Identifying important patents helps to drive business growth and focus investment. In the past, centralitymeasures such as degree centrality and betweenness centrality have been applied to identify influentialor important patents in patent citation networks. How such a complex process like technological changecan be analyzed is an important research topic. However, no existing centrality measure leverages thepowerful graph kernels for this end. This paper presents a new centrality measure based on the changeof the node similarity matrix after leveraging graph kernels. The proposed approach provides a morerobust understanding of the identification of influential nodes, since it focuses on graph structure informationby considering direct and indirect patent citations. This study begins with the premise that thechange of similarity matrix that results from removing a given node indicates the importance of the nodewithin its network, since each node makes a contribution to the similarity matrix among nodes. Wecalculate the change of the similarity matrix norms for a given node after we calculate the singular valuesfor the case of the existence and the case of nonexistence of that node within the network. Then, the noderesulting in the largest change (i.e., decrease) in the similarity matrix norm is considered to be themost influential node. We compare the performance of our proposed approach with other widely-usedcentrality measures using artificial data and real-life U.S. patent data. Experimental results show thatour proposed approach performs better than existing methods.