
- 22:43X Receiver model
- 24:50Training metrics
related talks
30mApplying The Magic Of Neural Networks
32mCutting Edge Football Analytics in Python
42mHow Deep Learning is Revolutionizing Sports Analytics
35mFootball video analysis using Deep Learning
38mDeep Learning plays Handball
33mUsing machine learning to improve player safety in the NFL
34mAn AI assistant for football tactics
20mAI-Driven Real-Time Ball Tracking for Live Sports Streaming