mlu355/metadatanorm

Repository for the paper "Metadata Normalization"

metadatanorm's Issues

Categorical variable case

Hi @mlu355,
Thanks for releasing your work. Do you have any intuitions on how to handle categorical variables (as in the categorical cases or even in some continuous variable cases, the XTX matrix may not be full rank, resulting in the non-invertible matrix) do you have any thoughts on how to address this issue?

Thanks,
Avinash

Why remove the effects of metadata?

Hi,

Thank you for your work. But I am a little bit confused. Since race plays a role in predicting gender why not including them in the input data? I know that these data are usually from different modalities, but we can do early/late fuse or whatever to explicitly take them in. I am not sure if there will be some negative impact if data are not very orthogonal to each other in deep learning framework.

I also come up with another paper "REVERSIBLE INSTANCE NORMALIZATION FOR ACCURATE TIME-SERIES FORECASTING AGAINST DISTRIBUTION SHIFT"(under review). In that work, they get rid of the instance-wise mean of the initial time series and plug it back right before the output layer. Can I think of the instance-wise mean as meta data in this sense?

Thanks!

when will the code be released?

hi, i wonder when will the code be released? thank you~

looking forward to the code

Code

When will the code be released? I've been looking forward to it. Thank you