Friend Ranking in Online Games via Pre-training Edge Transformers

TL;DR

This paper introduces a novel Edge Transformer model pre-trained with masked auto-encoders for friend recall in online games, leveraging feature information and historical data to improve link prediction accuracy.

Contribution

It proposes a new Edge Transformer approach with pre-training for friend recall, addressing limitations of traditional methods by incorporating comprehensive feature and event data.

Findings

Achieves state-of-the-art offline results

Demonstrates significant online A/B test improvements

Outperforms existing link prediction methods

Abstract

Friend recall is an important way to improve Daily Active Users (DAU) in online games. The problem is to generate a proper lost friend ranking list essentially. Traditional friend recall methods focus on rules like friend intimacy or training a classifier for predicting lost players' return probability, but ignore feature information of (active) players and historical friend recall events. In this work, we treat friend recall as a link prediction problem and explore several link prediction methods which can use features of both active and lost players, as well as historical events. Furthermore, we propose a novel Edge Transformer model and pre-train the model via masked auto-encoders. Our method achieves state-of-the-art results in the offline experiments and online A/B Tests of three Tencent games.