Graph Reconstruction via MIS Queries

We consider the Graph Reconstruction problem given only query access to the input graph via a Maximal Independent Set oracle. In this setting, in each round, the player submits a query consisting of a subset of vertices to the oracle, and the oracle returns any maximal independent set in the subgraph induced by the queried vertices. The goal for the player is to learn all the edges of the input graph. In this paper, we give tight (up to poly-logarithmic factors) upper and lower bounds for this problem: 1. We give a randomized query algorithm that uses $O(\Delta² \log n)$ non-adaptive queries and succeeds with high probability to reconstruct an $n$-vertex graph with maximum degree $\Delta$. We also show that there is a non-adaptive deterministic algorithm that executes $O(\Delta³ \log n)$ queries. 2. We show that every non-adaptive deterministic algorithm requires $\Omega(\Delta³ / \log² \Delta)$ rounds, which renders our deterministic algorithm optimal, up to poly-logarithmic factors. 3. We also give two lower bounds that apply to arbitrary adaptive randomized algorithms that succeed with probability strictly greater than $\frac{1}{2}$. We show that, for such algorithms, $\Omega(\Delta^2)$ rounds are necessary in graphs of maximum degree $\Delta$, and that $\Omega(\log n)$ rounds are necessary even when the input graph is an $n$-vertex cycle.