# GOLD-NAS: Gradual, One-Level, Differentiable

arXiv: https://arxiv.org/abs/2007.03331 · HTML: https://mlsanity.com/paper/2007.03331/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2020.

## Built on by (most cited first, 15 of 15)

- [SparseBERT: Rethinking the Importance Analysis in Self-attention](https://mlsanity.com/paper/2102.12871/) (2021)
- [DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks](https://mlsanity.com/paper/2206.00843/) (2022)
- [iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization](https://mlsanity.com/paper/2108.11014/) (2021)
- [FT-MDT: Extracting Decision Trees from Medical Texts via a Novel Low-rank Adaptation Method](https://mlsanity.com/paper/2510.04655/) (2025)
- [Improving Differentiable Architecture Search via Self-Distillation](https://mlsanity.com/paper/2302.05629/) (2023)
- [Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks](https://mlsanity.com/paper/2305.14065/) (2023)
- [Single-DARTS: Towards Stable Architecture Search](https://mlsanity.com/paper/2108.08128/) (2021)
- [Differentiable Convolution Search for Point Cloud Processing](https://mlsanity.com/paper/2108.12856/) (2021)
- [μDARTS: Model Uncertainty-Aware Differentiable Architecture Search](https://mlsanity.com/paper/2107.11500/) (2021)
- [Exploring Complicated Search Spaces with Interleaving-Free Sampling](https://mlsanity.com/paper/2112.02488/) (2021)
- [Efficient Re-parameterization Operations Search for Easy-to-Deploy Network Based on Directional Evolutionary Strategy](https://mlsanity.com/paper/2204.06403/) (2022)
- [MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency](https://mlsanity.com/paper/2310.15074/) (2023)
- [The devil is in discretization discrepancy. Robustifying Differentiable NAS with Single-Stage Searching Protocol](https://mlsanity.com/paper/2405.16610/) (2024)
- [FX-DARTS: Designing Topology-unconstrained Architectures with Differentiable Architecture Search and Entropy-based Super-network Shrinking](https://mlsanity.com/paper/2504.20079/) (2025)
- [DNAD: Differentiable Neural Architecture Distillation](https://mlsanity.com/paper/2504.20080/) (2025)

## Abstract (arXiv)

There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper, we first relax these manually designed constraints and enlarge the search space to contain more than 10160 candidates. In the new space, most existing differentiable search methods can fail dramatically. We then propose a novel algorithm named Gradual One-Level Differentiable Neural Architecture Search (GOLD-NAS) which introduces a variable resource constraint to one-level optimization so that the weak operators are gradually pruned out from the super-network. In standard image classification benchmarks, GOLD-NAS can find a series of Pareto-optimal architectures within a single search procedure. Most of the discovered architectures were never studied before, yet they achieve a nice tradeoff between recognition accuracy and model complexity. We believe the new space and search algorithm can advance the search of differentiable NAS.