Similarity of Neural Architectures Based on Input Gradient Transferability. (arXiv:2210.11407v1 [cs.LG])

In this paper, we aim to design a quantitative similarity function between
two neural architectures. Specifically, we define a model similarity using
input gradient transferability. We generate adversarial samples of two networks
and measure the average accuracy of the networks on adversarial samples of each
other. If two networks are highly correlated, then the attack transferability
will be high, resulting in high similarity. Using the similarity score, we
investigate two topics: (1) Which network component contributes to the model
diversity? …

architectures arxiv gradient neural architectures