Sharpness-aware minimization (SAM) has received increasing attention in
computer vision since it can effectively eliminate the sharp local minima from
the training trajectory and mitigate generalization degradation. However, SAM
requires two sequential gradient computations during the optimization of each
step: one to obtain the perturbation gradient and the other to obtain the
updating gradient. Compared with the base optimizer (e.g., Adam), SAM doubles
the time overhead due to the additional perturbation gradient. By dissecting
the theory of SAM and observing the training gradient of the molecular graph
transformer, we propose a new algorithm named GraphSAM, which reduces the
training cost of SAM and improves the generalization performance of graph
transformer models. There are two key factors that contribute to this result:
(i) \textit{gradient approximation}: we use the updating gradient of the
previous step to approximate the perturbation gradient at the intermediate
steps smoothly (\textbf{increases efficiency}); (ii) \textit{loss landscape
approximation}: we theoretically prove that the loss landscape of GraphSAM is
limited to a small range centered on the expected loss of SAM
(\textbf{guarantees generalization performance}). The extensive experiments on
six datasets with different tasks demonstrate the superiority of GraphSAM,
especially in optimizing the model update process. The code is
in:this https URL

通过近似梯度和损失景观的限制，GraphSAM 算法减少了 Sharpness-aware minimization（SAM）的训练成本，并提高了图变压器模型的泛化性能。