Learning A Task-Specific Deep Architecture For Clustering
This work addresses clustering tasks for machine learning practitioners by offering a more efficient and scalable approach, though it is incremental as it builds on existing sparse coding and deep learning techniques.
The paper tackles the efficiency and scalability bottlenecks of sparse coding-based clustering by proposing a deep learning architecture that emulates the sparse coding pipeline, achieving remarkable performance margins over state-of-the-art methods.
While sparse coding-based clustering methods have shown to be successful, their bottlenecks in both efficiency and scalability limit the practical usage. In recent years, deep learning has been proved to be a highly effective, efficient and scalable feature learning tool. In this paper, we propose to emulate the sparse coding-based clustering pipeline in the context of deep learning, leading to a carefully crafted deep model benefiting from both. A feed-forward network structure, named TAGnet, is constructed based on a graph-regularized sparse coding algorithm. It is then trained with task-specific loss functions from end to end. We discover that connecting deep learning to sparse coding benefits not only the model performance, but also its initialization and interpretation. Moreover, by introducing auxiliary clustering tasks to the intermediate feature hierarchy, we formulate DTAGnet and obtain a further performance boost. Extensive experiments demonstrate that the proposed model gains remarkable margins over several state-of-the-art methods.