Transformed K-means Clustering
This work addresses clustering challenges in document analysis, representing an incremental advancement by combining existing techniques.
The authors tackled the problem of document clustering by embedding the K-means clustering loss into a transform learning framework and solving it jointly with ADMM, resulting in improvements over state-of-the-art methods.
In this work we propose a clustering framework based on the paradigm of transform learning. In simple terms the representation from transform learning is used for K-means clustering; however, the problem is not solved in such a naïve piecemeal fashion. The K-means clustering loss is embedded into the transform learning framework and the joint problem is solved using the alternating direction method of multipliers. Results on document clustering show that our proposed approach improves over the state-of-the-art.