Classical solver KaMIS outperforms leading AI methods for Maximum Independent Set on random graphs, with some AI approaches no better than simple greedy heuristics and a new serialization analysis revealing similar reasoning.
Can q-learning with graph networks learn a generalizable branching heuristic for a sat solver? Advances in Neural Information Processing Systems, 33:9608–9621, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set
Classical solver KaMIS outperforms leading AI methods for Maximum Independent Set on random graphs, with some AI approaches no better than simple greedy heuristics and a new serialization analysis revealing similar reasoning.