Your comment brings up two interesting variants that could be interesting if your goal is to increase the sparsity of the attention:

- Rectify the difference of the softmaxes. (min(0, s(A1) - lambda s(A2)))

- Apply the Heaviside function to the second softmax. (softmax(A1) - lambda H(s(A1) - lambda s(A2))

The second one being a bit more drastic and maybe harder to train.