tensorflow / tensorflow/recommenders
SampledSoftmax Loss in Retrieval
Open
@maciejkula is already working on this.
Since Nov 10, 2020.
question
- Dominant language
- Python
- Stars
- 2k
- Forks
- 300
- PR merge metrics
- No merged PRs in 30d
Description
Hi, as is shown in the basic_retrieval tutorial, we seem to use tf.keras.losses.CategoricalCrossentropy loss as default.
-
I wonder if there is any difference between that and
tf.nn.sampled_softmax_loss? In my view, which is also mentioned in YoutubeDNN paper(Google 2016), it might be better to use sampled softmax (corresponding to the multi-class classification) since we are at the retrieval stage? -
If so, how can we incorporate sampled softmax in the model as we are using keras as the high-level api. Any example code?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.