Semantic Guided and Response Times Bounded Top-k Similarity Search over Knowledge Graphs

Abstract

Recently, graph query is widely adopted for querying knowledge graphs. Given a query graph GQ, graph query finds subgraphs in a knowledge graph G that exactly or approximately match GQ. We face two challenges on graph query over a knowledge graph: (1) the structural gap between GQ and the predefined schema in G causes mismatch with query graph, (2) users cannot view the answers until the graph query terminates, leading to a longer system response time (SRT). In this paper, we propose a semantic guided and response-timebounded graph query to return top-k answers effectively and efficiently. We first leverage a knowledge graph embedding model to build the semantic graph SGQ for each GQ. Then we define the path semantic similarity (pss) over SGQ to evaluate the answer's quality. We propose an A* semantic search on SGQ to find top-k answers with the greatest pss via a heuristic pss estimation. Furthermore, we make an approximate optimization on A* semantic search to allow users to trade off the effectiveness for SRT within a user-specific time bound. Extensive experiments over real datasets confirm the effectiveness and efficiency.