论文标题
在顶级建议任务上的双曲几何模型的性能
Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks
论文作者
论文摘要
我们引入了一个基于双曲线几何形状的简单自动编码器，以解决标准协作过滤问题。与许多现代深度学习技术相反，我们仅使用单个隐藏层构建解决方案。值得注意的是，即使采用这种简约的方法，我们不仅要优于欧几里得的表现，而且还取得了当前最新的竞争性能。我们还探讨了空间曲率对双曲线模型质量的影响，并提出了一种有效的数据驱动方法来估计其最佳值。
We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem. In contrast to many modern deep learning techniques, we build our solution using only a single hidden layer. Remarkably, even with such a minimalistic approach, we not only outperform the Euclidean counterpart but also achieve a competitive performance with respect to the current state-of-the-art. We additionally explore the effects of space curvature on the quality of hyperbolic models and propose an efficient data-driven method for estimating its optimal value.
