rnyak
rnyak
@sararb can we close this issue?
@tottenjordan is this still an issue? can we close the ticket?
> @rnyak After discussion with @marcromeyn . Seems like adding something about 'in batch' to the name may help make the name closer to it's natural sense. Something like `InBatchNegatives`...
@sararb and @oliverholworthy was that addressed already or still an open ticket?
@karlhigley mostly likely we will use Ecom-REES46 dataset for KDD'22 and real H&M dataset for RecSys'22 tutorial, if we can get permission to use it and share on our DLI...
partially addressed by https://github.com/NVIDIA-Merlin/models/pull/680
we can close it since there will be a new PR for top_k_recommender via https://github.com/NVIDIA-Merlin/models/issues/718
@marcromeyn this problem is still valid. Oliver has a WIP PR https://github.com/NVIDIA-Merlin/models/pull/787 to fix.
@karlhigley Yes, I think we can do that for the datasets with timestamp.
related https://github.com/NVIDIA-Merlin/systems/pull/134