%0 Journal Article
%T 图数据领域的频繁项集挖掘<br>Frequent Itemset Mining in the Graph Data Field
%A 邱文韬
%A 兰红
%J Computer Science and Application
%P 158-172
%@ 2161-881X
%D 2024
%I Hans Publishing
%R 10.12677/CSA.2024.141017
%X <span style=\"font-size:14px;\">本文对图数据中的频繁子图挖掘算法进行了综述。追溯了从传统非图数据频繁项集挖掘技术到图数据频繁子图挖掘的演化，详细阐述了经典算法如类Apriori方法和gSpan算法的原理与应用。也对近年来兴起的基于图表示学习的先进算法，如SPMiner、NSIC、LSS和NeurSC进行了系统的介绍和比较。本文不仅回顾了算法的历史演进，还对各类算法进行了详细的分析与讨论，通过分析这些算法的性能和特点，揭示了它们的优势与局限。最后，展望了图神经网络在频繁子图挖掘领域的未来发展方向，并指出了这些技术在生物网络分析、社交网络分析等领域应用的广阔前景。</span><br />
<span style=\"font-size:14px;\">We present a comprehensive review of frequent subgraph mining algorithms in graph data. We trace the evolution from traditional frequent itemset mining techniques for non-graph data to the current state-of-the-art in frequent subgraph mining for graph data, elaborating on the principles and applications of classic algorithms such as Apriori-like methods and the gSpan algorithm. We also systematically introduce and compare recent advanced algorithms that have emerged from graph representation learning, including SPMiner, NSIC, LSS, and NeurSC. We not only recount the historical progression of these algorithms but also provide a detailed analysis and discussion of each category. By examining their performance and characteristics, we reveal their advantages and limitations. Finally, we anticipate the future trajectory of graph neural networks in the field of fre-quent subgraph mining and highlight the vast potential for these technologies in applications like biological network analysis and social network analysis.</span>
%K 频繁项集挖掘，图数据，频繁子图，图神经网络，机器学习<br>Frequent Itemset Mining
%K Graph Data
%K Frequent Subgraphs
%K Graph Neural Networks
%K Machine Learning
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=80318