It looks like the batch effect correction is improving. Its not great, but... it is in the ballpark.
Two things that could likely lead to improvement
Optimization strategy - I've noticed that we just run it longer, we can have better estimates of batches
It is very possible that our encoder architecture just sucks. I'm tempted to add arcsine transform and have a rigorous evaluation of activation functions.
It looks like the batch effect correction is improving. Its not great, but... it is in the ballpark.
Two things that could likely lead to improvement