SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models

• URL: http://arxiv.org/abs/2502.20422v1
• Date: Thu, 27 Feb 2025 09:17:49 GMT
• Title: SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models
• Authors: Zicheng Cai, Yaohua Tang, Yutao Lai, Hua Wang, Zhi Chen, Hao Chen,
• Abstract summary: We introduce SEKI, a novel large language model (LLM)-based neural architecture search (NAS) method.<n>Inspired by the chain-of-thought (CoT) paradigm in modern LLMs, SEKI operates in two key stages: self-evolution and knowledge distillation.
• Score: 11.670056503731905
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce SEKI, a novel large language model (LLM)-based neural architecture search (NAS) method. Inspired by the chain-of-thought (CoT) paradigm in modern LLMs, SEKI operates in two key stages: self-evolution and knowledge distillation. In the self-evolution stage, LLMs initially lack sufficient reference examples, so we implement an iterative refinement mechanism that enhances architectures based on performance feedback. Over time, this process accumulates a repository of high-performance architectures. In the knowledge distillation stage, LLMs analyze common patterns among these architectures to generate new, optimized designs. Combining these two stages, SEKI greatly leverages the capacity of LLMs on NAS and without requiring any domain-specific data. Experimental results show that SEKI achieves state-of-the-art (SOTA) performance across various datasets and search spaces while requiring only 0.05 GPU-days, outperforming existing methods in both efficiency and accuracy. Furthermore, SEKI demonstrates strong generalization capabilities, achieving SOTA-competitive results across multiple tasks.

Related papers

• LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection [0.0]
  In machine learning, Neural Architecture Search (NAS) requires domain knowledge of model design and a large amount of trial-and-error to achieve promising performance. The Large Language Model (LLM)-Guided Evolution (GE) framework transformed this approach by incorporating LLMs to directly modify model source code for image classification algorithms on CIFAR data. We show that LLM-GE produced variants with significant performance improvements, such as an increase in Mean Average Precision from 92.5% to 94.5%.
  arXiv  Detail & Related papers  (2025-04-03T05:06:06Z)
• Instructing the Architecture Search for Spatial-temporal Sequence Forecasting with LLM [18.649295352998546]
  We propose a novel NAS method for STSF based on large language models (LLMs) Our method can achieve competitive effectiveness with superior efficiency against existing NAS methods for STSF.
  arXiv  Detail & Related papers  (2025-03-23T08:59:04Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models. Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start. Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities. We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• LLM Inference Unveiled: Survey and Roofline Model Insights [62.92811060490876]
  Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems.
  arXiv  Detail & Related papers  (2024-02-26T07:33:05Z)
• EvoPrompting: Language Models for Code-Level Neural Architecture Search [21.759268833999627]
  We explore the use of language models (LMs) as adaptive mutation and crossover operators for an evolutionary neural architecture search algorithm. We find that the combination of evolutionary prompt engineering with soft prompt-tuning, a method we term EvoPrompting, consistently finds diverse and high performing models.
  arXiv  Detail & Related papers  (2023-02-28T18:37:25Z)
• Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation [11.866947846619064]
  neural architecture search (NAS) has emerged as a promising avenue toward automating the design of architectures. We propose a surrogate-assisted multi-objective method to address the challenges of applying NAS to semantic segmentation. Our method can identify architectures significantly outperforming existing state-of-the-art architectures designed both manually by human experts and automatically by other NAS methods.
  arXiv  Detail & Related papers  (2022-08-14T10:18:51Z)
• Incremental Learning with Differentiable Architecture and Forgetting Search [3.6868861317674524]
  We show that leveraging NAS for incremental learning results in strong performance gains for classification tasks. We evaluate our method on both RF signal and image classification tasks, and demonstrate we can achieve up to a 10% performance increase over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-19T21:47:26Z)
• AutoBERT-Zero: Evolving BERT Backbone from Scratch [94.89102524181986]
  We propose an Operation-Priority Neural Architecture Search (OP-NAS) algorithm to automatically search for promising hybrid backbone architectures. We optimize both the search algorithm and evaluation of candidate models to boost the efficiency of our proposed OP-NAS. Experiments show that the searched architecture (named AutoBERT-Zero) significantly outperforms BERT and its variants of different model capacities in various downstream tasks.
  arXiv  Detail & Related papers  (2021-07-15T16:46:01Z)
• Stage-Wise Neural Architecture Search [65.03109178056937]
  Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications. These networks consist of stages, which are sets of layers that operate on representations in the same resolution. It has been demonstrated that increasing the number of layers in each stage improves the prediction ability of the network. However, the resulting architecture becomes computationally expensive in terms of floating point operations, memory requirements and inference time.
  arXiv  Detail & Related papers  (2020-04-23T14:16:39Z)

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.