Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNs (2405.20543v2)

Published 31 May 2024 in cs.LG, cs.AI, and cs.DM

Abstract: Graph neural networks (GNNs) have achieved great success for a variety of tasks such as node classification, graph classification, and link prediction. However, the use of GNNs (and machine learning more generally) to solve combinatorial optimization (CO) problems is much less explored. Here, we introduce GCON, a novel GNN architecture that leverages a complex filter bank and localized attention mechanisms to solve CO problems on graphs. We show how our method differentiates itself from prior GNN-based CO solvers and how it can be effectively applied to the maximum cut, minimum dominating set, and maximum clique problems in a unsupervised learning setting. GCON is competitive across all tasks and consistently outperforms other specialized GNN-based approaches, and is on par with the powerful Gurobi solver on the max-cut problem. We provide an open-source implementation of our work at https://github.com/WenkelF/copt.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Frederik Wenkel (14 papers)
  2. Semih Cantürk (7 papers)
  3. Michael Perlmutter (35 papers)
  4. Guy Wolf (79 papers)
  5. Stefan Horoi (8 papers)

Summary

We haven't generated a summary for this paper yet.