Symmetry Structured Convolutional Neural Networks
This work addresses efficiency and accuracy challenges in specific domains like recommendation systems and bioinformatics, but it is incremental as it builds on existing CNN methods.
The authors tackled the problem of modeling pairwise relationships in sequential recommendation and secondary structure inference by developing a CNN architecture that preserves symmetry in spatial dimensions, resulting in improved performance with fewer parameters.
We consider Convolutional Neural Networks (CNNs) with 2D structured features that are symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships for a sequential recommendation problem, as well as secondary structure inference problems of RNA and protein sequences. We develop a CNN architecture that generates and preserves the symmetry structure in the network's convolutional layers. We present parameterizations for the convolutional kernels that produce update rules to maintain symmetry throughout the training. We apply this architecture to the sequential recommendation problem, the RNA secondary structure inference problem, and the protein contact map prediction problem, showing that the symmetric structured networks produce improved results using fewer numbers of machine parameters.