paper-with-me

Papers

IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance

2023-12-19 · Hongyi He, Longjun Liu, Haonan Zhang, Nanning Zheng

Among existing Neural Architecture Search methods, DARTS is known for its efficiency and simplicity. This approach applies continuous relaxation of network representation to construct a weight-sharing supernet and enables the identification of excellent subnets in just a few GPU days. However, performance collapse in DARTS results in deteriorating architectures filled with parameter-free operations and remains a great challenge to the robustness. To resolve this problem, we reveal that the fundamental reason is the biased estimation of the candidate importance in the search space through theoretical and experimental analysis, and more precisely select operations via information-based measurements. Furthermore, we demonstrate that the excessive concern over the supernet and inefficient utilization of data in bi-level optimization also account for suboptimal results. We adopt a more realistic objective focusing on the performance of subnets and simplify it with the help of the information-based measurements. Finally, we explain theoretically why progressively shrinking the width of the supernet is necessary and reduce the approximation error of optimal weights in DARTS. Our proposed method, named IS-DARTS, comprehensively improves DARTS and resolves the aforementioned problems. Extensive experiments on NAS-Bench-201 and DARTS-based search space demonstrate the effectiveness of IS-DARTS.

📄 PDF Abstract BibTeX arXiv:2312.12648

Code (1)

hy-he/is-darts 공식 구현 pytorch

Tasks

GPUNeural Architecture Search

Methods 이 논문이 사용한 방법론

DARTS Differentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with…

Similar Papers 제목 키워드 기반

Stabilizing Differentiable Architecture Search via Perturbation-based Regularization

2020-02-12 · ICML 2020 1 · Xiangning Chen, Cho-Jui Hsieh

Differentiable architecture search (DARTS) is a prevailing NAS solution to identify architectures. Based on the continuous relaxation of the architecture space, DARTS learns a differentiable architecture weight and large…

Adversarial AttackNeural Architecture Search

Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters

2019-10-25 · Kaifeng Bi, Changping Hu, Lingxi Xie, Xin Chen 외

DARTS is a popular algorithm for neural architecture search (NAS). Despite its great advantage in search efficiency, DARTS often suffers weak stability, which reflects in the large variation among individual trials as we…

Neural Architecture Search

Relax DARTS: Relaxing the Constraints of Differentiable Architecture Search for Eye Movement Recognition

2024-09-18 · Hongyu Zhu, Xin Jin, Hongchao Liao, Yan Xiang 외

Eye movement biometrics is a secure and innovative identification method. Deep learning methods have shown good performance, but their network architecture relies on manual design and combined priori knowledge. To addres…

emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition

2024-03-21 · Thejan Rajapakshe, Rajib Rana, Sara Khalifa, Berrak Sisman 외

Speech Emotion Recognition (SER) is crucial for enabling computers to understand the emotions conveyed in human communication. With recent advancements in Deep Learning (DL), the performance of SER models has significant…

Emotion RecognitionNeural Architecture SearchSpeech Emotion Recognition

DARTS for Inverse Problems: a Study on Stability

2021-10-19 · NeurIPS Workshop Deep_Invers 2021 12 · Jonas Geiping, Jovita Lukasik, Margret Keuper, Michael Moeller

Differentiable architecture search (DARTS) is a widely researched tool for neural architecture search, due to its promising results for image classification. The main benefit of DARTS is the effectiveness achieved throug…

image-classificationImage ClassificationNeural Architecture Search