论文标题
设置标准和均衡的跳过连接：将深度放入深处
Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets
论文作者
论文摘要
置换不变的神经网络是从集合进行预测的有前途的工具。但是，我们表明，现有的置换式体系结构，深度集和固定的变压器可能会在深度时消失或爆炸。此外，层规范（SET变压器中选择的归一化）可能会通过删除对预测有用的信息来损害性能。为了解决这些问题，我们介绍了白皮剩余连接的干净路径原理，并制定了设置规范，这是针对集合量身定制的标准化。有了这些，我们构建了深度集++和SET Transformer ++的模型，这些模型比其在各种任务套件上的原始配音都具有可比或更好的性能。我们还引入了Flow-RBC，这是一个新的单细胞数据集和置换不变预测的现实应用。我们在此处开放数据和代码：https：//github.com/rajesh-lab/deep_permunt_invariant。
Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set Transformer, can suffer from vanishing or exploding gradients when they are deep. Additionally, layer norm, the normalization of choice in Set Transformer, can hurt performance by removing information useful for prediction. To address these issues, we introduce the clean path principle for equivariant residual connections and develop set norm, a normalization tailored for sets. With these, we build Deep Sets++ and Set Transformer++, models that reach high depths with comparable or better performance than their original counterparts on a diverse suite of tasks. We additionally introduce Flow-RBC, a new single-cell dataset and real-world application of permutation invariant prediction. We open-source our data and code here: https://github.com/rajesh-lab/deep_permutation_invariant.
