Maximum Independent Set: Self-Training through Dynamic Programming

Autor:	Brusca, Lorenzo, Quaedvlieg, Lars C. P. M., Skoulakis, Stratis, Chrysos, Grigorios G, Cevher, Volkan
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Discrete Mathematics
Druh dokumentu:	Working Paper
Popis:	This work presents a graph neural network (GNN) framework for solving the maximum independent set (MIS) problem, inspired by dynamic programming (DP). Specifically, given a graph, we propose a DP-like recursive algorithm based on GNNs that firstly constructs two smaller sub-graphs, predicts the one with the larger MIS, and then uses it in the next recursive call. To train our algorithm, we require annotated comparisons of different graphs concerning their MIS size. Annotating the comparisons with the output of our algorithm leads to a self-training process that results in more accurate self-annotation of the comparisons and vice versa. We provide numerical evidence showing the superiority of our method vs prior methods in multiple synthetic and real-world datasets. Comment: Accepted in NeurIPS 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2310.18672 Zobrazit plný text záznamu View this record from Arxiv