Results of the Big ANN: NeurIPS'23 competition
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANN
BatANN delivers near-linear throughput scaling for distributed disk-based approximate nearest neighbor search on a single global graph, with 3.5-5.59x gains over scatter-gather baselines on 1B-point datasets at 0.95 recall.
-
Onyx: Cost-Efficient Disk-Oblivious ANN Search
Onyx inverts ANN-ORAM optimization priorities with a compact pruning representation and locality-aware shallow tree to deliver 1.7-9.9x lower cost and 2.3-12.3x lower latency for disk-oblivious ANN search.
-
MINT: Multi-Vector Search Index Tuning
MINT defines multi-vector search index tuning and provides algorithms that achieve 2.1X to 8.3X latency speedup over baselines under storage and recall constraints.
-
When to Repair a Graph ANN Index: Navigability-Signal-Triggered Local Repair Protects Tail Recall Under Bursty Churn
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.
-
AlayaLaser: Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search
AlayaLaser uses a SIMD-optimized on-disk graph layout plus caching and search strategies to outperform prior on-disk ANNS systems and match or exceed in-memory performance on large high-dimensional datasets.
-
From Embedding Geometry to Spectral Search: Energy Dispersion Networks For Vector Retrieval
Introduces Graph Wiring and Spectral Indexing to combine geometric similarity with spectral graph structure for improved vector retrieval and adaptive tau-modulated search.
-
The Faiss library
Faiss is a library offering indexing methods and primitives for efficient vector similarity search, a core need in vector databases for AI applications.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.