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.

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

Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search

Petar Veličković - CatalyzeX

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

Adam Zsolt Wagner

Adam Zsolt Wagner

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

Tabu Search — AI Search Algorithms for Smart Mobility

graphml - Telegram channel posts - Graph Machine Learning - Telemetrio

Petar Veličković on LinkedIn: #icml2023

Evolutionary binary feature selection using adaptive ebola optimization search algorithm for high-dimensional datasets

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