# Anytime Neural Prediction via Slicing Networks Vertically

arXiv: https://arxiv.org/abs/1807.02609 · HTML: https://mlsanity.com/paper/1807.02609/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2018.

## Built on by (most cited first, 7 of 7)

- [Dynamic Slimmable Network](https://mlsanity.com/paper/2103.13258/) (2021)
- [ElasticTok: Adaptive Tokenization for Image and Video](https://mlsanity.com/paper/2410.08368/) (2024)
- [Automated Progressive Learning for Efficient Training of Vision Transformers](https://mlsanity.com/paper/2203.14509/) (2022)
- [Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss](https://mlsanity.com/paper/2102.09808/) (2021)
- [DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers](https://mlsanity.com/paper/2109.10060/) (2021)
- [Efficient Training of Large Vision Models via Advanced Automated Progressive Learning](https://mlsanity.com/paper/2410.00350/) (2024)
- [TIPS: Topologically Important Path Sampling for Anytime Neural Networks](https://mlsanity.com/paper/2305.08021/) (2023)

## Abstract (arXiv)

The pioneer deep neural networks (DNNs) have emerged to be deeper or wider for improving their accuracy in various applications of artificial intelligence. However, DNNs are often too heavy to deploy in practice, and it is often required to control their architectures dynamically given computing resource budget, i.e., anytime prediction. While most existing approaches have focused on training multiple shallow sub-networks jointly, we study training thin sub-networks instead. To this end, we first build many inclusive thin sub-networks (of the same depth) under a minor modification of existing multi-branch DNNs, and found that they can significantly outperform the state-of-art dense architecture for anytime prediction. This is remarkable due to their simplicity and effectiveness, but training many thin sub-networks jointly faces a new challenge on training complexity. To address the issue, we also propose a novel DNN architecture by forcing a certain sparsity pattern on multi-branch network parameters, making them train efficiently for the purpose of anytime prediction. In our experiments on the ImageNet dataset, its sub-networks have up to 43.3% smaller sizes (FLOPs) compared to those of the state-of-art anytime model with respect to the same accuracy. Finally, we also propose an alternative task under the proposed architecture using a hierarchical taxonomy, which brings a new angle for anytime prediction.