[
https://issues.apache.org/jira/browse/LUCENE-9136?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17057886#comment-17057886
]
Jim Ferenczi commented on LUCENE-9136:
--------------------------------------
Thanks for chiming in [~tomoko]. Although I still think it would be valuable to
discuss the minimal signature needed to share a new codec in both approaches. I
also think that there is a consensus around the fact that multiple strategies
could be needed depending on the trade-offs that users are willing to take. If
we start adding codecs and formats for every strategy that we think valuable I
am afraid that this will block us sooner that we expect. If we agree that
having a new codec for vectors and ann is valuable in Lucene, my proposal is to
have a generic codec that can be used to test different strategies (k-means,
hsnw, ...). IMO this could also changed the goal for these approaches since we
don't want to require users to tune tons of internal options (numbers of
neighbors, numbers of levels, ...) upfront.
> Introduce IVFFlat to Lucene for ANN similarity search
> -----------------------------------------------------
>
> Key: LUCENE-9136
> URL: https://issues.apache.org/jira/browse/LUCENE-9136
> Project: Lucene - Core
> Issue Type: New Feature
> Reporter: Xin-Chun Zhang
> Priority: Major
> Attachments: glove-100-angular.png, glove-25-angular.png,
> image-2020-03-07-01-22-06-132.png, image-2020-03-07-01-25-58-047.png,
> image-2020-03-07-01-27-12-859.png, sift-128-euclidean.png
>
> Time Spent: 50m
> Remaining Estimate: 0h
>
> Representation learning (RL) has been an established discipline in the
> machine learning space for decades but it draws tremendous attention lately
> with the emergence of deep learning. The central problem of RL is to
> determine an optimal representation of the input data. By embedding the data
> into a high dimensional vector, the vector retrieval (VR) method is then
> applied to search the relevant items.
> With the rapid development of RL over the past few years, the technique has
> been used extensively in industry from online advertising to computer vision
> and speech recognition. There exist many open source implementations of VR
> algorithms, such as Facebook's FAISS and Microsoft's SPTAG, providing various
> choices for potential users. However, the aforementioned implementations are
> all written in C++, and no plan for supporting Java interface, making it hard
> to be integrated in Java projects or those who are not familier with C/C++
> [[https://github.com/facebookresearch/faiss/issues/105]].
> The algorithms for vector retrieval can be roughly classified into four
> categories,
> # Tree-base algorithms, such as KD-tree;
> # Hashing methods, such as LSH (Local Sensitive Hashing);
> # Product quantization based algorithms, such as IVFFlat;
> # Graph-base algorithms, such as HNSW, SSG, NSG;
> where IVFFlat and HNSW are the most popular ones among all the VR algorithms.
> IVFFlat is better for high-precision applications such as face recognition,
> while HNSW performs better in general scenarios including recommendation and
> personalized advertisement. *The recall ratio of IVFFlat could be gradually
> increased by adjusting the query parameter (nprobe), while it's hard for HNSW
> to improve its accuracy*. In theory, IVFFlat could achieve 100% recall ratio.
> Recently, the implementation of HNSW (Hierarchical Navigable Small World,
> LUCENE-9004) for Lucene, has made great progress. The issue draws attention
> of those who are interested in Lucene or hope to use HNSW with Solr/Lucene.
> As an alternative for solving ANN similarity search problems, IVFFlat is also
> very popular with many users and supporters. Compared with HNSW, IVFFlat has
> smaller index size but requires k-means clustering, while HNSW is faster in
> query (no training required) but requires extra storage for saving graphs
> [indexing 1M
> vectors|[https://github.com/facebookresearch/faiss/wiki/Indexing-1M-vectors]].
> Another advantage is that IVFFlat can be faster and more accurate when
> enables GPU parallel computing (current not support in Java). Both algorithms
> have their merits and demerits. Since HNSW is now under development, it may
> be better to provide both implementations (HNSW && IVFFlat) for potential
> users who are faced with very different scenarios and want to more choices.
> The latest branch is
> [*lucene-9136-ann-ivfflat*]([https://github.com/irvingzhang/lucene-solr/commits/jira/lucene-9136-ann-ivfflat)|https://github.com/irvingzhang/lucene-solr/commits/jira/lucene-9136-ann-ivfflat]
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org
