Model transparency, label correlation learning and the robust-ness to label noise are crucial for multilabel learning. However, few existing methods study these three characteristics simultaneously. To address this challenge, we propose the robust multilabel Takagi-Sugeno-Kang fuzzy system (R-MLTSK-FS) with three mechanisms. First, we design a soft label learning mechanism to reduce the effect of label noise by explicitly measuring the interactions between labels, which is also the basis of the other two mechanisms. Second, the rule-based TSK FS is used as the base model to efficiently model the inference relationship be-tween features and soft labels in a more transparent way than many existing multilabel models. Third, to further improve the performance of multilabel learning, we build a correlation enhancement learning mechanism based on the soft label space and the fuzzy feature space. Extensive experiments are conducted to demonstrate the superiority of the proposed method.
翻译:模型透明度、标签关联性学习和标签噪音的稳健性对于多标签学习至关重要,然而,现有的方法很少同时研究这三个特点。为了应对这一挑战,我们建议采用三个机制的强力多标签Takagi-Sugeno-Kang fuzzy系统(R-MLTSK-FS),首先,我们设计一个软标签学习机制,通过明确测量标签之间的相互作用来减少标签噪音的影响,这也是另外两个机制的基础。第二,基于规则的TSKFS被用作基础模型,以比许多现有的多标签模型更透明的方式有效地模拟推论关系为Tween特征和软标签。第三,为了进一步改进多标签学习的绩效,我们在软标签空间和模糊特征空间的基础上建立一个相关强化学习机制。进行了广泛的实验,以证明拟议方法的优越性。