We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This is achieved by adding extra networks and losses that help regularize the features extracted by the backbone encoder network. To this end we propose the novel use of the recently proposed unpaired image-toimage translation framework to constrain the features extracted by the encoder network. Specifically, we require that the features extracted are able to reconstruct the images in both domains. In addition we require that the distribution of features extracted from images in the two domains are indistinguishable. Many recent works can be seen as specific cases of our general framework. We apply our method for domain adaptation between MNIST, USPS, and SVHN datasets, and Amazon, Webcam and DSLR Office datasets in classification tasks, and also between GTA5 and Cityscapes datasets for a segmentation task. We demonstrate state of the art performance on each of these datasets.

哪些目标标签对于图形神经网络（GNN）培训最有效？在某些应用GNNS Excel样药物设计或欺诈检测的应用中，标记新实例很昂贵。我们开发一个具有数据效率的主动采样框架，即ScatterSample，以在主动学习设置下训练GNN。 ScatterSample采用称为不同确定性的抽样模块，从样品空间的不同区域收集具有较大不确定性的实例以进行标记。为了确保所选节点的多样化，不同的确定性簇群簇较高的不确定性节点，​​并从每个群集中选择代表性节点。严格的理论分析表明，与标准的主动采样方法相比，我们的ScatterSample算法进一步支持了其优势，该方法旨在简单地简单地提高不确定性，而不是使样品多样化。特别是，我们表明ScatterSample能够在整个样品空间上有效地减少模型不确定性。我们在五个数据集上的实验表明，散点样本明显优于其他GNN主动学习基线，特别是它将采样成本降低了50％，同时达到了相同的测试准确性。