what does the arguments 'reduce_D' and 'f_dim' mean?

[advancera]

sorry, i don't understant the meaning of arguments 'reduce_D' and 'f_dim', can you give me any help? thanks a lot!
def _build_extreme_FM(hparams, nn_input, res=True, direct=False, bias=False, reduce_D=True, f_dim=2)

[Leavingseason]

reduce_D and f_dim is about decomposing the filter matrix into two low-rank matrices. You can refer to the equation (9) in our paper.
We have a updated version of implementation for this part. In the old version, we only reduce the space complexity, but not time complexity. In the updated version, we reduce both. Let me know if you are interested in the updated version, and I will send you it.

[jaysharp]

reduce_D and f_dim is about decomposing the filter matrix into two low-rank matrices. You can refer to the equation (9) in our paper.
We have a updated version of implementation for this part. In the old version, we only reduce the space complexity, but not time complexity. In the updated version, we reduce both. Let me know if you are interested in the updated version, and I will send you it.

---

could you send me one copy? highly appreciated. my email: [email protected]

[Leavingseason]

Sent.

[jaysharp]

Sent.

thank you very much. it really helps.

[y-ksenia]

reduce_D and f_dim is about decomposing the filter matrix into two low-rank matrices. You can refer to the equation (9) in our paper.
We have a updated version of implementation for this part. In the old version, we only reduce the space complexity, but not time complexity. In the updated version, we reduce both. Let me know if you are interested in the updated version, and I will send you it.

Hi! I'm also interested in updated version. Could you please send me it too? my mail: [email protected]
Thank you in advance!

[chenhaoenen]

膜拜大佬，代码很棒，麻烦能否发一份同样的给我，万分感谢，同时期待大佬的其他模型的代码, [email protected],谢谢！祝好！

[yang-XH]

Hello! I'm also interested in the new version. Could you please send me the copy? my mail: [email protected]
Thank you!