Chaotic graph backpropagation adds a chaotic loss to GNN training and improves solution quality for large-scale combinatorial optimization problems.
Erdos goes ne ural: an unsupervised learning framework for combinatorial optimization on graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Brain-inspired Chaotic Graph Backpropagation for Large-scale Combinatorial Optimization
Chaotic graph backpropagation adds a chaotic loss to GNN training and improves solution quality for large-scale combinatorial optimization problems.