Neuron with Steady Response Leads to Better Generalization
This work addresses the generalization gap in machine learning by introducing a novel inductive bias based on neuron response steadiness, which is incremental but offers practical improvements for training neural networks.
The paper tackles the problem of generalization in neural networks by proposing a new regularization method, Neuron Steadiness Regularization (NSR), which reduces intra-class response variance in neurons, leading to consistent performance gains across various models and datasets with low computational overhead.
Regularization can mitigate the generalization gap between training and inference by introducing inductive bias. Existing works have already proposed various inductive biases from diverse perspectives. However, none of them explores inductive bias from the perspective of class-dependent response distribution of individual neurons. In this paper, we conduct a substantial analysis of the characteristics of such distribution. Based on the analysis results, we articulate the Neuron Steadiness Hypothesis: the neuron with similar responses to instances of the same class leads to better generalization. Accordingly, we propose a new regularization method called Neuron Steadiness Regularization (NSR) to reduce neuron intra-class response variance. Based on the Complexity Measure, we theoretically guarantee the effectiveness of NSR for improving generalization. We conduct extensive experiments on Multilayer Perceptron, Convolutional Neural Networks, and Graph Neural Networks with popular benchmark datasets of diverse domains, which show that our Neuron Steadiness Regularization consistently outperforms the vanilla version of models with significant gain and low additional computational overhead.