Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask
Summary: Exhaustive analysis of pre-trained model file compressibility across granularity levels, showing general-purpose compressors fail to exploit PTM-specific patterns. Propose Elf, an error-bounded float transform that removes shared exponents, and Elves framework; achieves 1.52× compression (~1.3× vs zstd/SZ3/quant) with negligible accuracy loss. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zhaoyuan Su
- 2. Ammar Ahmed
- 3. Zirui Wang
- 4. Ali Anwar
- 5. Yue Cheng
Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,688 | NeurDB: On the Design and Implementation of an AI-powered Autonomous Database | 2025 | CIDR | 4.4673127e-05 |
| 10,095 | NeurStore: Efficient In-database Deep Learning Model Management System | 2026 | SIGMOD | 4.1945683e-05 |
| 10,854 | LiquidCache: Efficient Pushdown Caching for Cloud-Native Data Analytics | 2025 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 210 | Gorilla: A Fast, Scalable, In-Memory Time Series Database | 2015 | VLDB | 0.0003404384 |
| 2,064 | Chimp: Efficient Lossless Floating Point Compression for Time Series Databases | 2022 | VLDB | 9.6418929e-05 |
| 2,613 | Decomposed Bounded Floats for Fast Compression and Queries | 2021 | VLDB | 8.4503824e-05 |
| 3,644 | BtrBlocks: Efficient Columnar Compression for Data Lakes | 2023 | SIGMOD | 6.8854928e-05 |
| 5,236 | Online Deduplication for Databases | 2017 | SIGMOD | 5.611324e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| Overall Rank | Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,291 | Morphing-based Compression for Data-centric ML Pipelines | 2026 | VLDB | 4.1945683e-05 |
| 6,538 | Tuple-oriented Compression for Large-scale Mini-batch Stochastic Gradient Descent | 2019 | SIGMOD | 5.023239e-05 |
| 4,507 | ALP: Adaptive Lossless floating-Point Compression | 2023 | SIGMOD | 6.131017e-05 |
| 8,786 | AWARE: Workload-aware, Redundancy-exploiting Linear Algebra | 2023 | SIGMOD | 4.4521262e-05 |
| 6,057 | Progressive Compressed Records: Taking a Byte out of Deep Learning Data | 2021 | VLDB | 5.2317752e-05 |
| 10,286 | QStore: Quantization-Aware Compressed Model Storage | 2026 | VLDB | 4.1945683e-05 |
| 11,574 | An Evaluation of Methods of Compressing Doubles | 2020 | SIGMOD | 4.1945683e-05 |
| 1,967 | Compressed Linear Algebra for Large-Scale Machine Learning | 2016 | VLDB | 9.9131712e-05 |
| 9,408 | Experimental Analysis of Large-scale Learnable Vector Storage Compression | 2024 | VLDB | 4.3441378e-05 |
| 4,392 | Elf: Erasing-based Lossless Floating-Point Compression | 2023 | VLDB | 6.2257087e-05 |