DBScholar

Back to papers

Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views: [Experiments & Analysis]

Summary: Iceberg: task-centric benchmark for VSS beyond recall/latency on metric ground truth; evaluates end-to-end pipeline across 8 datasets, exposing an Information Loss Funnel (embedding loss, metric misuse, distribution sensitivity). Re-ranks 13 VSS methods and provides interpretable guidance for workload-specific method selection. (summarized by gpt-5-mini on Apr 11 2026)

Paper ID
7707
Venue
SIGMOD
Year
2026
Pagerank
5.093636e-05
Overall Rank
10,493 | 28.01%
DOI
10.1145/3786690

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@inproceedings{chen_sigmod26,
        title = {{Reveal Hidden Pitfalls and Navigate Next Generation of Vector Similarity Search from Task-Centric Views: [Experiments \& Analysis]}},
        author = {Chen, Tingyang and Fu, Cong and Wu, Jiahua and Wu, Haotian and Fan, Hua and Ke, Xiangyu and Gao, Yunjun and Ni, Yabo and Zeng, Anxiang},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3786690},
        url = {https://dl.acm.org/doi/10.1145/3786690},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 16 of 16 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
93 Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph 2019 VLDB 0.00034701237
332 Query-Aware Locality-Sensitive Hashing for Approximate Nearest Neighbor Search 2016 VLDB 0.00020920444
398 A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search 2021 VLDB 0.00019194947
406 AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data 2020 VLDB 0.00019054532
990 SK-LSH: An Efficient Index Structure for Approximate Nearest Neighbor Search 2014 VLDB 0.00012796562
1,244 Efficient Approximate Nearest Neighbor Search in Multi-dimensional Databases 2023 SIGMOD 0.00011508159
1,357 RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search 2024 SIGMOD 0.00011043994
1,802 HVS: Hierarchical Graph Structure Based on Voronoi Diagrams for Solving Approximate Nearest Neighbor Search 2022 VLDB 9.7284341e-05
2,519 Similarity search in the blink of an eye with compressed indices 2023 VLDB 8.4741476e-05
3,108 Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search 2025 SIGMOD 7.7499741e-05
3,240 Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art 2025 SIGMOD 7.6071649e-05
4,116 RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search 2024 VLDB 6.892012e-05
5,223 FARGO: Fast Maximum Inner Product Search via Global Multi-Probing 2023 VLDB 6.3102417e-05
5,800 DET-LSH: A Locality-Sensitive Hashing Scheme with Dynamic Encoding Tree for Approximate Nearest Neighbor Search 2024 VLDB 6.0850924e-05
6,851 Maximum Inner Product is Query-Scaled Nearest Neighbor 2025 VLDB 5.7546877e-05
7,843 BigVectorBench: Heterogeneous Data Embedding and Compound Queries are Essential in Evaluating Vector Databases 2025 VLDB 5.5333312e-05
Previous Page 1 / 1 Next

Semantically Similar Papers