论文标题
使用多集变压器在多个集合上学习功能
Learning Functions on Multiple Sets using Multi-Set Transformers
论文作者
论文摘要
我们为多个置换不变的集合提供了一种一般的深度体系结构，以学习功能。我们还展示了如何通过维度等值的任何维度元素概括到任何维度元素的集合。我们证明了我们的体系结构是这些功能的通用近似值，并且在各种任务上的现有方法显示了较高的结果，包括计数任务，对齐任务，可区分性任务和统计距离测量值。最后一项任务在机器学习中非常重要。尽管我们的方法非常笼统，但我们证明它可以产生近似KL差异和相互信息的近似估计，这些估计比以前专门设计以近似这些统计距离的技术更准确。
We propose a general deep architecture for learning functions on multiple permutation-invariant sets. We also show how to generalize this architecture to sets of elements of any dimension by dimension equivariance. We demonstrate that our architecture is a universal approximator of these functions, and show superior results to existing methods on a variety of tasks including counting tasks, alignment tasks, distinguishability tasks and statistical distance measurements. This last task is quite important in Machine Learning. Although our approach is quite general, we demonstrate that it can generate approximate estimates of KL divergence and mutual information that are more accurate than previous techniques that are specifically designed to approximate those statistical distances.
