Efficient Approximation Algorithms for the Diameter-Bounded Max-Coverage Group Steiner Tree Problem

The Diameter-bounded max-Coverage Group Steiner Tree (DCGST) problem has recently been proposed as an expressive way of formulating keyword-based search and exploration of knowledge graphs. It aims at finding a diameter-bounded tree which covers the most given groups of vertices and has the minimum weight. In contrast to its specialization—the classic Group Steiner Tree (GST) problem which has been extensively studied, the emerging DCGST problem still lacks an efficient algorithm. In this paper, we propose Cba, the first approximation algorithm for the DCGST problem, and we prove its worst-case approximation ratio. Furthermore, we incorporate a best-first search strategy with two pruning methods into PrunedCBA, an improved approximation algorithm. Our extensive experiments on real and synthetic graphs demonstrate the effectiveness and efficiency of PrunedCBA.