Arch-LLM: Taming LLMs for Neural Architecture Generation via Unsupervised Discrete Representation Learning

• URL: http://arxiv.org/abs/2503.22063v1
• Date: Fri, 28 Mar 2025 00:56:56 GMT
• Title: Arch-LLM: Taming LLMs for Neural Architecture Generation via Unsupervised Discrete Representation Learning
• Authors: Deshani Geethika Poddenige, Sachith Seneviratne, Damith Senanayake, Mahesan Niranjan, PN Suganthan, Saman Halgamuge,
• Abstract summary: A common approach involves the use of Variational Autoencoders (VAEs) to map discrete architectures onto a continuous representation space.<n>We introduce a Vector Quantized Variational Autoencoder (VQ-VAE) to learn a discrete latent space more naturally aligned with the discrete neural architectures.<n>Compared to VAE-based methods, our approach improves the generation of valid and unique architectures by over 80% on NASBench-101 and over 8% on NASBench-201.
• Score: 2.981775461282335
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised representation learning has been widely explored across various modalities, including neural architectures, where it plays a key role in downstream applications like Neural Architecture Search (NAS). These methods typically learn an unsupervised representation space before generating/ sampling architectures for the downstream search. A common approach involves the use of Variational Autoencoders (VAEs) to map discrete architectures onto a continuous representation space, however, sampling from these spaces often leads to a high percentage of invalid or duplicate neural architectures. This could be due to the unnatural mapping of inherently discrete architectural space onto a continuous space, which emphasizes the need for a robust discrete representation of these architectures. To address this, we introduce a Vector Quantized Variational Autoencoder (VQ-VAE) to learn a discrete latent space more naturally aligned with the discrete neural architectures. In contrast to VAEs, VQ-VAEs (i) map each architecture into a discrete code sequence and (ii) allow the prior to be learned by any generative model rather than assuming a normal distribution. We then represent these architecture latent codes as numerical sequences and train a text-to-text model leveraging a Large Language Model to learn and generate sequences representing architectures. We experiment our method with Inception/ ResNet-like cell-based search spaces, namely NAS-Bench-101 and NAS-Bench-201. Compared to VAE-based methods, our approach improves the generation of valid and unique architectures by over 80% on NASBench-101 and over 8% on NASBench-201. Finally, we demonstrate the applicability of our method in NAS employing a sequence-modeling-based NAS algorithm.

Related papers

• Architecture-Aware Minimization (A$^2$M): How to Find Flat Minima in Neural Architecture Search [3.724847012963521]
  We investigate the geometric properties of neural architecture spaces commonly used in differentiable NAS methods.<n>Building on these insights, we propose Architecture-Aware Minimization (A$2$M), a novel analytically derived algorithmic framework.<n>A$2$M consistently improves generalization over state-of-the-art DARTS-based algorithms on benchmark datasets.
  arXiv  Detail & Related papers  (2025-03-13T14:30:17Z)
• DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions [121.05720140641189]
  We develop a family of models with the distilling neural architecture (DNA) techniques. Our proposed DNA models can rate all architecture candidates, as opposed to previous works that can only access a sub- search space using algorithms. Our models achieve state-of-the-art top-1 accuracy of 78.9% and 83.6% on ImageNet for a mobile convolutional network and a small vision transformer, respectively.
  arXiv  Detail & Related papers  (2024-03-02T22:16:47Z)
• Efficacy of Neural Prediction-Based Zero-Shot NAS [0.04096453902709291]
  We propose a novel approach for zero-shot Neural Architecture Search (NAS) using deep learning. Our method employs Fourier sum of sines encoding for convolutional kernels, enabling the construction of a computational feed-forward graph with a structure similar to the architecture under evaluation. Experimental results show that our approach surpasses previous methods using graph convolutional networks in terms of correlation on the NAS-Bench-201 dataset and exhibits a higher convergence rate.
  arXiv  Detail & Related papers  (2023-08-31T14:54:06Z)
• A General-Purpose Transferable Predictor for Neural Architecture Search [22.883809911265445]
  We propose a general-purpose neural predictor for Neural Architecture Search (NAS) that can transfer across search spaces. Experimental results on NAS-Bench-101, 201 and 301 demonstrate the efficacy of our scheme.
  arXiv  Detail & Related papers  (2023-02-21T17:28:05Z)
• NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks [76.8112416450677]
  Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL) NASiam is a novel approach that uses for the first time differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) NASiam reaches competitive performance in both small-scale (i.e., CIFAR-10/CIFAR-100) and large-scale (i.e., ImageNet) image classification datasets while costing only a few GPU hours.
  arXiv  Detail & Related papers  (2023-01-31T19:48:37Z)
• BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule [95.56873042777316]
  Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost. This paper formulates the neural architecture search as a distribution learning problem through relaxing the architecture weights into Gaussian distributions. We demonstrate how the differentiable NAS benefits from Bayesian principles, enhancing exploration and improving stability.
  arXiv  Detail & Related papers  (2021-11-25T18:13:42Z)
• Smooth Variational Graph Embeddings for Efficient Neural Architecture Search [41.62970837629573]
  We propose a two-sided variational graph autoencoder, which allows to smoothly encode and accurately reconstruct neural architectures from various search spaces. We evaluate the proposed approach on neural architectures defined by the ENAS approach, the NAS-Bench-101 and the NAS-Bench-201 search spaces.
  arXiv  Detail & Related papers  (2020-10-09T17:05:41Z)
• DC-NAS: Divide-and-Conquer Neural Architecture Search [108.57785531758076]
  We present a divide-and-conquer (DC) approach to effectively and efficiently search deep neural architectures. We achieve a $75.1%$ top-1 accuracy on the ImageNet dataset, which is higher than that of state-of-the-art methods using the same search space.
  arXiv  Detail & Related papers  (2020-05-29T09:02:16Z)
• A Semi-Supervised Assessor of Neural Architectures [157.76189339451565]
  We employ an auto-encoder to discover meaningful representations of neural architectures. A graph convolutional neural network is introduced to predict the performance of architectures.
  arXiv  Detail & Related papers  (2020-05-14T09:02:33Z)
• Learning Architectures from an Extended Search Space for Language Modeling [37.79977691127229]
  We present a general approach to learn both intra-cell and inter-cell architectures of Neural architecture search (NAS) For recurrent neural language modeling, it outperforms a strong baseline significantly on the PTB and WikiText data, with a new state-of-the-art on PTB. The learned architectures show good transferability to other systems.
  arXiv  Detail & Related papers  (2020-05-06T05:02:33Z)
• DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning [135.27931587381596]
  We propose an efficient and unified NAS framework termed DDPNAS via dynamic distribution pruning. In particular, we first sample architectures from a joint categorical distribution. Then the search space is dynamically pruned and its distribution is updated every few epochs. With the proposed efficient network generation method, we directly obtain the optimal neural architectures on given constraints.
  arXiv  Detail & Related papers  (2019-05-28T06:35:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.