Graph is all you need? Lightweight data-agnostic neural architecture search without training
Neural architecture search (NAS) enables the automatic design of neural network models. However, training the candidates generated by the search algorithm for performance evaluation incurs considerable computational overhead. Our method, dubbed nasgraph, remarkably reduces the computational costs by converting neural architectures to graphs and using the average degree, a graph measure, as the proxy in lieu of the evaluation metric. Our training-free NAS method is data-agnostic and light-weight. It can find the best architecture among 200 randomly sampled architectures from NAS-Bench201 in 217 CPU seconds. Besides, our method is able to achieve competitive performance on various datasets including NASBench-101, NASBench-201, and NDS search spaces. We also demonstrate that nasgraph generalizes to more challenging tasks on Micro TransNAS-Bench-101.
Code (0)
등록된 구현이 없습니다.
Tasks
AllCPUNeural Architecture SearchSimilar Papers 제목 키워드 기반
Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of real-world graphs in domains like recommender systems, fraud detectio…
Neural Architecture SearchFraud DetectionA Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR
Large-scale multilingual ASR (mASR) models such as Whisper achieve strong performance but incur high computational and latency costs, limiting their deployment on resource-constrained edge devices. In this study, we prop…
Domain AdaptationTowards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
Graph Neural Architecture Search (GNAS) has achieved superior performance on various graph-structured tasks. However, existing GNAS studies overlook the applications of GNAS in resource-constraint scenarios. This paper p…
Graph Neural NetworkNetwork PruningNeural Architecture SearchNode ClassificationGraph Attention Networks for Detecting Epilepsy from EEG Signals Using Accessible Hardware in Low-Resource Settings
Goal: Epilepsy remains under-diagnosed in low-income countries due to scarce neurologists and costly diagnostic tools. We propose a graph-based deep learning framework to detect epilepsy from low-cost Electroencephalogra…
TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs
Token-level code completion is one of the most critical features in modern Integrated Development Environments (IDEs). It assists developers by suggesting relevant identifiers and APIs during coding. While completions ar…
Prompt EngineeringCode Completion