Neural Topological Ordering for Computation Graphs. (arXiv:2207.05899v2 [cs.LG] UPDATED)

Recent works on machine learning for combinatorial optimization have shown
that learning based approaches can outperform heuristic methods in terms of
speed and performance. In this paper, we consider the problem of finding an
optimal topological order on a directed acyclic graph with focus on the memory
minimization problem which arises in compilers. We propose an end-to-end
machine learning based approach for topological ordering using an
encoder-decoder framework. Our encoder is a novel attention based graph neural
network architecture called …

arxiv computation graphs