The Complexity Landscape of Fixed-Parameter Directed Steiner Network Problems

Given a directed graph $G$ and a list $(s1,t1),\dots,(sd,td)$ of terminal pairs, the Directed Steiner Network problem asks for a minimum-cost subgraph of $G$ that contains a directed $si\to ti$ path for every $1\le i \le k$. The special case Directed Steiner Tree (when we ask for paths from a root $r$ to terminals $t1,\dots,td$) is known to be fixed-parameter tractable parameterized by the number of terminals, while the special case Strongly Connected Steiner Subgraph (when we ask for a path from every $ti$ to every other $tj$) is known to be W[1]-hard. We systematically explore the complexity landscape of directed Steiner problems to fully understand which other special cases are FPT or W[1]-hard. Formally, if $\mathcal{H}$ is a class of directed graphs, then we look at the special case of Directed Steiner Network where the list $(s1,t1),\dots,(sd,td)$ of requests form a directed graph that is a member of $\mathcal{H}$. Our main result is a complete characterization of the classes $\mathcal{H}$ resulting in fixed-parameter tractable special cases: we show that if every pattern in $\mathcal{H}$ has the combinatorial property of being "transitively equivalent to a bounded-length caterpillar with a bounded number of extra edges," then the problem is FPT, and it is W[1]-hard for every recursively enumerable $\mathcal{H}$ not having this property. This complete dichotomy unifies and generalizes the known results showing that Directed Steiner Tree is FPT [Dreyfus and Wagner, Networks 1971], $q$-Root Steiner Tree is FPT for constant $q$ [Such\'y, WG 2016], Strongly Connected Steiner Subgraph is W[1]-hard [Guo et al., SIAM J. Discrete Math. 2011], and Directed Steiner Network is solvable in polynomial-time for constant number of terminals [Feldman and Ruhl, SIAM J. Comput. 2006], and moreover reveals a large continent of tractable cases that were not known before.