FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer

arXiv:2403.12821v1 Announce Type: new
Abstract: The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no one-size-fits-all solution. Thus, considerable efforts have been made to quickly and accurately estimate the performances of neural architectures, without full training or evaluation, for given tasks and datasets. Neural architecture encoding has played a crucial role in the estimation, and graphbased methods, which treat an architecture as a graph, have shown prominent performance. For …

architecture arxiv cs.ai cs.lg encoding flow graph transformer type