让图神经网络提前输出结果，提速同时不损失甚至提升预测准确率。
Early-Exit Graph Neural Networks for Link Prediction
- 通过隐式架构设计实现早期退出，无需额外损失函数。
- 在HeaRT基准上显著提升GCN和SAS-GNN的推理速度，性能更优。
- 适合需要低延迟的大型图数据场景，如实时推荐系统。
图神经网络在各类网络结构中的链接预测表现优异；然而，其推理速度与精度之间的权衡问题尚未得到充分研究。尽管在小型基准上推理时间影响不大，但在大规模场景中延迟会限制实际应用。本文探索了适用于图神经网络的早期退出策略，以加速链接预测。该方法不依赖辅助损失来强制早期退出，而是让其作为架构的隐含特性自然产生。实验表明，该方法在多个设置下均能实现有效早期退出，使基于GCN和SAS-GNN主干的模型在HeaRT基准上的帕累托前沿向左上方移动。结果表明，在多数链接预测任务中，可显著提升推理速度，同时几乎不损失甚至提升预测质量。代码已开源：https://github.com/knyazer/link_prediction。
原文摘要 · Abstract (English)
Graph Neural Networks are great for link prediction in various network-like structures; however, the question of their speed/quality tradeoff has been barely studied. While in practice the time it takes to do inference matters little for small benchmarks, the latency does limit applicability in large-scale domains. In this work, we explore early-exiting strategies that can be applied to Graph Neural Networks to solve the problem of link-prediction faster. We use no auxiliary losses to enforce early exiting, allowing it to emerge as an implicit property of the architecture. We show that our method enables early exiting in several setups, moving the Pareto frontier on the HeaRT benchmark for GCN and SAS-GNN backbones. Our findings show that inference speed of GNNs on many link-prediction problems can be improved, while losing little, or even winning in terms of prediction quality. The code is available in our repository: https://github.com/knyazer/link_prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。