Predicting Quality of Video Gaming Experience Using Global-Scale Telemetry Data and Federated Learning

2024-12-12

arXiv.org

AI Summary

This paper addresses privacy preservation and cold-start challenges in FPS performance prediction for games—specifically, how to deliver personalized FPS distribution estimates for new users or new games without collecting sensitive device-level user data. Method: We propose a novel framework integrating pluggable knowledge kernels with federated learning. It jointly models player hardware configurations, game characteristics, and socioeconomic factors, leveraging telemetry data from 100,000 users across 224 countries and 835 games. Heterogeneous multi-source features are fused via Wasserstein-distance-optimized embedding, and learnable knowledge kernels enable cross-device–cross-game knowledge transfer. Contribution/Results: We introduce the first privacy-safe FPS distribution prediction paradigm, effectively mitigating cold-start issues. Evaluated on real-world data, our method achieves a mean Wasserstein distance of 0.469—outperforming all baselines—demonstrating superior calibration of predicted FPS distributions.

Technology Category

• Machine Learning: Privacy
• Game Theory and Economic Paradigms: Adversarial Learning
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Frames Per Second (FPS) significantly affects the gaming experience. Providing players with accurate FPS estimates prior to purchase benefits both players and game developers. However, we have a limited understanding of how to predict a game's FPS performance on a specific device. In this paper, we first conduct a comprehensive analysis of a wide range of factors that may affect game FPS on a global-scale dataset to identify the determinants of FPS. This includes player-side and game-side characteristics, as well as country-level socio-economic statistics. Furthermore, recognizing that accurate FPS predictions require extensive user data, which raises privacy concerns, we propose a federated learning-based model to ensure user privacy. Each player and game is assigned a unique learnable knowledge kernel that gradually extracts latent features for improved accuracy. We also introduce a novel training and prediction scheme that allows these kernels to be dynamically plug-and-play, effectively addressing cold start issues. To train this model with minimal bias, we collected a large telemetry dataset from 224 countries and regions, 100,000 users, and 835 games. Our model achieved a mean Wasserstein distance of 0.469 between predicted and ground truth FPS distributions, outperforming all baseline methods.

Problem

• Predict FPS for gaming experience
• Use federated learning for privacy
• Analyze global telemetry data

Innovation

• Federated learning ensures user privacy
• Dynamic plug-and-play kernels address cold start
• Global telemetry data enhances accuracy