AI Summary: Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search

This paper studies the problem of finding graphs that maximize the number of edges, while avoiding short cycles. It formulates graph generation as a reinforcement learning task, and compares methods like AlphaZero and tabu search. A key finding is that using a curriculum - building larger graphs from good smaller graphs - significantly improves performance. The work makes progress on an open problem in extremal graph theory.

Klara Kaleb (@klarakaleb) / X

Petar Veličković - CatalyzeX

Adam Zsolt Wagner

Petar Veličković - CatalyzeX

AI Summary: Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search

AI high: The island of Anguilla is riding the AI wave

Petar Veličković posted on LinkedIn

Nearly 100 Mila-affiliated scientific papers accepted at NeurIPS 2023 - Mila

Adam Zsolt Wagner

Petar Veličković on LinkedIn: Building Google Maps' Algorithm & AI Research at Google Deepmind - The…

TransformerCVAE/data/arxiv/artificial intelligence_10047_15000_15_title.txt at master · fangleai/TransformerCVAE · GitHub

A new hyper-heuristic based on ant lion optimizer and Tabu search algorithm for replica management in cloud environment

A memetic algorithm for finding multiple subgraphs that optimally cover an input network