Deep Embedding Clustering Driven by Sample Stability
Authors: Zhanwen Cheng, Feijiang Li, Jieting Wang, Yuhua Qian
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental results on five datasets illustrate that the proposed method achieves superior performance compared to state-of-art clustering approaches. |
| Researcher Affiliation | Academia | Institute of Big Data Science and Industry, Shanxi University, Taiyuan 030006, China. |
| Pseudocode | Yes | Algorithm 1 Algorithm of DECS |
| Open Source Code | Yes | Our source code is publicly available at: https://github.com/ChengZhanwen/DECS. |
| Open Datasets | Yes | In order to validate the performance and generality of the proposed method, we perform experiments on five image datasets, as shown in Table 2. Dataset samples Classes Dimensions MNIST-full 70,000 10 1x28x28 MNIST-test 10,000 10 1x28x28 USPS 9,298 10 1x16x16 Fashion-Mnist 70,000 10 1x28x28 YTF 12,183 41 3x55x55 |
| Dataset Splits | No | Considering that clustering tasks are fully unsupervised, the training and test split are merged in all our experiments. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU/CPU models, memory, or cloud instances used for running experiments. |
| Software Dependencies | No | The paper mentions 'Adam optimizer with default parameters in Keras' but does not specify version numbers for Keras or any other software dependencies. |
| Experiment Setup | Yes | For all datasets, we specify that the encoder to consists of four convolutional layers with channel sizes of 32, 64, 128, and 256, respectively. Each convolutional kernel has a size of 3x3 and uses a stride of 2. Furthermore, batch normalization and max pooling layers are added after each convolutional layer. The decoder uses a network that mirrors the encoder s structure. Additionally, Re LU is utilized as the activation function for all convolutional layers in the model. During the training process, data augmentation techniques such as random rotation, translation, and cropping are applied to improve the neural network s generalization ability. In addition, the autoencoder is trained end-to-end for 500 epochs using the Adam optimizer with default parameters in Keras. Then, the encoder is further trained for 10000 iterations with a batch size of 256. The coefficient λ for variance is set to 0.8 during the calculation of sample stability. |