Agree to Disagree: Robust Anomaly Detection with Noisy Labels
Summary: Unity: LNL for anomaly detection uniting sample selection and label refurbishment. Dual nets agree to pick clean labels, resolve disagreements for marginal cases, and apply anomaly-centric contrastive learning to refurbish the rest; iterative training yields strong F1 gains on 10 real datasets. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Dennis M. Hofmann (Worcester Polytechnic Institute)
- 2. Peter M. VanNostrand (Worcester Polytechnic Institute)
- 3. Lei Ma (Worcester Polytechnic Institute)
- 4. Huayi Zhang (ByteDance; Worcester Polytechnic Institute)
- 5. Joshua C. DeOliveira (Worcester Polytechnic Institute)
- 6. Lei Cao (Massachusetts Institute of Technology; University of Arizona)
- 7. Elke A. Rundensteiner (Worcester Polytechnic Institute)
BibTeX Citation
@inproceedings{hofmann_sigmod25,
title = {{Agree to Disagree: Robust Anomaly Detection with Noisy Labels}},
author = {Hofmann, Dennis M. and VanNostrand, Peter M. and Ma, Lei and Zhang, Huayi and DeOliveira, Joshua C. and Cao, Lei and Rundensteiner, Elke A.},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3709657},
url = {https://dl.acm.org/doi/10.1145/3709657},
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 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 |
|---|---|---|---|---|
| 1,833 | MacroBase: Prioritizing Attention in Fast Data | 2017 | SIGMOD | 9.5405247e-05 |
| 1,937 | TSB-UAD: An End-to-End Benchmark Suite for Univariate Time-Series Anomaly Detection | 2022 | VLDB | 9.3387043e-05 |
| 3,449 | Robust and Transferable Log-based Anomaly Detection | 2023 | SIGMOD | 7.2931951e-05 |
| 4,103 | AutoOD: Automatic Outlier Detection | 2023 | SIGMOD | 6.8066074e-05 |
| 5,148 | Unsupervised Contextual Anomaly Detection for Database Systems | 2022 | SIGMOD | 6.255522e-05 |
| 7,648 | MisDetect: Iterative Mislabel Detection using Early Loss | 2024 | VLDB | 5.4772833e-05 |
| 9,036 | LANCET: Labeling Complex Data at Scale | 2021 | VLDB | 5.2332952e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,103 | AutoOD: Automatic Outlier Detection | 2023 | SIGMOD |
| 2 | 3,726 | Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time Series | 2023 | VLDB |
| 3 | 1,740 | TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data | 2022 | VLDB |
| 4 | 9,567 | TAB: Unified Benchmarking of Time Series Anomaly Detection Methods | 2025 | VLDB |
| 5 | 11,451 | MLP-Mixer based Masked Autoencoders Are Effective, Explainable and Robust for Time Series Anomaly Detection | 2025 | VLDB |
| 6 | 6,073 | AutoTSAD: Unsupervised Holistic Anomaly Detection for Time Series Data | 2024 | VLDB |
| 7 | 6,268 | An Experimental Evaluation of Anomaly Detection in Time Series | 2024 | VLDB |
| 8 | 11,343 | CoLA: Model Collaboration for Log-based Anomaly Detection | 2025 | VLDB |
| 9 | 11,221 | Noise Matters: Cross Contrastive Learning for Flink Anomaly Detection | 2025 | VLDB |
| 10 | 3,449 | Robust and Transferable Log-based Anomaly Detection | 2023 | SIGMOD |