Trap of Feature Diversity in the Learning of MLPs
This addresses a specific optimization problem in MLP training, but it is incremental as it builds on known phenomena without introducing new methods.
The paper investigates the two-phase training phenomenon in MLPs, where feature diversity decreases in the first phase, hindering optimization, and explains this through learning dynamics and how four operations can mitigate it.
In this paper, we focus on a typical two-phase phenomenon in the learning of multi-layer perceptrons (MLPs), and we aim to explain the reason for the decrease of feature diversity in the first phase. Specifically, people find that, in the training of MLPs, the training loss does not decrease significantly until the second phase. To this end, we further explore the reason why the diversity of features over different samples keeps decreasing in the first phase, which hurts the optimization of MLPs. We explain such a phenomenon in terms of the learning dynamics of MLPs. Furthermore, we theoretically explain why four typical operations can alleviate the decrease of the feature diversity.