Wang

> I think it depends on many factors like > > * data availability - interaction data, feature-typed data, graph data. > > * problem setting - recall, ranking, etc....

> > > Hi @wanglu2014, it is better to use [Pyro forum](https://forum.pyro.ai/) for questions and discussions. We use github to track the issues and feature requests. For your question, in...

> The number of topics is a hyperparameter specified in cell 11. You can change it to 10 if you want. Sorry for not clarify my question. The parameter is...

> > > I see. So you are talking about supervised learning. LDA does not require pre-defined topics. If you use pre-defined topics, I guess you can just optimize the...

Thank you for your help. Actually, it has solved this problem in some conditions. However, for extramely large dataset, such as 40000*300*5000 Is there other way to compute it with...

Dear Dr Meyer, thank you for your kindly reply. However, the Slack channel page said that it need a new invitation. Could you kindly sent an invitation to my email...

> Hi @wanglu2014 - here's an [updated link for Slack](https://join.slack.com/t/tensorly/shared_invite/zt-wqnts2sk-wbiRX6ml~Xt6~GDYWRPFfg) I have joined the channel. Thank you for your timely reply!

> @wanglu2014 @aarmey should we close this or create a PR with more doc/user-guide to address this question? I receive no related advice from Slack, and have decided to perform...

If I only want to blastp with a mini NR database, which method is more efficient? Filtered and created a mini NR database, or modified some diamond parameter or commend?

> We just need output species name, not full taxonomy tree. Which code you recommend after 'diamond makedb --in nr --db nr'? > You can use the output fields `salltitles`...