提出图保留网络，高效处理动态图数据
Graph Retention Networks for Dynamic Graphs
- 将保留机制引入图数据，支持并行训练和低延迟推理
- 推理速度比现有方法快86.7倍，训练耗时大幅降低
- 适合大规模动态图任务，尤其对实时性要求高的场景
本文提出图保留网络（GRN），一种统一的动态图深度学习架构。GRN将保留机制扩展至图数据，引入三种核心计算范式：可并行训练、低成本$/mathcal{O}(1)$推理和长周期分块训练，实现效率、效果与可扩展性的最优平衡。在基准数据集上的大量实验表明，该模型在边级预测和节点级分类任务中表现优异，训练延迟显著降低，GPU内存开销减少，推理吞吐量相比最先进基线提升高达86.7倍。GRN在多种动态图基准上均达到竞争力性能，展现出对多样化任务的强适应性。
原文摘要 · Abstract (English)
In this paper, we propose Graph Retention Networks (GRNs) as a unified architecture for deep learning on dynamic graphs. The GRN extends the concept of retention into dynamic graph data as graph retention, equipping the model with three key computational paradigms: parallelizable training, low-cost $\mathcal{O}(1)$ inference, and long-term chunkwise training. This architecture achieves an optimal balance between efficiency, effectiveness, and scalability. Extensive experiments on benchmark datasets demonstrate its strong performance in both edge-level prediction and node-level classification tasks with significantly reduced training latency, lower GPU memory overhead, and improved inference throughput by up to 86.7x compared to SOTA baselines. The proposed GRN architecture achieves competitive performance across diverse dynamic graph benchmarks, demonstrating its adaptability to a wide range of tasks.
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。