QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models
Summary: QCore enables continual, on-device calibration of quantized models under distribution shift. It maintains a compact, evolving data core and uses a lightweight bit-flipping network instead of backpropagation, preserving past knowledge with low storage and compute. (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. David Campos (Aalborg University)
- 2. Bin Yang (East China Normal University)
- 3. Tung Kieu (Aalborg University)
- 4. Miao Zhang (Harbin Engineering University)
- 5. Chenjuan Guo (East China Normal University)
- 6. Christian S. Jensen (Aalborg University)
BibTeX Citation
@article{campos_vldb24,
title = {{QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models}},
author = {Campos, David and Yang, Bin and Kieu, Tung and Zhang, Miao and Guo, Chenjuan and Jensen, Christian S.},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {11},
pages = {2708--2721},
doi = {10.14778/3681954.3681957},
url = {https://doi.org/10.14778/3681954.3681957},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,433 | TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods | 2024 | VLDB | 7.2995872e-05 |
| 11,229 | Noise Matters: Cross Contrastive Learning for Flink Anomaly Detection | 2025 | VLDB | 4.9769913e-05 |
| 11,272 | Less is More: Efficient Time Series Dataset Condensation via Two-fold Modal Matching | 2025 | VLDB | 4.9769913e-05 |
| 11,293 | TEAM: Topological Evolution-aware Framework for Traffic Forecasting | 2025 | VLDB | 4.9769913e-05 |
| 13,646 | Fully Automated Correlated Time Series Forecasting in Minutes | 2025 | VLDB | - |
| 13,648 | A Memory Guided Transformer for Time Series Forecasting | 2025 | VLDB | - |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 15 of 15 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 | 6,249 | ColumnML: Column-Store Machine Learning with On-The-Fly Data Transformation | 2019 | VLDB |
| 2 | 12,151 | Query-Driven Learning for Next Generation Predictive Modeling & Analytics | 2019 | SIGMOD |
| 3 | 8,820 | FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement | 2023 | SIGMOD |
| 4 | 7,203 | Coresets over Multiple Tables for Feature-rich and Data-efficient Machine Learning | 2023 | VLDB |
| 5 | 11,460 | Datamap-Driven Tabular Coreset Selection for Classifier Training | 2025 | VLDB |
| 6 | 3,942 | GoodCore: Data-effective and Data-efficient Machine Learning through Coreset Selection over Incomplete Data | 2023 | SIGMOD |
| 7 | 3,971 | Optimizing Machine Learning Inference Queries with Correlative Proxy Models | 2022 | VLDB |
| 8 | 10,150 | QStore: Quantization-Aware Compressed Model Storage | 2026 | VLDB |
| 9 | 3,286 | Camel: Managing Data for Efficient Stream Learning | 2022 | SIGMOD |
| 10 | 11,884 | Efficient and Error-bounded Spatiotemporal Quantile Monitoring in Edge Computing Environments | 2022 | VLDB |