Deep Fusion Clustering Network
Authors: Wenxuan Tu, Sihang Zhou, Xinwang Liu, Xifeng Guo, Zhiping Cai, En Zhu, Jieren Cheng9978-9987
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on six benchmark datasets have demonstrated that the proposed DFCN consistently outperforms the state-of-the-art deep clustering methods. Our code is publicly available at https://github.com/Wx Tu/DFCN. ... Experiments Benchmark Datasets We evaluate the proposed DFCN on six popular public datasets, including three graph datasets (ACM, DBLP, and CITE) and three non-graph datasets (USPS, HHAR, and REUT). |
| Researcher Affiliation | Academia | Wenxuan Tu,1,* Sihang Zhou,2, Xinwang Liu,1, Xifeng Guo,1 Zhiping Cai,1, En Zhu,1 Jieren Cheng3,4 1College of Computer, National University of Defense Technology, Changsha, China 2College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China 3College of Computer Science and Cyberspace Security, Hainan University, Haikou, China 4Hainan Blockchain Technology Engineering Research Center, Haikou, China {wenxuantu, guoxifeng1990, cjr22}@163.com, sihangjoe@gmail.com, {xinwangliu, zpcai, enzhu}@nudt.edu.cn |
| Pseudocode | Yes | Algorithm 1 Deep Fusion Clustering Network |
| Open Source Code | Yes | Our code is publicly available at https://github.com/Wx Tu/DFCN. |
| Open Datasets | Yes | We evaluate the proposed DFCN on six popular public datasets, including three graph datasets (ACM1, DBLP2, and CITE3) and three non-graph datasets (USPS (Le Cun et al. 1990), HHAR (Lewis et al. 2004), and REUT (Stisen et al. 2015)). For the dataset (like USPS, HHAR, and REUT) whose affinity matrix is absent, we follow (Bo et al. 2020) and construct the matrix with heat kernel method. ... 1http://dl.acm.org/ 2https://dblp.uni-trier.de 3http://citeseerx.ist.psu.edu/index |
| Dataset Splits | Yes | The optimization stops when the validation loss comes to a plateau. |
| Hardware Specification | Yes | Our method is implemented with Py Torch platform and a NVIDIA 2080TI GPU. |
| Software Dependencies | No | The paper states 'Our method is implemented with Py Torch platform' but does not specify a version number for PyTorch or any other software libraries used. |
| Experiment Setup | Yes | The training of the proposed DFCN includes three steps. First, we pre-train the AE and IGAE independently for 30 iterations by minimizing the reconstruction loss functions. Then, both subnetworks are integrated into a united framework for another 100 iterations. Finally, with the learned centers of different clusters and under the guidance of the triplet self-supervised strategy, we train the whole network for at least 200 iterations until convergence. ... The learning rate is set to 1e-3 for USPS, HHAR, 1e-4 for REUT, DBLP, and CITE, and 5e-5 for ACM. The training batch size is set to 256 and we adopt an early stop strategy to avoid over-fitting. According to the results of parameter sensitivity testing, we fix two balanced hyper-parameters γ and λ to 0.1 and 10, respectively. Moreover, we set the nearest neighbors number of each node as 5 for all non-graph datasets. |