Noise Matters: Cross Contrastive Learning for Flink Anomaly Detection
Summary: Cross-contrastive learning that encodes per-timestamp context to capture Flink-specific anomalies (e.g., slow‑rising, sustained high‑level) in streaming metrics. Incorporates prior knowledge as an anomaly boundary to mitigate noisy training data, outperforming SOTA on Flink and public benchmarks. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhihao Zhuang (East China Normal University)
- 2. Yingying Zhang (Alibaba)
- 3. Kai Zhao (Aalborg University)
- 4. Chenjuan Guo (East China Normal University)
- 5. Bin Yang (East China Normal University)
- 6. Qingsong Wen (Squirrel Ai Learning)
- 7. Lunting Fan (Alibaba)
BibTeX Citation
@article{zhuang_vldb25,
title = {{Noise Matters: Cross Contrastive Learning for Flink Anomaly Detection}},
author = {Zhuang, Zhihao and Zhang, Yingying and Zhao, Kai and Guo, Chenjuan and Yang, Bin and Wen, Qingsong and Fan, Lunting},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {4},
pages = {1159--1168},
doi = {10.14778/3717755.3717773},
url = {https://doi.org/10.14778/3717755.3717773},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,382 | TAB: Unified Benchmarking of Time Series Anomaly Detection Methods | 2025 | VLDB | 5.2755515e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 142 | LOF: Identifying Density-Based Local Outliers | 2000 | SIGMOD | 0.0002962566 |
| 3,369 | TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods | 2024 | VLDB | 7.4706661e-05 |
| 6,078 | Multiple Time Series Forecasting with Dynamic Graph Modeling | 2024 | VLDB | 5.9850223e-05 |
| 6,443 | AutoCTS+: Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting | 2023 | SIGMOD | 5.8775356e-05 |
| 11,251 | QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models | 2024 | VLDB | 5.093636e-05 |
| 11,350 | Weakly Guided Adaptation for Robust Time Series Forecasting | 2024 | VLDB | 5.093636e-05 |
| 11,402 | LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation | 2023 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,300 | Time-Series Anomaly Detection: Overview and New Trends | 2024 | VLDB |
| 2 | 10,977 | TSB-AutoAD: Towards Automated Solutions for Time-Series Anomaly Detection | 2025 | VLDB |
| 3 | 5,986 | AutoTSAD: Unsupervised Holistic Anomaly Detection for Time Series Data | 2024 | VLDB |
| 4 | 3,376 | Robust and Transferable Log-based Anomaly Detection | 2023 | SIGMOD |
| 5 | 10,658 | Agree to Disagree: Robust Anomaly Detection with Noisy Labels | 2025 | SIGMOD |
| 6 | 11,099 | MLP-Mixer based Masked Autoencoders Are Effective, Explainable and Robust for Time Series Anomaly Detection | 2025 | VLDB |
| 7 | 9,379 | Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domains | 2025 | VLDB |
| 8 | 1,793 | TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data | 2022 | VLDB |
| 9 | 1,029 | Anomaly Detection in Time Series: A Comprehensive Evaluation | 2022 | VLDB |
| 10 | 6,141 | An Experimental Evaluation of Anomaly Detection in Time Series | 2024 | VLDB |