Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
This addresses the challenge of scalable sorting and ranking supervision for machine learning applications, though it is incremental as it builds on existing relaxations of sorting operations.
The paper tackles the problem of training neural networks with ordering constraints by proposing differentiable sorting networks that relax pairwise conditional swap operations, achieving stable training on large input sets of up to 1024 elements.
Sorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints. That is, the ground truth order of sets of samples is known, while their absolute values remain unsupervised. For that, we propose differentiable sorting networks by relaxing their pairwise conditional swap operations. To address the problems of vanishing gradients and extensive blurring that arise with larger numbers of layers, we propose mapping activations to regions with moderate gradients. We consider odd-even as well as bitonic sorting networks, which outperform existing relaxations of the sorting operation. We show that bitonic sorting networks can achieve stable training on large input sets of up to 1024 elements.