We study a new highly-practical problem setting that enables resource-constrained edge devices to adapt a pre-trained model to their local data distributions. Recognizing that device's data are likely to come from multiple latent domains that include a mixture of unlabelled domain-relevant and domain-irrelevant examples, we focus on the comparatively under-studied problem of latent domain adaptation. Considering limitations of edge devices, we aim to only use a pre-trained model and adapt it in a feed-forward way, without using back-propagation and without access to the source data. Modelling these realistic constraints bring us to the novel and practically important problem setting of feed-forward latent domain adaptation. Our solution is to meta-learn a network capable of embedding the mixed-relevance target dataset and dynamically adapting inference for target examples using cross-attention. The resulting framework leads to consistent improvements over strong ERM baselines. We also show that our framework sometimes even improves on the upper bound of domain-supervised adaptation, where only domain-relevant instances are provided for adaptation. This suggests that human annotated domain labels may not always be optimal, and raises the possibility of doing better through automated instance selection.

翻译：我们研究了一种新的高度实用性问题设定，该方法使得资源受限的边缘设备能够将预训练模型适应于其本地数据分布。考虑到设备数据很可能来自多个潜在域，其中包含与领域相关和无关的未标注示例混合，我们聚焦于相对研究较少的潜在域适应问题。鉴于边缘设备的局限性，我们旨在仅使用预训练模型并以前馈方式对其进行适应，无需反向传播且不访问源数据。这些现实约束的建模引出了前馈式潜在域适应这一新颖且具有重要实践意义的问题设定。我们的解决方案是元学习一个网络，该网络能够嵌入混合相关性的目标数据集，并通过交叉注意力机制动态调整目标样本的推理过程。该框架相较于强经验风险最小化基线方法取得了持续改进。我们还表明，该框架有时甚至能超越领域监督适应的上界——即仅提供领域相关实例进行适应的场景。这表明人工标注的领域标签可能并非最优，并提出了通过自动化实例选择实现更优性能的可能性。