Large-scale Urban Facility Location Selection with Knowledge-informed Reinforcement Learning
Abstract: The facility location problem (FLP) is a classical combinatorial optimization challenge aimed at strategically laying out facilities to maximize their accessibility. In this paper, we propose a reinforcement learning method tailored to solve large-scale urban FLP, capable of producing near-optimal solutions at superfast inference speed. We distill the essential swap operation from local search, and simulate it by intelligently selecting edges on a graph of urban regions, guided by a knowledge-informed graph neural network, thus sidestepping the need for heavy computation of local search. Extensive experiments on four US cities with different geospatial conditions demonstrate that our approach can achieve comparable performance to commercial solvers with less than 5\% accessibility loss, while displaying up to 1000 times speedup. We deploy our model as an online geospatial application at https://huggingface.co/spaces/randommmm/MFLP.
- Erling D Andersen and Knud D Andersen. 2000. The MOSEK interior point optimizer for linear programming: an implementation of the homogeneous algorithm. In High performance optimization. Springer, 197–232.
- Zvi Drezner and Horst W Hamacher. 2004. Facility location: applications and theory. Springer Science & Business Media.
- Evaluation of heuristics for the p-median problem: Scale and spatial demand distribution. Computers, environment and urban systems 88 (2021), 101656.
- Oded Kariv and S Louis Hakimi. 1979. An algorithmic approach to network location problems. I: The p-centers. SIAM journal on applied mathematics 37, 3 (1979), 513–538.
- FE Maranzana. 1964. On the location of supply points to minimize transport costs. Journal of the Operational Research Society 15, 3 (1964), 261–270.
- Mauricio GC Resende and Renato F Werneck. 2007. A fast swap-based local search procedure for location problems. Annals of Operations Research 150 (2007), 205–230.
- An efficient tabu search procedure for the p-median problem. European Journal of Operational Research 96, 2 (1997), 329–342.
- Approximation algorithms for facility location problems. In Proceedings of the twenty-ninth annual ACM symposium on Theory of computing. 265–274.
- Rumor Mitigation in Social Media Platforms with Deep Reinforcement Learning. In Companion Proceedings of the ACM on Web Conference 2024. 814–817.
- Pointer networks. Advances in neural information processing systems 28 (2015).
- Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case. In The Eleventh International Conference on Learning Representations.
- Deconstructing laws of accessibility and facility distribution in cities. Science advances 6, 37 (2020), eabb4112.
- Spatial planning of urban communities via deep reinforcement learning. Nature Computational Science 3, 9 (2023), 748–762.
- Road Planning for Slums via Deep Reinforcement Learning. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’23). Association for Computing Machinery, New York, NY, USA, 5695–5706. https://doi.org/10.1145/3580305.3599901
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.