We present results for the distance sensitivity oracle (DSO) problem, where one needs to preprocess a given directed weighted graph $G=(V,E)$ in order to answer queries about the shortest path distance from $s$ to $t$ in $G$ that avoids edge $e$, for any $s,t \in V, e \in E$. No non-trivial results are known for DSO in the distributed CONGEST model even though it is of importance to maintain efficient communication under an edge failure. Let $n=|V|$, and let $D$ be the undirected diameter of $G$. Our first DSO algorithm optimizes query response rounds and can answer a batch of any $k\geq 1$ queries in $O(k+D)$ rounds after taking $\tilde{O}(n^{3/2})$ rounds to preprocess $G$. Our second algorithm takes $\tilde{O}(n)$ rounds for preprocessing, and then it can answer any batch of $k\geq 1$ queries in $\tilde{O}(k\sqrt{n}+D)$ rounds. We complement these algorithms with some unconditional CONGEST lower bounds that give trade-offs between preprocessing rounds and rounds needed to answer queries. Additionally, we present almost-optimal upper and lower bounds for the related all pairs second simple shortest path (2-APSiSP) problem, where for all pairs of vertices $x,y \in V$, we need to compute the minimum weight of a simple $x$-$y$ path that differs from the precomputed $x$-$y$ shortest path by at least one edge.
翻译:暂无翻译