Skip to content

Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocol

Anomaly detection is a widely explored domain in machine learning. Many models are proposed in the literature, and compared through different metrics measured on various datasets.
The most popular metrics used to compare performances are F1-score, AUC and AVPR.
In this paper, we show that F1-score and AVPR are highly sensitive to the contamination rate.
One consequence is that it is possible to artificially increase their values by modifying the train-test split procedure.
This leads to misleading comparisons between algorithms in the literature, especially when the evaluation protocol is not well detailed.
Moreover, we show that the F1-score and the AVPR cannot be used to compare performances on different datasets as they do not reflect the intrinsic difficulty of modeling such data.
Based on these observations, we claim that F1-score and AVPR should not be used as metrics for anomaly detection. We recommend a generic evaluation procedure for unsupervised anomaly detection, including the use of other metrics such as the AUC, which are more robust to arbitrary choices in the evaluation protocol.

Damien Fourure*, Muhammad Usama Javaid*, Nicolas Posocco*, Simon Tihon*, Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocol, In Proc. of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021.

* equal contributions

Click here to access the paper.

Releated Posts

Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings

In this paper, we study graph representation learning and show that data augmentation that preserves semantics can be learned and used to produce interpretations. Our framework, which we named INGENIOUS, creates inherently interpretable embeddings and eliminates the need for costly additional post-hoc analysis.
Read More

SANGEA: Scalable and Attributed Network Generation

In this paper, we present SANGEA, a sizeable synthetic graph generation framework that extends the applicability of any SGG to large graphs. By first splitting the large graph into communities, SANGEA trains one SGG per community, then links the community graphs back together to create a synthetic large graph.
Read More