SoF: Soft-Cluster Matrix Factorization for Probabilistic Clustering
Authors: Han Zhao, Pascal Poupart, Yongfeng Zhang, Martin Lysy
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on both synthetic and real-world datasets show that So F significantly outperforms previous NMF-based algorithms and that it is able to detect non-convex patterns as well as cluster boundaries. |
| Researcher Affiliation | Academia | David R. Cheriton School of Computer Science, University of Waterloo, Canada Department of Computer Science and Technology, Tsinghua University, China Department of Statistics and Actuarial Science, University of Waterloo, Canada |
| Pseudocode | Yes | Algorithm 1 Sequential Minimization to Unconstrained Problem |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the described methodology. |
| Open Datasets | Yes | We use 7 real-world data sets from the UCI Machine Learning Repository5. The statistics of the datasets are summarized in Table 2. More detailed information about these data sets can be found at the UCI Machine Learning Repository. archive.ics.uci.edu/ml/datasets.html |
| Dataset Splits | No | The paper mentions running algorithms multiple times and evaluating on datasets, but it does not specify train/validation/test splits, percentages, or cross-validation setup for the datasets. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU/CPU models or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions various algorithms and optimization methods but does not provide specific version numbers for any software libraries or dependencies used for implementation. |
| Experiment Setup | Yes | Input: I = {v1, . . . , v N}, distance function L, # of clusters K, scale factor c > 0, initial penalty parameters λ(0) 1 , λ(0) 2 > 0, step-factor µ > 1, initial learning rate 0 < γ(0) < 1, threshold 0 < ϵ1, ϵ2 1. |