CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations

2026-04-15

AI Summary

This work addresses the limitations of existing graph neural network–based game recommendation systems, which often suffer from oversmoothing due to neglecting individual player preference differences and struggle to balance accuracy with diversity. To overcome these challenges, we propose CPGRec+, a novel framework that integrates a Preference-aware Edge Reweighting (PER) mechanism with a large language model–driven Context-aware Representation Generation (PRG) module. By assigning signed edge weights to differentiate the strength of user interests and generating more discriminative representations for both users and games, CPGRec+ effectively captures nuanced preference signals. Experimental results on two real-world Steam datasets demonstrate that our approach significantly outperforms state-of-the-art baselines in both recommendation accuracy and diversity.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Preferences
• Game Theory and Economic Paradigms: Cooperative Game Theory

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network (GNN)-based methods primarily prioritize accuracy over diversity, overlooking their inherent trade-off. To address this, we previously proposed CPGRec, a balance-oriented gaming recommender system. However, CPGRec fails to account for critical disparities in player-game interactions, which carry varying significance in reflecting players' personal preferences and may exacerbate over-smoothness issues inherent in GNN-based models. Moreover, existing approaches underutilize the reasoning capabilities and extensive knowledge of large language models (LLMs) in addressing these limitations. To bridge this gap, we propose two new modules. First, Preference-informed Edge Reweighting (PER) module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions. Second, Preference-informed Representation Generation (PRG) module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests, thereby refining representations of players and games. Experiments on \textcolor{black}{two Steam datasets} demonstrate CPGRec+'s superior accuracy and diversity over state-of-the-art models. The code is accessible at https://github.com/HsipingLi/CPGRec-Plus.

Problem

• personalized recommendation
• graph neural networks
• accuracy-diversity trade-off
• over-smoothing
• player-game interactions

Innovation

• Preference-informed Edge Reweighting
• Preference-informed Representation Generation
• Graph Neural Networks
• Large Language Models
• Recommendation Diversity