Homogeneous linear inequality constraints for neural network activations
Frerix T, Niessner M, Cremers D (2020)
Publication Type: Conference contribution
Publication year: 2020
Publisher: IEEE Computer Society
Book Volume: 2020-June
Pages Range: 3229-3234
Conference Proceedings Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Event location: Virtual, Online, USA
ISBN: 9781728193601
DOI: 10.1109/CVPRW50498.2020.00382
Abstract
We propose a method to impose homogeneous linear inequality constraints of the form Ax ≤ 0 on neural network activations. The proposed method allows a data-driven training approach to be combined with modeling prior knowledge about the task. One way to achieve this task is by means of a projection step at test time after unconstrained training. However, this is an expensive operation. By directly incorporating the constraints into the architecture, we can significantly speed-up inference at test time; for instance, our experiments show a speed-up of up to two orders of magnitude over a projection method. Our algorithm computes a suitable parameterization of the feasible set at initialization and uses standard variants of stochastic gradient descent to find solutions to the constrained network. Thus, the modeling constraints are always satisfied during training. Crucially, our approach avoids to solve an optimization problem at each training step or to manually trade-off data and constraint fidelity with additional hyperparameters. We consider constrained generative modeling as an important application domain and experimentally demonstrate the proposed method by constraining a variational autoencoder.
Involved external institutions
Germany (DE)How to cite
APA:
Frerix, T., Niessner, M., & Cremers, D. (2020). Homogeneous linear inequality constraints for neural network activations. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 3229-3234). Virtual, Online, USA: IEEE Computer Society.
MLA:
Frerix, Thomas, Matthias Niessner, and Daniel Cremers. "Homogeneous linear inequality constraints for neural network activations." Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020, Virtual, Online, USA IEEE Computer Society, 2020. 3229-3234.
BibTeX: Download