Convolution, attention and structure embedding.

By Jean-Marc Andreoli. 2019

27 citations recorded by the source corpus.

Deep neural networks are composed of layers of parametrised linear operations intertwined with non linear activations. In basic models, such as the multi-layer perceptron, a linear layer operates on a simple input vector embedding of the instance being processed, and produces an output vector embedding by straight multiplication by a matrix parameter. In more complex models, the input and output are structured and their embeddings are higher order tensors. The parameter of each linear operation must then be controlled so as not to explode with the complexity of the structures involved. This is essentially the role of convolution models, which exist in many flavours dependent on the type of structure they deal with (grids, networks, time series etc.). We present here a unified framework which aims at capturing the essence of these diverse models, allowing a systematic analysis of their properties and their mutual enrichment. We also show that attention models naturally fit in the same framework: attention is convolution in which the structure itself is adaptive, and learnt, instead of being given a priori.

Subfields: Artificial Intelligence, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Model Architectures

Citations in the corpus

On the Relationship between Self-Attention and Convolutional Layers (2019, background): “The closest work in bridging the gap between attention and convolution is due to Andreoli (2019).”
Polarized Self-Attention: Towards High-quality Pixel-wise Regression (2021, background): “Attention mechanisms have been introduced into many visual tasks to address the weakness of standard convolutions [35][2][1][37][3].”