Experimental Analysis of Large-scale Learnable Vector Storage Compression
Summary: Taxonomy and comprehensive benchmark of 14 embedding-compression methods for large-scale learnable vectors using a uniform testbed. Quantifies memory–quality trade-offs, recommends per-use-case winners, and exposes method limitations and research gaps. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Hailin Zhang (Peking University)
- 2. Penghao Zhao (Peking University)
- 3. Xupeng Miao (Carnegie Mellon University)
- 4. Yingxia Shao (Beijing Institute of Technology)
- 5. Zirui Liu (Peking University)
- 6. Tong Yang (Peking University)
- 7. Bin Cui (Peking University)
BibTeX Citation
@article{zhang_vldb24,
title = {{Experimental Analysis of Large-scale Learnable Vector Storage Compression}},
author = {Zhang, Hailin and Zhao, Penghao and Miao, Xupeng and Shao, Yingxia and Liu, Zirui and Yang, Tong and Cui, Bin},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {4},
pages = {808--822},
doi = {10.14778/3636218.3636234},
url = {https://doi.org/10.14778/3636218.3636234},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,430 | PQCache: Product Quantization-based KVCache for Long Context LLM Inference | 2025 | SIGMOD | 6.7091071e-05 |
| 9,556 | CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models | 2024 | SIGMOD | 5.2528121e-05 |
| 9,880 | MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training | 2025 | SIGMOD | 5.2040783e-05 |
| 9,892 | Accelerating Approximate Nearest Neighbor Search in Hierarchical Graphs: Efficient Level Navigation with Shortcuts | 2025 | VLDB | 5.1997534e-05 |
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.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 8,617 | Improving Matrix-vector Multiplication via Lossless Grammar-Compressed Matrices | 2022 | VLDB |
| 2 | 3,240 | Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art | 2025 | SIGMOD |
| 3 | 2,224 | An Experimental Study of Bitmap Compression vs. Inverted List Compression | 2017 | SIGMOD |
| 4 | 11,770 | An Evaluation of Methods of Compressing Doubles | 2020 | SIGMOD |
| 5 | 3,092 | DeepSqueeze: Deep Semantic Compression for Tabular Data | 2020 | SIGMOD |
| 6 | 7,173 | CompressDB: Enabling Efficient Compressed Data Direct Processing for Various Databases | 2022 | SIGMOD |
| 7 | 10,980 | Beyond Compression: A Comprehensive Evaluation of Lossless Floating-Point Compression | 2025 | VLDB |
| 8 | 9,556 | CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models | 2024 | SIGMOD |
| 9 | 2,519 | Similarity search in the blink of an eye with compressed indices | 2023 | VLDB |
| 10 | 1,644 | Compressed Linear Algebra for Large-Scale Machine Learning | 2016 | VLDB |