Element-Wise Attention Layers: an option for optimization
share
The use of Attention Layers has become a trend since the popularization of the Transformer-based models, being the key element for many state-of-the-art models that have been developed through recent years. However, one of the biggest obstacles in implementing these architectures - as well as many others in Deep Learning Field - is the enormous amount of optimizing parameters they possess, which make its use conditioned on the availability of robust hardware. In this paper, it's proposed a new method of attention mechanism that adapts the Dot-Product Attention, which uses matrices multiplications, to become element-wise through the use of arrays multiplications. To test the effectiveness of such approach, two models (one with a VGG-like architecture and one with the proposed method) have been trained in a classification task using Fashion MNIST and CIFAR10 datasets. Each model has been trained for 10 epochs in a single Tesla T4 GPU from Google Colaboratory. The results show that this mechanism allows for an accuracy of 92 Fashion MNIST dataset, while reducing the number of parameters in 97 CIFAR10, the accuracy is still equivalent to 60 while using 50
READ FULL TEXT