Conventional Federated Domain Adaptation (FDA) approaches usually demand an
abundance of assumptions, such as label set consistency, which makes them
significantly less feasible for real-world situations and introduces security
hazards. In this work, we propose 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. This relaxes the assumptions made by FDA, which are often
challenging to meet in real-world cases and diminish model security. To address
the UFDA scenario, we propose a corresponding framework called Hot-Learning
with Contrastive Label Disambiguation (HCLD), which tackles UFDA's domain
shifts and category gaps problem 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. The extensive experiments on three
benchmarks demonstrate that our HCLD achieves comparable performance for our
UFDA scenario with much fewer assumptions, compared to the previous
methodologies with many additional assumptions.

我们提出了一种更实用的方案，名为 Hot-Learning with Contrastive Label Disambiguation（HCLD），解决了 Universal Federated Domain Adaptation（UFDA）场景中的领域变化和类别差距问题，并通过使用各个源域的黑盒模型的单热输出来区分共享类和未知类。在三个基准测试上的广泛实验表明，与具有许多额外假设的先前方法相比，我们的 HCLD 在 UFDA 场景中以更少的假设达到了可比较的性能。