Technology Category
Machine Learning: Deep Neural Architectures and Foundation ModelsSearch and Optimization: Metareasoning and MetaheuristicsComputer Vision: Generative Adversarial Networks (GANs) for Vision
Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation
🤖 AI Summary
Existing meta-neural architecture search (Meta-NAS) approaches suffer from poor generalization, restricted search spaces, and high computational overhead. To address these limitations, we propose GraB-NAS—a novel Meta-NAS framework that pioneers Bayesian optimization-guided graph generation. It models neural architectures as graphs and jointly leverages global Bayesian optimization and local latent-space gradient exploration, thereby eliminating reliance on predefined search spaces and enabling efficient, task-aware architecture discovery. GraB-NAS integrates graph neural networks, variational autoencoders, and meta-learning to support rapid cross-task adaptation. Extensive experiments on multiple benchmarks demonstrate that GraB-NAS significantly outperforms state-of-the-art Meta-NAS methods in both search efficiency and final model performance. Its superior generalization capability and practical effectiveness are empirically validated across diverse tasks and datasets.
Technology Category
Application Category
📝 Abstract
Neural Architecture Search (NAS) automates the design of high-performing neural networks but typically targets a single predefined task, thereby restricting its real-world applicability. To address this, Meta Neural Architecture Search (Meta-NAS) has emerged as a promising paradigm that leverages prior knowledge across tasks to enable rapid adaptation to new ones. Nevertheless, existing Meta-NAS methods often struggle with poor generalization, limited search spaces, or high computational costs. In this paper, we propose a novel Meta-NAS framework, GraB-NAS. Specifically, GraB-NAS first models neural architectures as graphs, and then a hybrid search strategy is developed to find and generate new graphs that lead to promising neural architectures. The search strategy combines global architecture search via Bayesian Optimization in the search space with local exploration for novel neural networks via gradient ascent in the latent space. Such a hybrid search strategy allows GraB-NAS to discover task-aware architectures with strong performance, even beyond the predefined search space. Extensive experiments demonstrate that GraB-NAS outperforms state-of-the-art Meta-NAS baselines, achieving better generalization and search effectiveness.
Problem
Research questions and friction points this paper is trying to address.
Enhance Meta-NAS generalization across diverse tasks
Expand limited search spaces in neural architecture design
Reduce high computational costs in architecture search
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hybrid search strategy combining Bayesian Optimization and gradient ascent
Models neural architectures as graphs for flexible generation
Enables task-aware architecture discovery beyond predefined search space
🔎 Similar Papers
No similar papers found.
