Graph Representation Learning (GRL) has been advancing at an unprecedented rate. However, many results rely on careful design and tuning of architectures, objectives, and training schemes. We propose efficient GRL methods that optimize convexified objectives with known closed form solutions. Guaranteed convergence to a global optimum releases practitioners from hyper-parameter and architecture tuning. Nevertheless, our proposed method achieves competitive or state-of-the-art performance on popular GRL tasks while providing orders of magnitude speedup. Although the design matrix ($\mathbf{M}$) of our objective is expensive to compute, we exploit results from random matrix theory to approximate solutions in linear time while avoiding an explicit calculation of $\mathbf{M}$. Our code is online: http://github.com/samihaija/tf-fsvd

中文翻译：

---

通过独特的最佳解决方案进行快速图形学习

图表示学习（GRL）以前所未有的速度发展。但是，许多结果依赖于对体系结构，目标和培训方案的精心设计和调整。我们提出有效的GRL方法，以已知的封闭形式解决方案优化凸目标。保证收敛到全局最佳状态，使从业人员摆脱了超参数和体系结构调整。尽管如此，我们提出的方法在流行的GRL任务上实现了竞争性或最先进的性能，同时提供了数量级的加速。尽管我们目标的设计矩阵（$ \ mathbf {M} $）的计算成本很高，但我们利用随机矩阵理论的结果在线性时间内近似求解，同时避免了对$ \ mathbf {M} $的显式计算。我们的代码在线：http：//github.com/samihaija/tf-fsvd