Structured constraints on neural network layers are presented as a lever for stable, smooth, and scalable learning dynamics.
Gao and another, ``Learning stable graph neural networks via spectral regularization, '' in Asilomar Conference on Signals, Systems, and Computers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding Learning Dynamics Through Structured Representations
Structured constraints on neural network layers are presented as a lever for stable, smooth, and scalable learning dynamics.