Clustering-aware Graph Construction: A Joint Learning Perspective
This work addresses a bottleneck in graph-based clustering for data analysis applications, offering an incremental improvement over existing methods.
The paper tackles the problem of graph-based clustering methods suffering from suboptimal accuracy due to separate graph construction and clustering steps, by proposing a joint learning framework that simultaneously learns the graph and clustering results, achieving improved performance as demonstrated by comparisons with 19 state-of-the-art methods on 10 datasets using 4 metrics.
Graph-based clustering methods have demonstrated the effectiveness in various applications. Generally, existing graph-based clustering methods first construct a graph to represent the input data and then partition it to generate the clustering result. However, such a stepwise manner may make the constructed graph not fit the requirements for the subsequent decomposition, leading to compromised clustering accuracy. To this end, we propose a joint learning framework, which is able to learn the graph and the clustering result simultaneously, such that the resulting graph is tailored to the clustering task. The proposed model is formulated as a well-defined nonnegative and off-diagonal constrained optimization problem, which is further efficiently solved with convergence theoretically guaranteed. The advantage of the proposed model is demonstrated by comparing with 19 state-of-the-art clustering methods on 10 datasets with 4 clustering metrics.