Macro Graph Neural Networks for Online Billion-Scale Recommender Systems

TL;DR

This paper introduces Macro Graph Neural Networks (MacGNN) and the Macro Recommendation Graph (MAG) to efficiently and accurately predict click-through rates in billion-scale recommender systems, overcoming computational and sampling challenges.

Contribution

The paper proposes a macro-level graph structure and tailored GNNs that reduce complexity and improve recommendation accuracy in billion-scale systems, demonstrated on industrial and benchmark datasets.

Findings

MacGNN outperforms twelve CTR baselines in offline experiments.

MacGNN achieves superior online A/B test results.

MAG reduces node count from billions to hundreds, enabling efficient computation.

Abstract

Predicting Click-Through Rate (CTR) in billion-scale recommender systems poses a long-standing challenge for Graph Neural Networks (GNNs) due to the overwhelming computational complexity involved in aggregating billions of neighbors. To tackle this, GNN-based CTR models usually sample hundreds of neighbors out of the billions to facilitate efficient online recommendations. However, sampling only a small portion of neighbors results in a severe sampling bias and the failure to encompass the full spectrum of user or item behavioral patterns. To address this challenge, we name the conventional user-item recommendation graph as "micro recommendation graph" and introduce a more suitable MAcro Recommendation Graph (MAG) for billion-scale recommendations. MAG resolves the computational complexity problems in the infrastructure by reducing the node count from billions to hundreds. Specifically, MAG groups micro nodes (users and items) with similar behavior patterns to form macro nodes. Subsequently, we introduce tailored Macro Graph Neural Networks (MacGNN) to aggregate information on a macro level and revise the embeddings of macro nodes. MacGNN has already served Taobao's homepage feed for two months, providing recommendations for over one billion users. Extensive offline experiments on three public benchmark datasets and an industrial dataset present that MacGNN significantly outperforms twelve CTR baselines while remaining computationally efficient. Besides, online A/B tests confirm MacGNN's superiority in billion-scale recommender systems.