paper-with-me

홈 › Papers

A Study on Encodings for Neural Architecture Search

2020-07-09 · NeurIPS 2020 12 · Colin White, Willie Neiswanger, Sam Nolen, Yash Savani

Neural architecture search (NAS) has been extensively studied in the past few years. A popular approach is to represent each neural architecture in the search space as a directed acyclic graph (DAG), and then search over all DAGs by encoding the adjacency matrix and list of operations as a set of hyperparameters. Recent work has demonstrated that even small changes to the way each architecture is encoded can have a significant effect on the performance of NAS algorithms. In this work, we present the first formal study on the effect of architecture encodings for NAS, including a theoretical grounding and an empirical study. First we formally define architecture encodings and give a theoretical characterization on the scalability of the encodings we study Then we identify the main encoding-dependent subroutines which NAS algorithms employ, running experiments to show which encodings work best with each subroutine for many popular algorithms. The experiments act as an ablation study for prior work, disentangling the algorithmic and encoding-based contributions, as well as a guideline for future work. Our results demonstrate that NAS encodings are an important design decision which can have a significant impact on overall performance. Our code is available at https://github.com/naszilla/nas-encodings.

📄 PDF Abstract BibTeX arXiv:2007.04965

Code (2)

naszilla/nas-encodings 공식 구현 tf
naszilla/naszilla tf

Tasks

Neural Architecture Search

Similar Papers 제목 키워드 기반

Encodings for Prediction-based Neural Architecture Search

2024-03-04 · Yash Akhauri, Mohamed S. Abdelfattah

Predictor-based methods have substantially enhanced Neural Architecture Search (NAS) optimization. The efficacy of these predictors is largely influenced by the method of encoding neural network architectures. While trad…

Neural Architecture SearchPredictionTransfer Learning

CATE: Computation-aware Neural Architecture Encoding with Transformers

2021-02-14 · Shen Yan, Kaiqiang Song, Fei Liu, Mi Zhang

Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structure or computation information of the neu…

AutoMLNeural Architecture SearchRepresentation LearningUnsupervised Pre-training

Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search

2026-05-15 · Pranav Somu, Advay Balakrishnan, Stepan Kravtsov, Aaron McDaniel 외 arxiv

Developing effective surrogates (performance predictors) for Neural Architecture Search (NAS) typically requires expensive fine-tuning or the engineering of complex representations. We propose a low-cost embedding strate…

Neural Architecture Search

Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity

2026-06-16 · Viet-Hoang Tran, Vinh Khanh Bui, Van-Hoan Trinh, Tan Lai Ngoc 외 arxiv

Neural network parameter spaces are inherently non-injective, as distinct parameter configurations can realize identical functions through functional equivalence. While this symmetry is well understood in classical fully…

Encoding Selection for Solving Hamiltonian Cycle Problems with ASP

2019-09-18 · Liu Liu, Miroslaw Truszczynski

It is common for search and optimization problems to have alternative equivalent encodings in ASP. Typically none of them is uniformly better than others when evaluated on broad classes of problem instances. We claim tha…