PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs. (arXiv:2203.10304v2 [cs.LG] UPDATED)

Optimization of directed acyclic graph (DAG) structures has many
applications, such as neural architecture search (NAS) and probabilistic
graphical model learning. Encoding DAGs into real vectors is a dominant
component in most neural-network-based DAG optimization frameworks. Currently,
most DAG encoders use an asynchronous message passing scheme which sequentially
processes nodes according to the dependency between nodes in a DAG. That is, a
node must not be processed until all its predecessors are processed. As a
result, they are inherently not …

arxiv computation encoder graphs