{"title":"Knowledge Extraction from Auto-Encoders on Anomaly Detection Tasks Using Co-activation Graphs","authors":"Daniyal Selani, Ilaria Tiddi","doi":"10.1145/3460210.3493571","DOIUrl":null,"url":null,"abstract":"Deep neural networks have exploded in popularity and different types of networks are used to solve a multitude of complex tasks. One such task is anomaly detection, that a type of deep neural network called auto-encoder has become extremely proficient at solving. The low level neural activity, produced by such a network, generates extremely rich representations of the data, which can be used to extract task specific knowledge. In this paper, we built upon previous work and used co-activation graph analysis to extract knowledge from auto-encoders, that were trained for the specific task of anomaly detection. First, we outlined a method for extracting co-activation graphs from auto-encoders. Then, we performed graph analysis to discover that task specific knowledge from the auto-encoder was being encoded into the co-activation graph, and that the extracted knowledge could be used to reveal the role of individual neurons in the network.","PeriodicalId":377331,"journal":{"name":"Proceedings of the 11th on Knowledge Capture Conference","volume":"482 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 11th on Knowledge Capture Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3460210.3493571","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Deep neural networks have exploded in popularity and different types of networks are used to solve a multitude of complex tasks. One such task is anomaly detection, that a type of deep neural network called auto-encoder has become extremely proficient at solving. The low level neural activity, produced by such a network, generates extremely rich representations of the data, which can be used to extract task specific knowledge. In this paper, we built upon previous work and used co-activation graph analysis to extract knowledge from auto-encoders, that were trained for the specific task of anomaly detection. First, we outlined a method for extracting co-activation graphs from auto-encoders. Then, we performed graph analysis to discover that task specific knowledge from the auto-encoder was being encoded into the co-activation graph, and that the extracted knowledge could be used to reveal the role of individual neurons in the network.