# NASGEM: Neural Architecture Search via Graph Embedding Method

arXiv: https://arxiv.org/abs/2007.04452 · HTML: https://mlsanity.com/paper/2007.04452/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks](https://mlsanity.com/paper/2102.10423/) (2021)
- [FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?](https://mlsanity.com/paper/2205.11656/) (2022)
- [FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer](https://mlsanity.com/paper/2403.12821/) (2024)
- [CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework](https://mlsanity.com/paper/2212.03965/) (2022)
- [Series of quasi-uniform scatterings with fast search, root systems and neural network classifications](https://mlsanity.com/paper/2512.04865/) (2025)
- [GraphIR: Architecture-Level Search States for LLM-Guided Neural Architecture Evolution](https://mlsanity.com/paper/2608.01633/) (2026)
- [Evolutionary Neural Architecture Search with Dual Contrastive Learning](https://mlsanity.com/paper/2512.20112/) (2025)
- [Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning](https://mlsanity.com/paper/2103.08157/) (2021)
- [CSCO: Connectivity Search of Convolutional Operators](https://mlsanity.com/paper/2404.17152/) (2024)

## Abstract (arXiv)

Neural Architecture Search (NAS) automates and prospers the design of neural networks. Estimator-based NAS has been proposed recently to model the relationship between architectures and their performance to enable scalable and flexible search. However, existing estimator-based methods encode the architecture into a latent space without considering graph similarity. Ignoring graph similarity in node-based search space may induce a large inconsistency between similar graphs and their distance in the continuous encoding space, leading to inaccurate encoding representation and/or reduced representation capacity that can yield sub-optimal search results. To preserve graph correlation information in encoding, we propose NASGEM which stands for Neural Architecture Search via Graph Embedding Method. NASGEM is driven by a novel graph embedding method equipped with similarity measures to capture the graph topology information. By precisely estimating the graph distance and using an auxiliary Weisfeiler-Lehman kernel to guide the encoding, NASGEM can utilize additional structural information to get more accurate graph representation to improve the search efficiency. GEMNet, a set of networks discovered by NASGEM, consistently outperforms networks crafted by existing search methods in classification tasks, i.e., with 0.4%-3.6% higher accuracy while having 11%- 21% fewer Multiply-Accumulates. We further transfer GEMNet for COCO object detection. In both one-stage and twostage detectors, our GEMNet surpasses its manually-crafted and automatically-searched counterparts.