Conventional Federated Domain Adaptation (FDA) approaches usually demand an abundance of assumptions, which makes them significantly less feasible for real-world situations and introduces security hazards. This paper relaxes the assumptions from previous FDAs and studies a more practical scenario named Universal Federated Domain Adaptation (UFDA). It only requires the black-box model and the label set information of each source domain, while the label sets of different source domains could be inconsistent, and the target-domain label set is totally blind. Towards a more effective solution for our newly proposed UFDA scenario, we propose a corresponding methodology called Hot-Learning with Contrastive Label Disambiguation (HCLD). It particularly tackles UFDA's domain shifts and category gaps problems by using one-hot outputs from the black-box models of various source domains. Moreover, to better distinguish the shared and unknown classes, we further present a cluster-level strategy named Mutual-Voting Decision (MVD) to extract robust consensus knowledge across peer classes from both source and target domains. Extensive experiments on three benchmark datasets demonstrate that our method achieves comparable performance for our UFDA scenario with much fewer assumptions, compared to previous methodologies with comprehensive additional assumptions.

翻译：传统的联邦域适应方法通常需要大量假设，这使得它们在现实场景中的可行性显著降低，并带来安全隐患。本文放宽了先前联邦域适应的假设条件，研究了一种更实用的场景——通用联邦域适应。该方法仅需各源域的黑盒模型和标签集信息，允许不同源域的标签集不一致，且目标域标签集完全未知。针对新提出的UFDA场景，我们提出了一种名为"对比标签消歧热学习"的方法。该方法通过利用各源域黑盒模型的独热输出，专门解决UFDA中的域偏移和类别缺口问题。此外，为更好地区分共享类与未知类，我们进一步提出名为"互投票决策"的聚类策略，从源域和目标域中提取跨同类别的鲁棒共识知识。在三个基准数据集上的大量实验表明，与需要大量额外假设的先前方法相比，我们的方法在假设条件大幅减少的情况下，在UFDA场景中取得了可比的性能。