Neural Architecture Search (NAS) has become a popular method for discovering
effective model architectures, especially for target hardware. As such, NAS
methods that find optimal architectures under constraints are essential. In our
paper, we propose LayerNAS to address the challenge of multi-objective NAS by
transforming it into a combinatorial optimization problem, which effectively
constrains the search complexity to be polynomial.
For a model architecture with $L$ layers, we perform layerwise-search for
each layer, selecting from a set of search options $\mathbb{S}$. LayerNAS
groups model candidates based on one objective, such as model size or latency,
and searches for the optimal model based on another objective, thereby
splitting the cost and reward elements of the search. This approach limits the
search complexity to $ O(H \cdot |\mathbb{S}| \cdot L) $, where $H$ is a
constant set in LayerNAS.
Our experiments show that LayerNAS is able to consistently discover superior
models across a variety of search spaces in comparison to strong baselines,
including search spaces derived from NATS-Bench, MobileNetV2 and MobileNetV3.

LayerNAS 是一种利用组合优化来解决多目标神经网络架构搜索的方法，能够在多种搜索空间中发现优秀的模型候选项。

LayerNAS：多项式复杂度下的神经架构搜索

LayerNAS: Neural Architecture Search in Polynomial Complexity

We present SSS3D, a fast multi-objective NAS framework designed to find
computationally efficient 3D semantic scene segmentation networks. It uses
RandLA-Net, an off-the-shelf point-based network, as a super-network to enable
weight sharing and reduce search time by 99.67% for single-stage searches.
SSS3D has a complex search space composed of sampling and architectural
parameters that can form 2.88 * 10^17 possible networks. To further reduce
search time, SSS3D splits the complete search space and introduces a two-stage
search that finds optimal subnetworks in 54% of the time required by
single-stage searches.

SSS3D 是一个快速多目标的 NAS 框架，使用 RandLA-Net 作为超网络，通过权重共用和两阶段搜索，有效地降低了搜索时间，用于寻找计算效率高的 3D 语义场景分割网络。