Dynamic Weighted Graph Fusion for Deep Multi-View Clustering

Authors: Yazhou Ren, Jingyu Pu, Chenhang Cui, Yan Zheng, Xinyue Chen, Xiaorong Pu, Lifang He

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results demonstrate the efficacy of DFMVC. ... Experiments. ... Clustering Results Comparison with Baselines. ... Ablation Studies. ... Table 2: Results of all methods on three original datasets.
Researcher Affiliation Academia 1School of Computer Science and Engineering,University of Electronic Science and Technology of China 2Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China 3Department of Computer Science and Engineering, Lehigh University, Bethlehem, USA
Pseudocode Yes Algorithm 1 Dynamic weighted graph fusion for deep multi-view clustering (DFMVC)
Open Source Code No The paper does not explicitly state that its source code is open-source or provide a link to a code repository.
Open Datasets Yes Datasets The following three real-world multi-view datasets are tested in our experiments. BDGP [Cai et al., 2012] contains 2500 samples of 5 different types of drosophila embryos. ... Fashion-MV [Xiao et al., 2017] collects images from 10 categories, i.e., t-shirt, trouser, pullover, dress, coat, sandal, shirt, sneaker, bag, and ankle boot. ... Handwritten Numerals (HW) encompasses 2000 samples distributed across 10 classes, each representing numerals ranging from 0 to 9.
Dataset Splits No The paper does not specify distinct training, validation, and test splits with percentages or counts. It mentions
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments (e.g., GPU models, CPU types).
Software Dependencies No The paper mentions general software components like "fully connected (Fc) autoencoder structure" but does not specify any software libraries or dependencies with version numbers.
Experiment Setup Yes For our method, the trade-off coefficient τ is set at 0.5, while the k NN graph algorithm employs a value of 30 for the number of neighbors (k). It is worth noting that our approach necessitates constructing a graph encompassing all nodes, with the batch size equal to the total number of instances (N). ... all autoencoders undergo 3000 epochs.