Attn-JGNN: Attention Enhanced Join-Graph Neural Networks
This addresses the #SAT problem for computational logic and AI, but appears incremental as it builds on existing methods like IJGP and neural networks.
The paper tackled the problem of solving #SAT (model counting) by proposing Attn-JGNN, an attention-enhanced join-graph neural network, which improved solving accuracy compared to other neural network methods.
We propose an Attention Enhanced Join-Graph Neural Networks(Attn-JGNN) model for solving #SAT problems, which significantly improves the solving accuracy. Inspired by the Iterative Join Graph Propagation (IJGP) algorithm, Attn-JGNN uses tree decomposition to encode the CNF formula into a join-graph, then performs iterative message passing on the join-graph, and finally approximates the model number by learning partition functions. In order to further improve the accuracy of the solution, we apply the attention mechanism in and between clusters of the join-graphs, which makes Attn-JGNN pay more attention to the key variables and clusters in probabilistic inference, and reduces the redundant calculation. Finally, our experiments show that our Attn-JGNN model achieves better results than other neural network methods.