Research on the design of teaching aid resource system based on unsupervised representation learning

In the absence of manual annotation information, using only the topology information of the graph to achieve unsupervised graph alignment has always been one of the important challenges faced by graph data mining, especially in the large-scale graph alignment task, the discovery of initial seed nodes and the low computational efficiency have always been a problem. This paper proposes a large-scale unsupervised graph-aligned physical education teaching resource system framework based on topological representation learning, which is highly scalable and adaptable. Firstly, representative subgraphs are selected from the graph to be matched as seed node candidate sets, and the local topology information is used to calculate to obtain highly reliable seed node matching results; then, the obtained seed nodes are used to integrate the graph to be matched, and an efficient unsupervised representation learning algorithm is proposed to map the fusion graph to a unified vector space; finally the obtained node vectors are used to achieve the alignment of large-scale graphs. The proposed technique shows the shortest time when dealing with large-scale graph alignment tasks, and at the same time reaches the highest level of accuracy of alignment results, in addition, the performance of the physical education auxiliary resource system algorithm has the least impact on the difference of graph structure.