论文标题
使用连续的k-nearest邻居图形图形来保存自动编码器的局部距离
Local Distance Preserving Auto-encoders using Continuous k-Nearest Neighbours Graphs
论文作者
论文摘要
保留数据中相似性的自动编码器模型是表示学习中的流行工具。在本文中，我们介绍了几种自动编码器模型，这些模型在从数据空间到潜在空间时保留本地距离。我们使用基于连续的K-Nearthiend邻居图的局部距离保留损失，该图已知可以同时捕获所有尺度的拓扑特征。为了提高培训绩效，我们将学习作为约束优化问题，并保存本地距离，作为主要目标和重建精度作为约束。我们将这种方法推广到分层变分自动编码器，从而学习具有几何一致的潜在和数据空间的生成模型。我们的方法在几个标准数据集和评估指标上提供了最先进的性能。
Auto-encoder models that preserve similarities in the data are a popular tool in representation learning. In this paper we introduce several auto-encoder models that preserve local distances when mapping from the data space to the latent space. We use a local distance preserving loss that is based on the continuous k-nearest neighbours graph which is known to capture topological features at all scales simultaneously. To improve training performance, we formulate learning as a constraint optimisation problem with local distance preservation as the main objective and reconstruction accuracy as a constraint. We generalise this approach to hierarchical variational auto-encoders thus learning generative models with geometrically consistent latent and data spaces. Our method provides state-of-the-art performance across several standard datasets and evaluation metrics.
