2022各顶会NAS论文（不全）

CVPR 2022

1.Shapley-NAS: Discovering Operation Contribution for Neural Architecture SearchShapley-NAS：发现对神经架构搜索的操作贡献

2.GreedyNASv2: Greedier Search with a Greedy Path FilterGreedyNASv2：使用贪心路径过滤器的贪心搜索

3.BaLeNAS: Differentiable Architecture Search via Bayesian Learning RuleBaLeNAS：通过贝叶斯学习规则进行可微架构搜索

4.ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image PriorISNAS-DIP：用于深度图像先验的图像特定神经架构搜索

5.Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?从实用的角度揭开神经切线内核的神秘面纱：无需训练就可以信任神经架构搜索吗？

6.SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted SystemsSplitNets：为头戴式系统上的高效分布式计算设计神经架构

7.Neural Architecture Search with Representation Mutual Information具有表示互信息的神经架构搜索

8.Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot LearningMAML 的全局收敛和受理论启发的神经架构搜索以进行 Few-Shot 学习

9.Learning to Learn by Jointly Optimizing Neural Architecture and Weights通过联合优化神经架构和权重来学习学习

10.Shapley-NAS: Discovering Operation Contribution for Neural Architecture SearchShapley-NAS：发现对神经架构搜索的操作贡献

11.Distribution Consistent Neural Architecture Search分布一致的神经架构搜索

12.BaLeNAS: Differentiable Architecture Search via Bayesian Learning RuleBaLeNAS：通过贝叶斯学习规则进行可微架构搜索

13.Training-free Transformer Architecture Search免培训变压器架构搜索

14.ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image PriorISNAS-DIP：用于深度图像先验的图像特定神经架构搜索

15.Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search改进神经架构搜索的性能感知互知识蒸馏

16.Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture SearchArch-Graph：用于任务可转移神经架构搜索的非循环架构关系预测器

17.β-DARTS: Beta-Decay Regularization for Differentiable Architecture Searchβ-DARTS：可微架构搜索的 Beta-Decay 正则化

18.Searching the Deployable Convolution Neural Networks for GPUs

19.Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

20.DATA: Domain-Aware and Task-Aware Self-supervised Learning

AAAI 2022

1.DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy

2.BM-NAS: Bilevel Multimodal Neural Architecture Search

3.Learning from Mistakes - A Framework for Neural Architecture Search

4.Learning Network Architecture for Open-Set Recognition

ICLR2022

1.NASPY: Automated Extraction of Automated Machine Learning Models

2.NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

3.NASI: Label- and Data-agnostic Neural Architecture Search at Initialization

4.Generalizing Few-Shot NAS with Gradient Matching

5.Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks

6.Learning Versatile Neural Architectures by Propagating Network Codes

7.On Redundancy and Diversity in Cell-based Neural Architecture Search

8.NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training

9.GradSign: Model Performance Inference with Theoretical Insights

10.SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search

ICML2022

1.AGNAS: Attention-Guided Unifying Micro- and Macro-Architecture Search

2.ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks

3.MAE-DET: Revisiting Maximal Entropy Principle in Zero-Shot NAS for Efficient Object Detection

4.Deep and Flexible Graph Neural Architecture Search

5.Large-Scale Graph Neural Architecture Search

6.Graph Neural Architecture Search Under Distribution Shifts

7.Analyzing and Mitigating Interference in Neural Architecture Search

8.AutoSNN: Towards Energy-Efficient Spiking Neural Networks

IJCAI2022

1.Graph Masked Autoencoder Enhanced Predictor for Neural Architecture Search

2.Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization

标签：Search,架构,Neural,NAS,搜索,Architecture,2022,各顶会
来源： https://www.cnblogs.com/Zhengsh123/p/16452551.html