Deep Clustering with a Constraint for Topological Invariance based on Symmetric InfoNCE
This addresses a limitation in deep clustering for scenarios with limited prior knowledge, though it appears incremental as it builds on existing methods.
The paper tackles the problem of deep clustering methods performing poorly on datasets with complex topological structures by proposing a constraint based on symmetric InfoNCE to improve training efficiency for both simple and complex topologies. The method MIST, which incorporates this constraint, outperforms other state-of-the-art methods on most of ten benchmark datasets.
We consider the scenario of deep clustering, in which the available prior knowledge is limited. In this scenario, few existing state-of-the-art deep clustering methods can perform well for both non-complex topology and complex topology datasets. To address the problem, we propose a constraint utilizing symmetric InfoNCE, which helps an objective of deep clustering method in the scenario train the model so as to be efficient for not only non-complex topology but also complex topology datasets. Additionally, we provide several theoretical explanations of the reason why the constraint can enhances performance of deep clustering methods. To confirm the effectiveness of the proposed constraint, we introduce a deep clustering method named MIST, which is a combination of an existing deep clustering method and our constraint. Our numerical experiments via MIST demonstrate that the constraint is effective. In addition, MIST outperforms other state-of-the-art deep clustering methods for most of the commonly used ten benchmark datasets.