# Could the Jensen-Shannon divergence and Kullback-Leibler divergence be used as loss functions of non-generation problems?

If I understand correctly, the KL divergence is a measure of information loss between a ground truth distribution $$P$$ and a predicted distribution $$Q$$, and the Jensen-Shannon divergence is the mean of the KL Divergences of 2 cases

1. Predicted distribution is mean of $$P$$ and $$Q$$, and ground truth is $$P$$

2. Predicted distribution is mean of $$P$$ and $$Q$$, and ground truth is $$Q$$

Since KL divergence can be easily interpreted as information loss in $$Q$$ relative to $$P$$, what can JS divergence interpret-ably represent? I cannot see any use cases of these measures unless there are two distributions to compare. Is there any other problem where I could use them as loss functions other than generation problems? If so how, and why?