Diya Roy | Searcharxiv

arXiv2026

Exploiting Graph Structure for Near-Optimal Broadcasting

Telephone broadcasting is a classical model for spreading information in a network. Given a connected graph $G(V,E)$ with source vertex $s$, each informed vertex may inform exactly one uninformed neighbor in every time step. The \textsc{Broadcasting} problem asks whether all vertices can be informed within $t$ steps; the minimum such value is the broadcast time $b(G,s)$. A related variant considers the worst-case source, $b(G)=\max_{u\in V} b(G,u)$. Both variants are NP-hard, and every $n$-vertex graph satisfies $b(G,s)\ge \log_2 n$. Fomin \textit{et al.}~\cite{fomin2023parameterized} recently gave FPT algorithms for this problem under several structural graph parameters. Instead of computing optimal broadcast schedules, we study faster approximation algorithms that produce valid schedules. We improve the $O^*(3^n)$ exact algorithm of Fomin \textit{et al.} to an $O^*((3-f(x))^n)$ algorithm with a $+x$ additive approximation, where $f(x)>0$ is a constant for every fixed $x$. We also give approximation algorithms on graphs of bounded vertex integrity, including a polynomial-time $+2k$ additive approximation algorithm. Complementing these positive results, we prove parameterized hardness for vertex cover above maximum matching ($\mathrm{VC}-\mathrm{MM}$), dominating set size, and graph diameter, indicating that FPT algorithms for these parameters are unlikely. Finally, we present a $+2$ additive approximation algorithm for distance-to-clique running in $O^*(2^{O(k\log k)})$ time, a $2$-factor approximation algorithm for distance-to-path running in XP time, and a polynomial-time algorithm for polar graphs.

cs.DS↗

arXiv2025

Learning with Structure: Computing Consistent Subsets on Structurally-Regular Graphs

The Minimum Consistent Subset (MCS) problem arises naturally in the context of supervised clustering and instance selection. In supervised clustering, one aims to infer a meaningful partitioning of data using a small labeled subset. However, the sheer volume of training data in modern applications poses a significant computational challenge. The MCS problem formalizes this goal: given a labeled dataset $\mathcal{X}$ in a metric space, the task is to compute a smallest subset $S \subseteq \mathcal{X}$ such that every point in $\mathcal{X}$ shares its label with at least one of its nearest neighbors in $S$. Recently, the MCS problem has been extended to graph metrics, where distances are defined by shortest paths. Prior work has shown that MCS remains NP-hard even on simple graph classes like trees, though an algorithm with runtime $\mathcal{O}(2^{6c} \cdot n^6)$ is known for trees, where $c$ is the number of colors and $n$ the number of vertices. This raises the challenge of identifying graph classes that admit algorithms efficient in both $n$ and $c$. In this work, we study the Minimum Consistent Subset problem on graphs, focusing on two well-established measures: the vertex cover number ($vc$) and the neighborhood diversity ($nd$). We develop an algorithm with running time $vc^{\mathcal{O}(vc)}\cdot\text{Poly}(n,c)$, and another algorithm with runtime $nd^{\mathcal{O}(nd)}\cdot\text{Poly}(n,c)$. In the language of parameterized complexity, this implies that MCS is fixed-parameter tractable (FPT) parameterized by the vertex cover number and the neighborhood diversity. Notably, our algorithms remain efficient for arbitrarily many colors, as their complexity is polynomially dependent on the number of colors.

cs.DS↗