Fremer: Lightweight and Effective Frequency Transformer for Workload Forecasting in Cloud Services
Summary: Fremer is a lightweight frequency-domain Transformer tailored to complex, multi-period cloud workloads, delivering SOTA accuracy with substantially lower parameters and compute. Its ByteDance-scale datasets and Kubernetes evaluation show practical gains: 18.78% lower latency and 2.35% less resource use. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Hengyu Ye (Shanghai Jiao Tong University)
- 2. Jiadong Chen (Shanghai Jiao Tong University; University of New South Wales)
- 3. Fuxin Jiang (ByteDance)
- 4. Xiao He (ByteDance)
- 5. Tieying Zhang (ByteDance)
- 6. Jianjun Chen (ByteDance)
- 7. Xiaofeng Gao (Shanghai Jiao Tong University)
BibTeX Citation
@article{ye_vldb25,
title = {{Fremer: Lightweight and Effective Frequency Transformer for Workload Forecasting in Cloud Services}},
author = {Ye, Hengyu and Chen, Jiadong and Jiang, Fuxin and He, Xiao and Zhang, Tieying and Chen, Jianjun and Gao, Xiaofeng},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {3812--3825},
doi = {10.14778/3749646.3749656},
url = {https://doi.org/10.14778/3749646.3749656},
year = {2025}
}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 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,369 | TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods | 2024 | VLDB | 7.4706661e-05 |
| 8,517 | OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting | 2023 | VLDB | 5.4119882e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,283 | A Flexible Forecasting Stack | 2024 | VLDB |
| 2 | 4,424 | Classical and Contemporary Approaches to Big Time Series Forecasting | 2019 | SIGMOD |
| 3 | 461 | Query-based Workload Forecasting for Self-Driving Database Management Systems | 2018 | SIGMOD |
| 4 | 11,291 | OptScaler: A Collaborative Framework for Robust Autoscaling in the Cloud | 2024 | VLDB |
| 5 | 13,318 | Fully Automated Correlated Time Series Forecasting in Minutes | 2025 | VLDB |
| 6 | 5,158 | Forecasting Big Time Series: Old and New | 2018 | VLDB |
| 7 | 11,266 | DARKER: Efficient Transformer with Data-driven Attention Mechanism for Time Series | 2024 | VLDB |
| 8 | 13,320 | A Memory Guided Transformer for Time Series Forecasting | 2025 | VLDB |
| 9 | 6,673 | Database Workload Capacity Planning using Time Series Analysis and Machine Learning | 2020 | SIGMOD |
| 10 | 5,498 | SimpleTS: An Efficient and Universal Model Selection Framework for Time Series Forecasting | 2023 | VLDB |