JingsongLi opened a new pull request, #132:
URL: https://github.com/apache/paimon-vector-index/pull/132

   ### Purpose
   
   Use an automatic outer probe floor of 3 for a four-centroid router and 4 for 
an eight-centroid router. The floor enters the existing candidate-count and 
filter-selectivity calculation before expansion and clamping. The caller can 
still set an explicit probe width. The ordinary IVF reader keeps its existing 
floor of 8.
   
   The behavior is shared by IVF and DiskANN shard layouts through the existing 
`CentroidRouter.resolveNprobe` API. The serialized model and JNI signatures are 
unchanged. [Paimon integration and 
benchmark](https://github.com/apache/paimon/pull/11249)
   
   ### Verification
   
   Rust workspace tests, Clippy with warnings as errors, rustfmt and the Java 
API suite passed. Regression tests exercise 4 and 8 centroids, adjacent counts, 
large top-K, filtered searches, fixed probes and the ordinary IVF policy.
   
   Compared two release JNI builds against the same pinned index snapshot for 
each pair. The baseline was `e794291`. The Paimon benchmark omits 
`centroid.nprobe` in both arms. The dataset contains 100,000 SIFT vectors (L2, 
128 dimensions) in four disjoint row-ID ranges. Random masks retain exactly 
80%, 50% or 5% of rows per range. Ground truth is exhaustive L2 within the 
eligible set. Each pair used the same 80–512 held-out queries and identical 
shard-local settings. Inputs came from original SIFT query positions 8000–9249. 
Fresh readers counted all logical bytes returned by Paimon streams, including 
the routers, on an Apple M4 Pro with four native threads.
   
   All 32 paired scenarios met the existing recall criterion, an absolute mean 
difference of at most 1 percentage point and a paired 95% bootstrap lower bound 
above −1 point. The largest measured recall decrease was 0.111 points 
(IVF-FLAT, 8 centers, K=1000, 100% eligible). The lowest lower bound was -0.180 
points. 10,944 paired query measurements were taken across scenarios. Scenarios 
can reuse query IDs. The table gives old → new.
   
   | Index | Centroids per range | Top-K | Eligible rows | Recall@K (%) | 
Files/query | Logical MiB/query |
   | --- | ---: | ---: | ---: | ---: | ---: | ---: |
   | IVF-FLAT | 4 | 100 | 100% | 98.645 → 98.645 | 20 → 16 | 23.40 → 17.14 |
   | IVF-FLAT | 4 | 100 | 80% | 98.561 → 98.561 | 20 → 20 | 23.40 → 23.40 |
   | IVF-FLAT | 8 | 100 | 80% | 97.934 → 97.932 | 36 → 24 | 23.37 → 14.91 |
   | IVF-SQ | 8 | 100 | 80% | 97.781 → 97.779 | 36 → 24 | 6.74 → 4.32 |
   | IVF-PQ | 8 | 100 | 80% | 84.138 → 84.135 | 36 → 24 | 5.64 → 3.55 |
   | IVF-RQ | 8 | 100 | 80% | 95.320 → 95.318 | 36 → 24 | 6.52 → 4.12 |
   | DISKANN | 8 | 100 | 80% | 100.000 → 99.997 | 36 → 24 | 32.19 → 19.75 |
   | IVF-FLAT | 8 | 10 | 5% | 97.422 → 97.422 | 36 → 36 | 23.37 → 23.37 |
   | IVF-FLAT | 8 | 1,000 | 100% | 94.468 → 94.357 | 36 → 20 | 23.38 → 12.30 |
   | IVF-PQ | 8 | 1,000 | 80% | 80.648 → 80.645 | 36 → 24 | 5.64 → 3.55 |
   | DISKANN | 8 | 1,000 | 80% | 100.000 → 99.994 | 36 → 24 | 35.17 → 21.18 |
   | IVF-FLAT | 4 | 5,000 | 100% | 90.586 → 90.586 | 20 → 20 | 23.40 → 23.40 |
   | IVF-FLAT | 8 | 5,000 | 100% | 84.634 → 84.634 | 36 → 32 | 23.37 → 20.45 |
   


-- 
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: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to