Paper ID: 2203.14768

Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks

Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari, Francesco Conti, Lorenzo Lamberti, Enrico Macii, Luca Benini, Massimo Poncino

Temporal Convolutional Networks (TCNs) are promising Deep Learning models for time-series processing tasks. One key feature of TCNs is time-dilated convolution, whose optimization requires extensive experimentation. We propose an automatic dilation optimizer, which tackles the problem as a weight pruning on the time-axis, and learns dilation factors together with weights, in a single training. Our method reduces the model size and inference latency on a real SoC hardware target by up to 7.4x and 3x, respectively with no accuracy drop compared to a network without dilation. It also yields a rich set of Pareto-optimal TCNs starting from a single model, outperforming hand-designed solutions in both size and accuracy.

Submitted: Mar 28, 2022