Tree-based Learning

Decision Trees, Random Forests, Extremely Randomized Trees, Isolation Forests, Mondrian Forests and many others all have an important role to play in Machine Learning research and applciations. While they may not be ultimately as powerful for unstructured data as Deep Learning, Tree-based methods are fully general and can be computed and learned relatively quickly. They also leave open the potential for interpretation.
Ma, H. et al., 2020. Isolation Mondrian Forest for Batch and Online Anomaly Detection. IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2020. Available at: arXiv preprint arXiv:2003.03692. Also available at:
See also: Tree-based Learning, Anomaly Detection, Anomaly Detection, Highlighted Papers
Abstract
imondrian.pdf

We propose a new method, named isolation Mon- drian forest (iMondrian forest), for batch and online anomaly detection. The proposed method is a novel hybrid of isolation forest and Mondrian forest which are existing methods for batch anomaly detection and online random forest, respectively. iMondrian forest takes the idea of isolation, using the depth of a node in a tree, and implements it in the Mondrian forest structure. The result is a new data structure which can accept streaming data in an online manner while being used for anomaly detection. Our experiments show that iMondrian forest mostly performs better than isolation forest in batch settings and has better or comparable performance against other batch and online anomaly detection methods.