Reinforcement Learning Based Layer Skipping Vision Transformer for Efficient Inference

No Thumbnail Available

Date

2023-05

Journal Title

Journal ISSN

Volume Title

Publisher

Addis Ababa University

Abstract

Recent advancements in language and vision tasks owe their success largely to the Transformer architecture. However, the computational requirements of these models have limited their applicability in resource-constrained environments. To address this issue, various techniques, such as Weight pruning, have been proven effective in reducing the deployment cost of such models. Additionally, methods tailored just for transformers, such as linear self-attention and token early exiting, have shown promise in making transformers more cost-effective. Nevertheless, these techniques often come with drawbacks such as decreased performance or additional training costs. This thesis proposes a layer-skipping dynamic vision transformer (ViT) network that skips layers depending on the given input based on decisions made by a reinforcement learning agent (RL). To the best of our knowledge, this work is the first to introduce such a model that not only significantly reduces the computational demands of transformers, but also improves performance. The proposed technique is extensively tested on various model sizes and three standard benchmarking datasets: CIFAR-10, CIFAR-100, and Tiny-ImageNet. First, we show that the dynamic models improve performance when compared to their state-of-the-art static counterparts. Second, we show that in comparison to these static models, they achieve an average inference speed boost of 53% across different model sizes, datasets, and batch sizes. Similarly, the technique lowers working space memory consumption by 53%, enabling larger input processing at a time without imposing an accuracy-speed trade-off. In addition, these models achieve very high accuracy when tested in transfer learning scenarios. We then show that, although these models have high accuracy, they can be optimized even more through post-training using genetic algorithms (NSGA-II). As such, we propose the joint RL-NSGA-II optimization technique, where the GA is aware of the dynamics of skipping through the RL reward. These optimized models achieve competitive performance compared to the already high-performing dynamic models while reducing the number of layers by 33%. In real-world applications, the technique translates to an average of 53% faster throughput, reduced power consumption, or lower computing costs without loss of accuracy.

Description

Keywords

Based Layer Skipping Vision Transformer, Efficient Inference

Citation