Pith. sign in

REVIEW 6 cited by

OOD-DiskANN: Efficient and Scalable Graph ANNS for Out-of-Distribution Queries

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.12850 v2 pith:3IEO6JZQ submitted 2022-10-22 cs.LG cs.IR

classification cs.LGcs.IR
keywords queriesalgorithmsannsindexquerydataefficiencyindices
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

State-of-the-art algorithms for Approximate Nearest Neighbor Search (ANNS) such as DiskANN, FAISS-IVF, and HNSW build data dependent indices that offer substantially better accuracy and search efficiency over data-agnostic indices by overfitting to the index data distribution. When the query data is drawn from a different distribution - e.g., when index represents image embeddings and query represents textual embeddings - such algorithms lose much of this performance advantage. On a variety of datasets, for a fixed recall target, latency is worse by an order of magnitude or more for Out-Of-Distribution (OOD) queries as compared to In-Distribution (ID) queries. The question we address in this work is whether ANNS algorithms can be made efficient for OOD queries if the index construction is given access to a small sample set of these queries. We answer positively by presenting OOD-DiskANN, which uses a sparing sample (1% of index set size) of OOD queries, and provides up to 40% improvement in mean query latency over SoTA algorithms of a similar memory footprint. OOD-DiskANN is scalable and has the efficiency of graph-based ANNS indices. Some of our contributions can improve query efficiency for ID queries as well.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. iFVS: Towards Instance-Optimized Filtered Vector Search

    cs.DB 2026-07 conditional novelty 7.0 of 10

    iFVS adapts Product Quantization codebooks to individual filter predicates and query vectors, improving QPS-recall tradeoff over fixed-codebook PQ on SIFT1M/SIFT10M.

  2. Sparse Neighborhood Graph-Based Approximate Nearest Neighbor Search Revisited: Theoretical Analysis and Optimization

    cs.DS 2025-09 conditional novelty 7.0 of 10

    OPT-SNG introduces a martingale model for SNG pruning in ANNS, proves O(n^{2/3+ε}) max out-degree and O(log n) expected path length, and gives a closed-form optimal truncation parameter that yields 5.9× average constr...

  3. ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A modular ANNS framework decouples search algorithms from graph storage, delivering filtered search, dynamic updates, and snapshot queries at performance close to that of specialized systems.

  4. Fast Approximate Vector Joins via Offline-Online Co-Design

    cs.DB 2026-03 conditional novelty 6.0 of 10

    A merged index and soft work sharing speed up approximate threshold-based vector joins by up to 56x, with a hybrid search improving out-of-distribution recall by up to 43%.

  5. RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

    cs.LG 2024-09 conditional novelty 6.0 of 10

    RetrievalAttention approximates full attention in long-context LLMs by retrieving relevant KV vectors from CPU-based ANNS indexes with an attention-aware algorithm, achieving near-full accuracy while accessing only 1-...

  6. NAVIS: Concurrent Search and Update with Low Position-Seeking Overhead in On-SSD Graph-Based Vector Search

    cs.DC 2026-05 unverdicted novelty 5.0 of 10

    NAVIS improves concurrent search and update throughput in on-SSD graph vector search by up to 2.74x for insertions and 1.37x for searches through reduced position-seeking overhead.

Pith tools