benchaplin opened a new pull request, #14085:
URL: https://github.com/apache/lucene/pull/14085

   ### Description
   
   Playing around with some ideas from 
[ACORN-1](https://arxiv.org/pdf/2403.04871) to improve filtered HNSW search. 
The ideas are:
   - Predicate subgraph traversal (only consider/score candidates that pass the 
filter)
   - Two-hop neighbor expansion (I read up on [Weaviate's 
implementation](https://weaviate.io/blog/speed-up-filtered-vector-search) and 
used their idea to consider two-hop neighbors only when the first hop doesn't 
pass the filter)
   
   I benchmarked using 
[Cohere/wikipedia-22-12-en-embeddings](https://huggingface.co/datasets/Cohere/wikipedia-22-12-en-embeddings)
 with params:
   - nDoc = 200000
   - topK = 100
   - fanout = 50
   - maxConn = 32
   - beamWidth = 100
   - filterSelectivity = [0.05, 0.25, 0.5, 0.75, 0.95]
   
   Here are some average results:
   
   **Baseline:**
   | filterSelectivity | recall | latency (ms) |
   | --------------- | ------ | ------------ |
   | 0.05 | 0.037  | 17.182       |
   | 0.25 | 0.166  | 7.348        |
   | 0.5 | 0.332  | 4.376        |
   | 0.75 | 0.489  | 3.165        |
   | 0.95 | 0.608  | 2.441        |
   
   **Candidate** (this code): 
   | filterSelectivity | recall | latency (ms) |
   | --------------- | ------ | ------------ |
   | 0.05 | 0.028  | 2.744        |
   | 0.25 | 0.157  | 4.614        |
   | 0.5 | 0.308  | 4.833        |
   | 0.75 | 0.449  | 4.622        |
   | 0.95 | 0.563  | 3.244        |
   
   Pros: significantly faster for selective filters.
   Cons: slightly worse recall across the board, slightly slower for inclusive 
filters. 
   
   There's a lot to play around with here, this code represents the best 
results I got with this testing. One thing that must be tested is correlation 
between filter and query vector (this is discussed and tested in the paper). 
luceneutil only offers zero correlation at the moment, so I'm working on adding 
a knob to turn there for future benchmarks. 
   
   Code should also be cleaned up, but for me, keeping everything in one method 
makes it easier to read the changes. 
   
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org

Reply via email to