REVIEW 12 cited by
Results of the Big ANN: NeurIPS'23 competition
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
read the original abstract
The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect the growing complexity and diversity of workloads. Unlike prior challenges that emphasized scaling up classical ANN search ~\cite{DBLP:conf/nips/SimhadriWADBBCH21}, this competition addressed filtered search, out-of-distribution data, sparse and streaming variants of ANNS. Participants developed and submitted innovative solutions that were evaluated on new standard datasets with constrained computational resources. The results showcased significant improvements in search accuracy and efficiency over industry-standard baselines, with notable contributions from both academic and industrial teams. This paper summarizes the competition tracks, datasets, evaluation metrics, and the innovative approaches of the top-performing submissions, providing insights into the current advancements and future directions in the field of approximate nearest neighbor search.
Forward citations
Cited by 12 Pith papers
-
VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs
A label-centric GPU index that routes common labels through graph search and rare labels through brute-force scans achieves up to 135x higher filtered-search throughput than previous CPU approaches.
-
ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search
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.
-
When to Repair a Graph ANN Index: A Matched-Budget Negative Result, and the Interpolated-Baseline Trap That Hid It
Signal-triggered local repair in graph ANN indexes improves minimum recall@10 by 0.014-0.050 under bursty churn versus fixed-cadence repair at matched budget on SIFT-128 and Fashion-MNIST-784.
-
PiPNN: Ultra-Scalable Graph-Based Nearest Neighbor Indexing
PiPNN builds high-quality approximate-nearest-neighbor search graphs up to 12.9x faster than HNSW and 11.6x faster than Vamana by replacing search-based construction with overlapping partitions, dense GEMM distance co...
-
SIEVE: Effective Filtered Vector Search with Collection of Indexes
SIEVE builds a workload-aware collection of small HNSW subindexes and uses a cost model to pick the best one per query, speeding up filtered vector search up to 8.06x versus prior graph-based methods.
-
Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
Sampling a random hypersphere point from a von Mises-Fisher distribution around the state and retrieving its nearest neighbor asymptotically reproduces Boltzmann exploration probabilities at sublinear cost.
-
LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table
A fast post-processing method for approximate nearest neighbor search uses a precomputed cutoff table to greedily prune candidates and guarantee a minimum pairwise distance among the returned results.
-
Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search
A distance-based stopping rule for beam search in graph-based ANN is proven to give exact or approximate nearest neighbors on navigable graphs and beats fixed-width beam search in experiments.
-
Inference-time sparse attention with asymmetric indexing
Saap approximates attention by clustering keys with k-means and learning a query classifier, reducing KV-cache lookups about 20x at 4-5% selectivity with small accuracy loss on several long-context benchmarks.
-
Scalable k-Means Clustering for Large k via Seeded Approximate Nearest-Neighbor Search
A seeded graph-based nearest-center search (SHEESH) makes k-means with huge k (up to 10^6 clusters) practical on a single CPU, beating GPU Lloyd baselines in the reported experiments.
-
From Embedding Geometry to Spectral Search: Energy Dispersion Networks For Vector Retrieval
Mixing cosine similarity with Rayleigh energy on a feature-space graph Laplacian improves head-tail coherence and modest semantic metrics over pure geometric retrieval.
-
Filtered Approximate Nearest Neighbor Search: A Unified Benchmark and Systematic Experimental Study [Experiment, Analysis & Benchmark]
A systematic benchmark of filtered nearest-neighbor search algorithms shows no single winner: filter-then-search methods excel at containment and equality filters, while hybrid methods dominate overlap filters.
Discussion (0). Continue with ORCID to comment.