In this paper, we propose a novel domain generalization (DG) framework based
on a new upper bound to the risk on the unseen domain. Particularly, our
framework proposes to jointly minimize both the covariate-shift as well as the
concept-shift between the seen domains for a better performance on the unseen
domain. While the proposed approach can be implemented via an arbitrary
combination of covariate-alignment and concept-alignment modules, in this work
we use well-established approaches for distributional alignment namely, Maximum
Mean Discrepancy (MMD) and covariance Alignment (CORAL), and use an Invariant
Risk Minimization (IRM)-based approach for concept alignment. Our numerical
results show that the proposed methods perform as well as or better than the
state-of-the-art for domain generalization on several data sets.

本文提出了一种新颖的领域泛化（DG）框架，该框架基于一种新的风险上限，旨在联合最小化在已见域之间的协变量转移和概念转移，以在未见域上获得更好的性能。在本文中，我们使用了分布对齐的常用方法，即最大均值差异（MMD）和协方差对齐（CORAL），并使用基于不变风险最小化（IRM）的方法来进行概念对齐。我们的数值结果表明，所提出的方法在多个数据集上表现不输于领域泛化的最新技术。

联合协变量对齐和概念对齐：一种领域泛化框架

Joint covariate-alignment and concept-alignment: a framework for domain generalization

Building subject-independent deep learning models for EEG decoding faces the
challenge of strong covariate-shift across different datasets, subjects and
recording sessions. Our approach to address this difficulty is to explicitly
align feature distributions at various layers of the deep learning model, using
both simple statistical techniques as well as trainable methods with more
representational capacity. This follows in a similar vein as covariance-based
alignment methods, often used in a Riemannian manifold context. The methodology
proposed herein won first place in the 2021 Benchmarks in EEG Transfer Learning
(BEETL) competition, hosted at the NeurIPS conference. The first task of the
competition consisted of sleep stage classification, which required the
transfer of models trained on younger subjects to perform inference on multiple
subjects of older age groups without personalized calibration data, requiring
subject-independent models. The second task required to transfer models trained
on the subjects of one or more source motor imagery datasets to perform
inference on two target datasets, providing a small set of personalized
calibration data for multiple test subjects.

采用统计技术和可训练方法明确地对齐深度学习模型各层的特征分布，以应对跨数据集、受试者和记录会话的强协变量转移，从而构建针对 EEG 解码的主体无关的深度学习模型，该方法在 2021 年的 BEETL 比赛中获得了第一名。

NeurIPS 2021：团队 Cogitat 所提供的 EEG 迁移学习竞赛基准测试数据集

Team Cogitat at NeurIPS 2021: Benchmarks for EEG Transfer Learning Competition

We present new minimax results that concisely capture the relative benefits
of source and target labeled data, under covariate-shift. Namely, we show that
the benefits of target labels are controlled by a transfer-exponent $\gamma$
that encodes how singular Q is locally w.r.t. P, and interestingly allows
situations where transfer did not seem possible under previous insights. In
fact, our new minimax analysis - in terms of $\gamma$ - reveals a continuum of
regimes ranging from situations where target labels have little benefit, to
regimes where target labels dramatically improve classification. We then show
that a recently proposed semi-supervised procedure can be extended to adapt to
unknown $\gamma$, and therefore requests labels only when beneficial, while
achieving minimax transfer rates.

我们提出了新的极小极大结果，用于简洁地捕捉协变量偏移下源标记数据和目标标记数据之间的相对收益。我们展示了目标标记的收益由一个传输指数 $\gamma$ 控制，这个指数编码了 Q 在局部相对于 P 的奇异性，并且允许了在之前的研究中似乎不可能进行的情况。实际上，我们的新的极小极大分析显示了一个连续的区域，从目标标记几乎没有收益的情况到目标标记显著提高分类的情况。然后，我们展示了最近提出的半监督程序可以扩展到适应未知的 $\gamma$，因此只在有效时才请求标签，同时实现最小极大传输速率。