Closed MxMstrmn closed 2 years ago
Potential experiment: Make classifier stringer including more layer than just the linear one for the logistic regression.
Stringer seems to be a typo? This is about adjusting the classifier during the evaluation, right? vs the discriminator that runs during training (which is already non-linear).
You are correct, I meant to include a non-linear classifier during the evaluation (going beyond the multi-class logistic regression)
I corrected the typo in the issue.
The experiment to be run here:
This doesn't need to be a separate cluster sweep, we'll get these scores through #69.
Expected outcome: The Vanilla CPA has higher disentanglement scores (= bad). We would be able to use this to argue that the chemical embeddings contribute meaningfully to making the adversarial autoencoder easier to train.
Without having done any further analysis, the initial results from #69 don't really support this hypothesis.
Not super related, but what configuration determines that we have at least 125 epochs?
Or ist this just a random artifact since models usually improve at first (~50 epochs) and then our settings with checkpoint_freq=25
+ patience=3
leads to something like 125?
I think it's because at the first evaluation we always improve (since it's the first), then we wait for 3 evaluations (patience=3) and terminate once the 5th evaluation doesn't yield improvements -> 5*25=125. So there is no way to finish earlier.
Will close this, did not make it into the final paper version.
Looking at the results in
chemical_CPA/simon/plot_sweep_results.ipynb
Hypothesis: The drug disentanglement might be easier for NN based embeddings as these are chemically motivated. Potential experiment: Make classifier stronger including more layer than just the linear one for the logistic regression.