Kangaroo: Efficient Lossless Floating-Point Compression via Dynamic Reference Selection
Summary: Kangaroo replaces predecessor-only XOR references with efficient dynamic selection from a historical window, using pruning and bit-flip erasure to maximize trailing zeros. Across 26 datasets, it improves compression by 23.2% on average while accelerating compression/decompression. (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. Shuo Li (Northeastern University)
- 2. Xiaochun Yang (Northeastern University)
- 3. Chunhui Shen (Alibaba)
- 4. Yutong Han (Dalian Minzu University)
- 5. Xiang Wang (Alibaba)
- 6. Lingdu Kong (Northeastern University)
- 7. Bin Wang (Northeastern University)
- 8. Feibo Li (Alibaba)
BibTeX Citation
@inproceedings{li_sigmod26,
title = {{Kangaroo: Efficient Lossless Floating-Point Compression via Dynamic Reference Selection}},
author = {Li, Shuo and Yang, Xiaochun and Shen, Chunhui and Han, Yutong and Wang, Xiang and Kong, Lingdu and Wang, Bin and Li, Feibo},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802076},
url = {https://dl.acm.org/doi/10.1145/3802076},
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 11 of 11 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 | 10,946 | LogLite: Lightweight Plug-and-Play Streaming Log Compression | 2025 | VLDB |
| 2 | 10,923 | Improving Time Series Data Compression in Apache IoTDB | 2025 | VLDB |
| 3 | 3,269 | ALP: Adaptive Lossless floating-Point Compression | 2023 | SIGMOD |
| 4 | 11,770 | An Evaluation of Methods of Compressing Doubles | 2020 | SIGMOD |
| 5 | 10,980 | Beyond Compression: A Comprehensive Evaluation of Lossless Floating-Point Compression | 2025 | VLDB |
| 6 | 10,619 | DeXOR: Enabling xor in Decimal Space for Streaming Lossless Compression of Floating-point Data | 2026 | VLDB |
| 7 | 1,364 | Chimp: Efficient Lossless Floating Point Compression for Time Series Databases | 2022 | VLDB |
| 8 | 3,540 | Elf: Erasing-based Lossless Floating-Point Compression | 2023 | VLDB |
| 9 | 7,892 | Serf: Streaming Error-Bounded Floating-Point Compression | 2025 | SIGMOD |
| 10 | 8,635 | Camel: Efficient Compression of Floating-Point Time Series | 2024 | SIGMOD |