fcjy
fcjy
> @fcjy do you have the same issue with NMSLIB implementation? > PS: HNSW doesn't always work. I have an example where it doesn't work with the cosine similarity and...
@yurymalkov Of course! I had sent an email to you(yurymalkov_mail_ru), please check it. And I will try the two methods you mentioned today. Thanks!
I do a transform, let the MIPS problem change to NNS problem, such as chapter 2.1 in [this paper](https://papers.nips.cc/paper/7722-non-metric-similarity-graphs-for-maximum-inner-product-search.pdf), and then run libhnsw, that get a very nice result!
@searchivarius Of course! I had sent it.