Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search
Summary: Laser shows that on-disk graph ANNS becomes compute-, rather than I/O-, bound at high dimensionality, challenging conventional optimization priorities. Its SIMD-friendly layout, degree-aware caching, clustered entry points, and early dispatch achieve in-memory-level throughput. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Weijian Chen (Southern University of Science and Technology)
- 2. Haotian Liu (AlayaDB AI)
- 3. Yangshen Deng (University of Edinburgh)
- 4. Long Xiang (AlayaDB AI)
- 5. Liang Huang (Southern University of Science and Technology)
- 6. Bo Tang (Southern University of Science and Technology)
BibTeX Citation
@inproceedings{chen_sigmod26,
title = {{Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search}},
author = {Chen, Weijian and Liu, Haotian and Deng, Yangshen and Xiang, Long and Huang, Liang and Tang, Bo},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802045},
url = {https://dl.acm.org/doi/10.1145/3802045},
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 17 of 17 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 1,244 | Efficient Approximate Nearest Neighbor Search in Multi-dimensional Databases | 2023 | SIGMOD |
| 2 | 580 | SRS: Solving c-Approximate Nearest Neighbor Queries in High Dimensional Euclidean Space with a Tiny Index | 2015 | VLDB |
| 3 | 9,778 | Turbocharging Vector Databases using Modern SSDs | 2025 | VLDB |
| 4 | 21 | Similarity Search in High Dimensions via Hashing | 1999 | VLDB |
| 5 | 8,655 | A Non-Linear Dimensionality-Reduction Technique for Fast Similarity Search in Large Databases | 2006 | SIGMOD |
| 6 | 7,259 | Efficient Dynamic Indexing for Range Filtered Approximate Nearest Neighbor Search | 2025 | SIGMOD |
| 7 | 10,251 | GPS: Revisiting the Data Layout for Disk-based High-Dimensional Vector Search | 2026 | SIGMOD |
| 8 | 1,934 | Towards Efficient Index Construction and Approximate Nearest Neighbor Search in High-Dimensional Spaces | 2023 | VLDB |
| 9 | 2,519 | Similarity search in the blink of an eye with compressed indices | 2023 | VLDB |
| 10 | 7,166 | Accelerating Graph Indexing for ANNS on Modern CPUs | 2025 | SIGMOD |