The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Interpretable Unsupervised Anomaly Detection For RAN Cell Trace Analysis
Abstract
The high complexity of modern communication networks requires an increasing degree of automation for performance and fault management tasks. A key task is the classification and identification of anomalous operation modes (and faults). This is important to separate them from normal operation conditions. In addition, these diagnoses should be interpretable by domain experts to (a) gain acceptance by these experts and (b) support effective root cause analysis and localisation. In this paper, we investigate the analysis of multivariant network data in order to identify anomalous data instances. Root cause analysis benefits from this by filtering features whose values lead (to some extent) to such anomalies. We are using Deep Neural Networks (DNNs), a powerful tool for anomaly detection in the telecommunication domain. We demonstrate the effectiveness of autoencoders (an unsupervised technique) to detect multivariant anomalies and anomalous features. To overcome the black box nature of neural networks (and thus increase their acceptance by domain experts), we apply SHapley Additive exPlanations (SHAP), which are used to explain the output model of a neural network.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“First of all, Shapley values-based techniques such as SHAP are typically used to obtain feature contributions for explaining AEs.”
From A Survey on Explainable Anomaly Detection (2024) · cites this paper as [40]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623
Chai, T., & Draxler, R. R. (2014) · Geoscientific Model Development · doi:10.5194/gmd-7-1247-2014 · Cited by 7,178 · cited 1×
“The Root Mean Squared Error (RMSE) [18] is used as an evaluation metric to calculate the squared error difference between the observed ( x ) and predicted ( x (cid:48) ) values of a set of n .”
MethodSaito, T., & Rehmsmeier, M. (2015) · PLOS ONE · doi:10.1371/journal.pone.0118432 · Cited by 5,309
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
Feature selection, L 1 vs. L 2 regularization, and rotational invariance
Ng, A. Y. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015435 · Cited by 1,572 · cited 1×
“We add an L1 norm regularization [21] which learns sparse and enlarged representation of the input data.”
MethodLearning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing
Li, H., Ota, K., & Dong, M. (2018) · IEEE Network · doi:10.1109/mnet.2018.1700202 · Cited by 1,566
Hecht-Nielsen, R. (1992) · Elsevier eBooks · doi:10.1016/b978-0-12-741252-8.50010-8 · Cited by 1,052
Research works printed but not linked: 4
- wang, 2018, Anomaly Detection for Mobie Network Management, International Journal of Next-Generative Computing, 9, 80
- mnih, 2016, Asynchronous methods for deep reinforcement learning, International Conference on Machine Learning, 1928
- arjovsky, 2017, Wasserstein GAN, 1050, 26
- lundberg, 2017, A unified approach to interpreting model predictions, Advances in neural information processing systems, 4765
Cited by
Sorted by citations
A Survey on Explainable Anomaly Detection
Li, Z., Zhu, Y., & Van Leeuwen, M. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3609333 · Cited by 139
“[40] set up a Sparse AutoEncoder (SAE) based anomaly detection algorithm and then applies kernel SHAP to explain the results.”
Method
Metadata
- Authors
- Chawla, A., Jacob, P., Feghhi, S., Rughwani, D., van der Meer, S., & Fallon, S.
- Affiliations
- Athlone Institute of Technology (IE)
- Ericsson (Ireland) (IE)
- Venue
- 2020 16th International Conference on Network and Service Management (CNSM)
- Publisher
- IEEE
- Published
- 2020-11-02
- Pages
- 1-5
- OpenAlex
- W3108357108
- Cited by
- 14
- References
- 22
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 4 · 2023: 3 · 2022: 2 · 2021: 1
- FWCI
- 0.57
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Network and Service Management (CNSM) (publishedVersion)
- Funders
- Irish Research Council
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- unsupervised anomaly detection, radio access network, interpretability, SHAP, autoencoder, deep neural network, root cause analysis, fault diagnosis, telecommunications networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
