0
$\begingroup$

I have been working on some research using a type of auto-encoder to generate new points with specific desirable properties. I trained my network and successfully generated some points, but when I compare them to my training data using nearest neighbor distance (NND), the resulting values are lower than I would like (although since I am somewhat new to machine learning I am not sure what an appropriate threshold value for uniqueness would be).

I think this might be in part related to how large my training dataset is (it makes sense to me that with less training points to compare to, I would have larger NND's for my generated points), but because my current model is doing a very good job at generating points with specific desirable properties, I am hesitant to change it. I wanted to see what the common solutions for this sort of problem are before I start changing the number of data points I use in training.

I was also wondering about whether it would be useful to add an NND-based term into the loss function when training, although I imagine this would slow things down significantly.

So in total my questions are: 1.) What is a reasonable NND threshold for uniqueness 2.) What are some good ways to bring about higher NND values for generated points 3.) Is an NND-based loss term a reasonable thing to consider?

Thank you!

$\endgroup$
2
  • $\begingroup$ I'm having some trouble understanding what your goal is. It sounds like you're using the AE to generate new samples - since you're comparing it's output to the training data. Is that right? You're getting a low NND - low distance suggests its close to your training samples, but why is that bad? Is this what you mean by "unique" - that your AE is just regurgitating your training data? $\endgroup$
    – bogovicj
    Sep 7 '21 at 15:55
  • $\begingroup$ Yes essentially the low NND would suggest that the generated points are very close in value to the training data points. I would like to generate points that are not always so close to the training data. Although I am still not sure what counts as a low value relatively speaking. $\endgroup$ Sep 7 '21 at 23:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.