Efficient Mining of Frequent Closed XML Query Pattern

Previous research works have presented convincing arguments that afrequent pattern mining algorithm should not mine all frequent but onlythe closed ones because the latter leads to not only more compact yetcomplete result set but also better efficiency. Upon discovery offrequent closed XML query patterns, indexing and caching can beeffectively adopted for query performance enhancement. Most of the previousalgorithms for finding frequent patterns basically introduced astraightforward generate-and-test strategy. In this paper, wepresent SOLARIA^*, an efficient algorithm for mining frequentclosed XML query patterns without candidate maintenance and costlytree-containment checking. Efficient algorithm of sequence mining isinvolved in discovering frequent tree-structured patterns, which aimsat replacing expensive containment testing with cheap parent-childchecking in sequences. SOLARIA^* deeply prunes unrelated searchspace for frequent pattern enumeration by parent-child relationshipconstraint. By a thorough experimental study on various real-life data,we demonstrate the efficiency and scalability of SOLARIA^* overthe previous known alternative. SOLARIA^* is also linearlyscalable in terms of XML queries' size.