This paper proposes Meta-SAGE, a novel approach for improving the scalability
of deep reinforcement learning models for combinatorial optimization (CO)
tasks. Our method adapts pre-trained models to larger-scale problems in test
time by suggesting two components: a scale meta-learner (SML) and scheduled
adaptation with guided exploration (SAGE). First, SML transforms the context
embedding for subsequent adaptation of SAGE based on scale information. Then,
SAGE adjusts the model parameters dedicated to the context embedding for a
specific instance. SAGE introduces locality bias, which encourages selecting
nearby locations to determine the next location. The locality bias gradually
decays as the model is adapted to the target instance. Results show that
Meta-SAGE outperforms previous adaptation methods and significantly improves
scalability in representative CO tasks. Our source code is available at
this https URL

本文提出了 Meta-SAGE，一种用于改善组合优化（CO）任务中深度强化学习模型的可伸缩性的新方法。 我们的方法通过建议两个组件：一个比例元学习器（SML）和指导探索的计划适应性（SAGE），将预训练模型适应到测试时间中的更大规模的问题，结果表明 Meta-SAGE 优于以前的适应方法，并且显着提高了具有代表性的 CO 任务的可伸缩性。

Meta-SAGE: 尺度元学习调度适应与引导勘探在组合优化中缓解尺度漂移

Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided  Exploration for Mitigating Scale Shift on Combinatorial Optimization

Vision transformers have shown great potential in various computer vision
tasks owing to their strong capability to model long-range dependency using the
self-attention mechanism. Nevertheless, they treat an image as a 1D sequence of
visual tokens, lacking an intrinsic inductive bias (IB) in modeling local
visual structures and dealing with scale variance, which is instead learned
implicitly from large-scale training data with longer training schedules. In
this paper, we propose a Vision Transformer Advanced by Exploring intrinsic IB
from convolutions, i.e., ViTAE. Technically, ViTAE has several spatial pyramid
reduction modules to downsample and embed the input image into tokens with rich
multi-scale context using multiple convolutions with different dilation rates.
In this way, it acquires an intrinsic scale invariance IB and can learn robust
feature representation for objects at various scales. Moreover, in each
transformer layer, ViTAE has a convolution block parallel to the multi-head
self-attention module, whose features are fused and fed into the feed-forward
network. Consequently, it has the intrinsic locality IB and is able to learn
local features and global dependencies collaboratively. The proposed two kinds
of cells are stacked in both isotropic and multi-stage manners to formulate two
families of ViTAE models, i.e., the vanilla ViTAE and ViTAEv2. Experiments on
the ImageNet dataset as well as downstream tasks on the MS COCO, ADE20K, and
AP10K datasets validate the superiority of our models over the baseline
transformer models and concurrent works. Besides, we scale up our ViTAE model
to 644M parameters and obtain the state-of-the-art classification performance,
i.e., 88.5% Top-1 classification accuracy on ImageNet validation set and the
best 91.2% Top-1 accuracy on ImageNet real validation set, without using extra
private data.

本文提出了一种利用先验卷积 IB（intrinsic bias）的 Vision transformer 架构（ViTAE）来解决长程依赖建模中存在的局限性，并在 ImageNet 及其他数据集上进行了实验证明其在图像分类任务上的优越性。