The integrative mining of heterogeneous data and the interpretability of the data mining result are two of the most important challenges of today's data mining. It is commonly agreed in the community that, particularly in the research area of clustering, both challenges have not yet received the due attention. Only few approaches for clustering of objects with mixed-type attributes exist and those few approaches do not consider cluster-specific dependencies between numerical and categorical attributes. Likewise, only a few clustering papers address the problem of interpretability: to explain why a certain set of objects have been grouped into a cluster and what a particular cluster distinguishes from another. In this paper, we approach both challenges by constructing a relationship to the concept of data compression using the Minimum Description Length principle: a detected cluster structure is the better the more efficient it can be exploited for data compression. Following this idea, we can learn, during the run of a clustering algorithm, the optimal trade-off for attribute weights and distinguish relevant attribute dependencies from coincidental ones. We extend the efficient Cholesky decomposition to model dependencies in heterogeneous data and to ensure interpretability. Our proposed algorithm, INCONCO, successfully finds clusters in mixed type data sets, identifies the relevant attribute dependencies, and explains them using linear models and case-by-case analysis. Thereby, it outperforms existing approaches in effectiveness, as our extensive experimental evaluation demonstrates.
{"title":"INCONCO","authors":"C. Plant, Christian Böhm","doi":"10.1145/2020408.2020584","DOIUrl":"https://doi.org/10.1145/2020408.2020584","url":null,"abstract":"The integrative mining of heterogeneous data and the interpretability of the data mining result are two of the most important challenges of today's data mining. It is commonly agreed in the community that, particularly in the research area of clustering, both challenges have not yet received the due attention. Only few approaches for clustering of objects with mixed-type attributes exist and those few approaches do not consider cluster-specific dependencies between numerical and categorical attributes. Likewise, only a few clustering papers address the problem of interpretability: to explain why a certain set of objects have been grouped into a cluster and what a particular cluster distinguishes from another. In this paper, we approach both challenges by constructing a relationship to the concept of data compression using the Minimum Description Length principle: a detected cluster structure is the better the more efficient it can be exploited for data compression. Following this idea, we can learn, during the run of a clustering algorithm, the optimal trade-off for attribute weights and distinguish relevant attribute dependencies from coincidental ones. We extend the efficient Cholesky decomposition to model dependencies in heterogeneous data and to ensure interpretability. Our proposed algorithm, INCONCO, successfully finds clusters in mixed type data sets, identifies the relevant attribute dependencies, and explains them using linear models and case-by-case analysis. Thereby, it outperforms existing approaches in effectiveness, as our extensive experimental evaluation demonstrates.","PeriodicalId":244646,"journal":{"name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '11","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126349393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social media is becoming increasingly ubiquitous and popular on the Internet. Due to the huge popularity of social media websites, such as Facebook, Twitter, YouTube and Flickr, many companies or public figures are now active in maintaining pages on those websites to interact with online users, attracting a large number of fans/followers by posting interesting objects, e.g., (product) photos/videos and text messages. 'Like' has now become a very popular social function by allowing users to express their like of certain objects. It provides an accurate way of estimating user interests and an effective way of sharing/promoting information in social media. In this demo, we propose a system called LikeMiner to mine the power of 'like' in social media networks. We introduce a heterogeneous network model for social media with 'likes', and propose 'like' mining algorithms to estimate representativeness and influence of objects. The implemented prototype system demonstrates the effectiveness of the proposed approach using the large scale Facebook data.
{"title":"LikeMiner","authors":"Xin Jin, Chi Wang, Jiebo Luo, Xiao Yu, Jiawei Han","doi":"10.1145/2020408.2020528","DOIUrl":"https://doi.org/10.1145/2020408.2020528","url":null,"abstract":"Social media is becoming increasingly ubiquitous and popular on the Internet. Due to the huge popularity of social media websites, such as Facebook, Twitter, YouTube and Flickr, many companies or public figures are now active in maintaining pages on those websites to interact with online users, attracting a large number of fans/followers by posting interesting objects, e.g., (product) photos/videos and text messages. 'Like' has now become a very popular social function by allowing users to express their like of certain objects. It provides an accurate way of estimating user interests and an effective way of sharing/promoting information in social media. In this demo, we propose a system called LikeMiner to mine the power of 'like' in social media networks. We introduce a heterogeneous network model for social media with 'likes', and propose 'like' mining algorithms to estimate representativeness and influence of objects. The implemented prototype system demonstrates the effectiveness of the proposed approach using the large scale Facebook data.","PeriodicalId":244646,"journal":{"name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '11","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125484265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：