# A Semi-Supervised Assessor of Neural Architectures

arXiv: https://arxiv.org/abs/2005.06821 · HTML: https://mlsanity.com/paper/2005.06821/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2020.

## Built on by (most cited first, 28 of 28)

- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Manifold Regularized Dynamic Network Pruning](https://mlsanity.com/paper/2103.05861/) (2021)
- [Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets](https://mlsanity.com/paper/2107.00860/) (2021)
- [Prioritized Architecture Sampling with Monto-Carlo Tree Search](https://mlsanity.com/paper/2103.11922/) (2021)
- [Stronger NAS with Weaker Predictors](https://mlsanity.com/paper/2102.10490/) (2021)
- [CATE: Computation-aware Neural Architecture Encoding with Transformers](https://mlsanity.com/paper/2102.07108/) (2021)
- [Augmented Shortcuts for Vision Transformers](https://mlsanity.com/paper/2106.15941/) (2021)
- [Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?](https://mlsanity.com/paper/2203.14577/) (2022)
- [HAO: Hardware-aware neural Architecture Optimization for Efficient Inference](https://mlsanity.com/paper/2104.12766/) (2021)
- [Homogeneous Architecture Augmentation for Neural Predictor](https://mlsanity.com/paper/2107.13153/) (2021)
- [A Survey on Computationally Efficient Neural Architecture Search](https://mlsanity.com/paper/2206.01520/) (2022)
- [Calibrating a Deep Neural Network with Its Predecessors](https://mlsanity.com/paper/2302.06245/) (2023)
- [Task-Adaptive Neural Network Search with Meta-Contrastive Learning](https://mlsanity.com/paper/2103.01495/) (2021)
- [Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search](https://mlsanity.com/paper/2104.05309/) (2021)
- [GENNAPE: Towards Generalized Neural Architecture Performance Estimators](https://mlsanity.com/paper/2211.17226/) (2022)
- [Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation](https://mlsanity.com/paper/2412.15554/) (2024)
- [RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection](https://mlsanity.com/paper/2503.22733/) (2025)
- [Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"](https://mlsanity.com/paper/2302.00932/) (2023)
- [DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning](https://mlsanity.com/paper/2302.13020/) (2023)
- [CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks](https://mlsanity.com/paper/2211.05950/) (2022)
- [Differentiable Search of Accurate and Robust Architectures](https://mlsanity.com/paper/2212.14049/) (2022)
- [How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor](https://mlsanity.com/paper/2311.18451/) (2023)
- [A General-Purpose Transferable Predictor for Neural Architecture Search](https://mlsanity.com/paper/2302.10835/) (2023)
- [ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures](https://mlsanity.com/paper/2510.04938/) (2025)
- [Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning](https://mlsanity.com/paper/2103.08157/) (2021)
- [WPNAS: Neural Architecture Search by jointly using Weight Sharing and Predictor](https://mlsanity.com/paper/2203.02086/) (2022)
- [Automating Neural Architecture Design without Search](https://mlsanity.com/paper/2204.11838/) (2022)
- [From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search](https://mlsanity.com/paper/2605.09290/) (2026)

## Abstract (arXiv)

Neural architecture search (NAS) aims to automatically design deep neural networks of satisfactory performance. Wherein, architecture performance predictor is critical to efficiently value an intermediate neural architecture. But for the training of this predictor, a number of neural architectures and their corresponding real performance often have to be collected. In contrast with classical performance predictor optimized in a fully supervised way, this paper suggests a semi-supervised assessor of neural architectures. We employ an auto-encoder to discover meaningful representations of neural architectures. Taking each neural architecture as an individual instance in the search space, we construct a graph to capture their intrinsic similarities, where both labeled and unlabeled architectures are involved. A graph convolutional neural network is introduced to predict the performance of architectures based on the learned representations and their relation modeled by the graph. Extensive experimental results on the NAS-Benchmark-101 dataset demonstrated that our method is able to make a significant reduction on the required fully trained architectures for finding efficient architectures.