LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation

David Ireland, Giovanni Montana
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:9622-9638, 2022.

Abstract

Combinatorial Optimisation problems arise in several application domains and are often formulated in terms of graphs. Many of these problems are NP-hard, but exact solutions are not always needed. Several heuristics have been developed to provide near-optimal solutions; however, they do not typically scale well with the size of the graph. We propose a low-complexity approach for identifying a (possibly much smaller) subgraph of the original graph where the heuristics can be run in reasonable time and with a high likelihood of finding a global near-optimal solution. The core component of our approach is LeNSE, a reinforcement learning algorithm that learns how to navigate the space of possible subgraphs using an Euclidean subgraph embedding as its map. To solve CO problems, LeNSE is provided with a discriminative embedding trained using any existing heuristics using only on a small portion of the original graph. When tested on three problems (vertex cover, max-cut and influence maximisation) using real graphs with up to 10 million edges, LeNSE identifies small subgraphs yielding solutions comparable to those found by running the heuristics on the entire graph, but at a fraction of the total run time. Code for the experiments is available in the public GitHub repo at https://github.com/davidireland3/LeNSE.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-ireland22a, title = {{L}e{NSE}: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation}, author = {Ireland, David and Montana, Giovanni}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {9622--9638}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/ireland22a/ireland22a.pdf}, url = {https://proceedings.mlr.press/v162/ireland22a.html}, abstract = {Combinatorial Optimisation problems arise in several application domains and are often formulated in terms of graphs. Many of these problems are NP-hard, but exact solutions are not always needed. Several heuristics have been developed to provide near-optimal solutions; however, they do not typically scale well with the size of the graph. We propose a low-complexity approach for identifying a (possibly much smaller) subgraph of the original graph where the heuristics can be run in reasonable time and with a high likelihood of finding a global near-optimal solution. The core component of our approach is LeNSE, a reinforcement learning algorithm that learns how to navigate the space of possible subgraphs using an Euclidean subgraph embedding as its map. To solve CO problems, LeNSE is provided with a discriminative embedding trained using any existing heuristics using only on a small portion of the original graph. When tested on three problems (vertex cover, max-cut and influence maximisation) using real graphs with up to $10$ million edges, LeNSE identifies small subgraphs yielding solutions comparable to those found by running the heuristics on the entire graph, but at a fraction of the total run time. Code for the experiments is available in the public GitHub repo at https://github.com/davidireland3/LeNSE.} }
Endnote
%0 Conference Paper %T LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation %A David Ireland %A Giovanni Montana %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-ireland22a %I PMLR %P 9622--9638 %U https://proceedings.mlr.press/v162/ireland22a.html %V 162 %X Combinatorial Optimisation problems arise in several application domains and are often formulated in terms of graphs. Many of these problems are NP-hard, but exact solutions are not always needed. Several heuristics have been developed to provide near-optimal solutions; however, they do not typically scale well with the size of the graph. We propose a low-complexity approach for identifying a (possibly much smaller) subgraph of the original graph where the heuristics can be run in reasonable time and with a high likelihood of finding a global near-optimal solution. The core component of our approach is LeNSE, a reinforcement learning algorithm that learns how to navigate the space of possible subgraphs using an Euclidean subgraph embedding as its map. To solve CO problems, LeNSE is provided with a discriminative embedding trained using any existing heuristics using only on a small portion of the original graph. When tested on three problems (vertex cover, max-cut and influence maximisation) using real graphs with up to $10$ million edges, LeNSE identifies small subgraphs yielding solutions comparable to those found by running the heuristics on the entire graph, but at a fraction of the total run time. Code for the experiments is available in the public GitHub repo at https://github.com/davidireland3/LeNSE.
APA
Ireland, D. & Montana, G.. (2022). LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:9622-9638 Available from https://proceedings.mlr.press/v162/ireland22a.html.

Related Material