Abstract:
End-to-end deep clustering method utilizes deep neural networks to jointly learn representation features and clustering assignments. Although many k-means-friendly deep c...Show MoreMetadata
Abstract:
End-to-end deep clustering method utilizes deep neural networks to jointly learn representation features and clustering assignments. Although many k-means-friendly deep clustering models have been explored, the existing division-based methods tend to directly implement clustering with a specific number of clusters, which suffers from poor performance resulted from indistinguishable clusters, and contributes to bad local optimum. At the same time, the representation learning of fuzzy c-means clustering in the feature space still needs more research. In this article, a deep fuzzy curriculum clustering method with the learning strategy of clustering from easy to complex automatically is proposed to tackle the above issues. First, considering the soft flexible allocation of fuzzy c-means and the preservation of local structure of original data, the fuzzy clustering loss and the autoencoder's reconstruction loss are constructed to learn the embedded features and clustering centers simultaneously. Second, curriculum loss is introduced into the constraint to make clusters successively merge in line with implementing clustering from easy to complex, and realize the bottom-up deep aggregative clustering automatically. In addition, novel curriculum information is proposed as constraint to guide the merging of clusters belonging to the same class. Experimental results on four real-world datasets show the superiority of the proposal.
Published in: IEEE Transactions on Fuzzy Systems ( Volume: 31, Issue: 12, December 2023)
Funding Agency:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Curriculum Learning ,
- Deep Neural Network ,
- Local Structure ,
- Feature Space ,
- Clustering Method ,
- Feature Representation ,
- Specific Number ,
- Structural Conservation ,
- Cluster Centers ,
- Real-world Datasets ,
- Cluster Assignment ,
- Means Clustering ,
- Reconstruction Loss ,
- Fuzzy Clustering ,
- Merging Clusters ,
- Clustering Loss ,
- Flexible Allocation ,
- Local Structure Of Data ,
- Objective Function ,
- Clustering Algorithm ,
- MNIST Dataset ,
- Adjusted Rand Index ,
- Latent Features ,
- Deep Autoencoder ,
- Clustering Step ,
- Clustering Results ,
- Soft Clustering ,
- Clustering Performance ,
- Membership Matrix ,
- Autoencoder Network
- Author Keywords
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Curriculum Learning ,
- Deep Neural Network ,
- Local Structure ,
- Feature Space ,
- Clustering Method ,
- Feature Representation ,
- Specific Number ,
- Structural Conservation ,
- Cluster Centers ,
- Real-world Datasets ,
- Cluster Assignment ,
- Means Clustering ,
- Reconstruction Loss ,
- Fuzzy Clustering ,
- Merging Clusters ,
- Clustering Loss ,
- Flexible Allocation ,
- Local Structure Of Data ,
- Objective Function ,
- Clustering Algorithm ,
- MNIST Dataset ,
- Adjusted Rand Index ,
- Latent Features ,
- Deep Autoencoder ,
- Clustering Step ,
- Clustering Results ,
- Soft Clustering ,
- Clustering Performance ,
- Membership Matrix ,
- Autoencoder Network
- Author Keywords