TY - JOUR

T1 - Federated Learning-Based Cross-Enterprise Recommendation With Graph Neural Networks

AU - Li, Zheng

AU - Bilal, Muhammad

AU - Xu, Xiaolong

AU - Jiang, Jielin

AU - Cui, Yan

PY - 2023/1/31

Y1 - 2023/1/31

N2 - Recommender systems are technology-driven marketing solutions for businesses that analyze user behavior data. However, collaborative data sharing between enterprises is often prohibited by privacy protection regulations, leading to insufficient data for graph neural networks (GNNs) training. Fortunately, federated learning (FL), a collaborative training framework without exposing source data, can be applied congruently. Nevertheless, most of FL-based GNN model training methods adopt federated averaging, which performs poorly on highly heterogeneous graph data. To solve this problem, a FL-based GNN Model Training framework for cross-enterprise recommendation, named FL-GMT, is proposed. Specifically, a GNN-based recommendation model is deployed as the local training model. Then, considering the performance inequity caused by uneven sample quality, a loss-based federated aggregation algorithm is designed, effectively improving the performance of disadvantaged participants. To improve the system stability at the end of the aggregation, a dynamic update method of loss attention is designed. Extensive experiments on benchmark datasets demonstrate that FL-GMT outperforms baselines in terms of system fairness, stability, and accuracy.

AB - Recommender systems are technology-driven marketing solutions for businesses that analyze user behavior data. However, collaborative data sharing between enterprises is often prohibited by privacy protection regulations, leading to insufficient data for graph neural networks (GNNs) training. Fortunately, federated learning (FL), a collaborative training framework without exposing source data, can be applied congruently. Nevertheless, most of FL-based GNN model training methods adopt federated averaging, which performs poorly on highly heterogeneous graph data. To solve this problem, a FL-based GNN Model Training framework for cross-enterprise recommendation, named FL-GMT, is proposed. Specifically, a GNN-based recommendation model is deployed as the local training model. Then, considering the performance inequity caused by uneven sample quality, a loss-based federated aggregation algorithm is designed, effectively improving the performance of disadvantaged participants. To improve the system stability at the end of the aggregation, a dynamic update method of loss attention is designed. Extensive experiments on benchmark datasets demonstrate that FL-GMT outperforms baselines in terms of system fairness, stability, and accuracy.

KW - Cross-enterprise recommendation

KW - federated learning (FL)

KW - graph neural network (GNN)

KW - user privacy protection

U2 - 10.1109/TII.2022.3203395

DO - 10.1109/TII.2022.3203395

M3 - Journal article

AN - SCOPUS:85137925587

VL - 19

SP - 673

EP - 682

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 1

ER -