FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
This work addresses the need for efficient neural architecture evaluation, which is crucial for researchers and practitioners in machine learning, though it is incremental as it builds on graph-based encoding methods.
The paper tackles the problem of estimating neural architecture performance without full training by introducing FlowerFormer, a graph transformer that incorporates information flows, achieving superior results over existing encoding methods across computer vision, graph neural networks, and speech recognition models.
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 enhanced representation learning of neural architectures, we introduce FlowerFormer, a powerful graph transformer that incorporates the information flows within a neural architecture. FlowerFormer consists of two key components: (a) bidirectional asynchronous message passing, inspired by the flows; (b) global attention built on flow-based masking. Our extensive experiments demonstrate the superiority of FlowerFormer over existing neural encoding methods, and its effectiveness extends beyond computer vision models to include graph neural networks and auto speech recognition models. Our code is available at http://github.com/y0ngjaenius/CVPR2024_FLOWERFormer.