将高维计算与图神经网络结合，实现高效精准的图学习。
HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing
- 用高维计算的绑定与打包操作融合图卷积
- 在同质与异质图上精度超越主流模型
- 速度比GNN和现有高维方法快近百倍，适合低功耗硬件
我们提出一种新算法 \\(\hdgc\)，将图卷积与高维计算中的绑定和打包操作相结合，用于归纳式图学习。在多种同质与异质图上，\hdgc\ 的预测精度优于主流图神经网络及先进的高维计算方法。在相同GPU平台上，相比最准确的测试方法，\hdgc\ 平均分别比 \gcnii\（图神经网络）和 \HDGL\（高维计算）快9561.0倍和144.5倍。由于大部分计算在二值向量上进行，预计 \hdgc\ 在类脑与新兴存内计算设备上具有优异能效表现。
原文摘要 · Abstract (English)
We present a novel algorithm, \hdgc, that marries graph convolution with binding and bundling operations in hyperdimensional computing for transductive graph learning. For prediction accuracy \hdgc outperforms major and popular graph neural network implementations as well as state-of-the-art hyperdimensional computing implementations for a collection of homophilic graphs and heterophilic graphs. Compared with the most accurate learning methodologies we have tested, on the same target GPU platform, \hdgc is on average 9561.0 and 144.5 times faster than \gcnii, a graph neural network implementation and HDGL, a hyperdimensional computing implementation, respectively. As the majority of the learning operates on binary vectors, we expect outstanding energy performance of \hdgc on neuromorphic and emerging process-in-memory devices.
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。