By rapid progress of network and storage technologies, a huge amount of electronic data such as Web pages and XML has been available on Internet. In this paper, we study a data-mining problem of discovering frequent o...By rapid progress of network and storage technologies, a huge amount of electronic data such as Web pages and XML has been available on Internet. In this paper, we study a data-mining problem of discovering frequent ordered sub-trees in a large collection of XML data, where both of the patterns and the data are modeled by labeled ordered trees. We present an efficient algorithm of Ordered Subtree Miner （OSTMiner） based on two- layer neural networks with Hebb rule, that computes all ordered sub-trees appearing in a collection of XML trees with frequent above a user-specified threshold using a special structure EM-tree. In this algo- rithm, EM-tree is used as an extended merging tree to supply scheme information for efficient pruning and mining frequent sub-trees. Experiments results showed that OSTMiner has good response time and scales well.展开更多
The number of frequent subtrees usually grows exponentially with the tree size because of combinatorial explosion. As a result, there are too many frequent subtrees for users to manage and use. To solve this problem, ...The number of frequent subtrees usually grows exponentially with the tree size because of combinatorial explosion. As a result, there are too many frequent subtrees for users to manage and use. To solve this problem, we generalize a compressed frame based on δ-cluster to the problem of compressing frequent-subtree sets, and propose an algorithm RPTlocal which can mine compressed frequent subtrees set directly. This algorithm sacrifices the theoretical bounds but still has good compression quality. By pruning the search space and generating frequent subtrees directly, this algorithm is also efficient. Experiment result shows that the representative subtrees mining by RPTlocal is almost two orders of magnitude less than the whole collection of the closed subtrees, and is more efficient than CMtreeMiner, the algorithm for mining both closed and Maximal frequent subtrees.展开更多
基金Supported by Key Science-Technology Project ofHeilongjiang Province(GA010401-3)
文摘By rapid progress of network and storage technologies, a huge amount of electronic data such as Web pages and XML has been available on Internet. In this paper, we study a data-mining problem of discovering frequent ordered sub-trees in a large collection of XML data, where both of the patterns and the data are modeled by labeled ordered trees. We present an efficient algorithm of Ordered Subtree Miner （OSTMiner） based on two- layer neural networks with Hebb rule, that computes all ordered sub-trees appearing in a collection of XML trees with frequent above a user-specified threshold using a special structure EM-tree. In this algo- rithm, EM-tree is used as an extended merging tree to supply scheme information for efficient pruning and mining frequent sub-trees. Experiments results showed that OSTMiner has good response time and scales well.
基金Supported by the National Natural Science Foundation of China (70371015)
文摘The number of frequent subtrees usually grows exponentially with the tree size because of combinatorial explosion. As a result, there are too many frequent subtrees for users to manage and use. To solve this problem, we generalize a compressed frame based on δ-cluster to the problem of compressing frequent-subtree sets, and propose an algorithm RPTlocal which can mine compressed frequent subtrees set directly. This algorithm sacrifices the theoretical bounds but still has good compression quality. By pruning the search space and generating frequent subtrees directly, this algorithm is also efficient. Experiment result shows that the representative subtrees mining by RPTlocal is almost two orders of magnitude less than the whole collection of the closed subtrees, and is more efficient than CMtreeMiner, the algorithm for mining both closed and Maximal frequent subtrees.
