Hierarchical Relationship Alignment Metric Learning
This work addresses metric learning challenges in real-world applications like multi-label learning, offering an incremental improvement over prior frameworks.
The paper tackles the limitation of existing metric learning methods that rely on simple similar/dissimilar pairs by proposing HRAML, a hierarchical model that handles complex datasets and multiple learning tasks, achieving better performance than popular methods and the RAML framework in experiments.
Most existing metric learning methods focus on learning a similarity or distance measure relying on similar and dissimilar relations between sample pairs. However, pairs of samples cannot be simply identified as similar or dissimilar in many real-world applications, e.g., multi-label learning, label distribution learning. To this end, relation alignment metric learning (RAML) framework is proposed to handle the metric learning problem in those scenarios. But RAML learn a linear metric, which can't model complex datasets. Combining with deep learning and RAML framework, we propose a hierarchical relationship alignment metric leaning model HRAML, which uses the concept of relationship alignment to model metric learning problems under multiple learning tasks, and makes full use of the consistency between the sample pair relationship in the feature space and the sample pair relationship in the label space. Further we organize several experiment divided by learning tasks, and verified the better performance of HRAML against many popular methods and RAML framework.