面向图神经网络的神经优先级队列
Neural Priority Queues for Graph Neural Networks
AI总结：
针对图神经算法推理中外部存储增强研究不足的问题，提出可微的神经优先级队列模块，验证其符合存储设计准则，且在算法推理和长程图交互任务上表现有效。
摘要：
图神经网络（GNNs）已在神经算法推理领域取得显著成果。许多传统算法会借助数据结构形式的显式存储器运行，但目前针对外部存储器增强GNN的研究仍较为有限。本文提出了适用于GNN的神经优先级队列——一种算法优先级队列的可微对等结构。我们提出并论证了存储模块的设计准则，证明神经优先级队列符合该准则，并阐释了其在算法推理中的应用逻辑。CLRS-30数据集上的实验结果进一步验证了上述结论。此外，我们发现神经优先级队列可有效捕捉长程交互，这一点在长程图基准（Long-Range Graph Benchmark）的一个数据集上得到了实证支持。
英文摘要：
Graph Neural Networks (GNNs) have shown considerable success in neural algorithmic reasoning. Many traditional algorithms make use of an explicit memory in the form of a data structure. However, there has been limited exploration on augmenting GNNs with external memory. In this paper, we present Neural Priority Queues, a differentiable analogue to algorithmic priority queues, for GNNs. We propose and motivate a desiderata for memory modules, and show that Neural PQs exhibit the desiderata, and reason about their use with algorithmic reasoning. This is further demonstrated by empirical results on the CLRS-30 dataset. Furthermore, we find the Neural PQs useful in capturing long-range interactions, as empirically shown on a dataset from the Long-Range Graph Benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
