Graph-Based Feature Selection Filter Utilizing Maximal Cliques

Huge amounts of data are collected every millisecond all around the world. This ranges from images and videos to an increasing amount of sensor data. Thus, it gets difficult for humans to decide on the most important features anymore. But reducing the feature vector is an important and necessary task to achieve higher precision in classification tasks. Detecting anomalies and classifying data points is crucial for a variety of objectives in many domains. Therefore, this work focuses on feature selection for binary decision problems (e.g. anomaly detection, binary classification). We propose a novel graph-based feature selection filter, which takes into account both the importance and correlation of features at the same time. The graph-based feature selection filter recommends a subset by applying a rating function onto the maximal cliques of the graph. The evaluation is based on a comparison of the accuracy of multiple machine learning algorithms and datasets between different baseline feature selection approaches and the proposed approach. Results show that the proposed approach delivers the highest accuracy in about 69% of the cases compared to existing approaches, while reducing the number of features.

Download paper here

Bibtex

@inproceedings{SchroederSSAK19,
  author    = {Daniel Thilo Schroeder and
               Kevin Styp-Rekowski and
               Florian Schmidt and
               Alexander Acker and
               Odej Kao},
  editor    = {Mohammad A. Alsmirat and
               Yaser Jararweh},
  title     = {Graph-based Feature Selection Filter Utilizing Maximal Cliques},
  booktitle = {Sixth International Conference on Social Networks Analysis, Management
               and Security, SNAMS 2019, Granada, Spain, October 22-25, 2019},
  pages     = {297--302},
  publisher = {IEEE},
  year      = {2019},
  url       = {https://doi.org/10.1109/SNAMS.2019.8931841},
  doi       = {10.1109/SNAMS.2019.8931841},
  timestamp = {Fri, 08 May 2020 10:17:28 +0200},
  biburl    = {https://dblp.org/rec/conf/snams/SchroederSSAK19.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}