【文件属性】:
文件名称:Label Embedding with Partial Heterogeneous Contexts.pdf
文件大小:2.94MB
文件格式:PDF
更新时间:2022-09-16 07:29:30
数学之 人工智 机器学
Label embedding plays an important role in many real-world
applications. To enhance the label relatedness captured by
the embeddings, multiple contexts can be adopted. However,
these contexts are heterogeneous and often partially observed
in practical tasks, imposing significant challenges to capture
the overall relatedness among labels. In this paper, we propose
a general Partial Heterogeneous Context Label Embedding
(PHCLE) framework to address these challenges. Categorizing
heterogeneous contexts into two groups, relational
context and descriptive context, we design tailor-made matrix
factorization formula to effectively exploit the label relatedness
in each context. With a shared embedding principle
across heterogeneous contexts, the label relatedness is selectively
aligned in a shared space. Due to our elegant formulation,
PHCLE overcomes the partial context problem and can
nicely incorporate more contexts, which both cannot be tackled
with existing multi-context label embedding methods. An
effective alternative optimization algorithm is further derived
to solve the sparse matrix factorization problem. Experimental
results demonstrate that the label embeddings obtained
with PHCLE achieve superb performance in image classification
task and exhibit good interpretability in the downstream
label similarity analysis and image understanding task.