论文标题
连接足够的域适应条件：源指导的不确定性，放松的分歧和差异定位
Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization
论文作者
论文摘要
域适应性的最新进展表明，要求对源域的风险低，并且相等的特征边缘降低了适应性的性能。同时，经验证据表明，纳入无监督的目标域项，该项将决策边界从高密度区域推开，以及放松的对齐，从而改善了适应性。在本文中，我们从理论上通过对目标风险的新结合来证明这种观察是合理的，并且我们将两个放松的概念连接起来，即差异$β-$放松的分歧和定位。这种连接使我们能够将源域的分类结构纳入所考虑的差异的放松中，从而尤其是更好地处理标签移位案例。
Recent advances in domain adaptation establish that requiring a low risk on the source domain and equal feature marginals degrade the adaptation's performance. At the same time, empirical evidence shows that incorporating an unsupervised target domain term that pushes decision boundaries away from the high-density regions, along with relaxed alignment, improves adaptation. In this paper, we theoretically justify such observations via a new bound on the target risk, and we connect two notions of relaxation for divergence, namely $β-$relaxed divergences and localization. This connection allows us to incorporate the source domain's categorical structure into the relaxation of the considered divergence, provably resulting in a better handling of the label shift case in particular.
