Discriminative Bayesian Nonparametric Clustering
Authors: Vu Nguyen, Dinh Phung, Trung Le, Hung Bui
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments in image clustering and dynamic location clustering demonstrate that by encouraging discrimination between induced clusters, our model enhances the quality of clustering in comparison with the traditional generative BNP models. |
| Researcher Affiliation | Collaboration | Deakin University, Australia Adobe Research, USA |
| Pseudocode | No | The paper describes sampling steps for the Gibbs sampler but does not present them in a structured pseudocode or algorithm block format. |
| Open Source Code | No | The paper does not provide any statement or link regarding the public availability of its source code. |
| Open Datasets | Yes | We evaluate DDPM on image clustering using NUS Wide (K=13, N=3411, D=500), Fifteen Scenes (K=15, N=2245, D=128) and MNIST (K=10, N=1000, D=784) datasets... We evaluate the proposed discriminative-state i HMM using sequential data on location dynamic discovery from the MDC dataset [Laurila et al., 2012]. |
| Dataset Splits | No | The paper mentions various datasets (NUS Wide, Fifteen Scenes, MNIST, MDC) and compares clustering performance to ground truth, but does not explicitly provide details about specific train, validation, or test dataset splits, percentages, or sample counts. |
| Hardware Specification | Yes | All experiments are running in the same Windows machine Core i7, 16GB of RAM. |
| Software Dependencies | No | The paper states that the implementation is in Matlab, but does not provide specific version numbers for Matlab or any other software libraries. |
| Experiment Setup | Yes | Throughout the experiments, the prior distribution for ηk is set as p(ηk | µ0,Σ0) N (0,I). We use symmetric Dirichlet with parameter 0.01. We set the hyperparameters as α,γ Gamma(1,1), then we resample them in each iteration (for robustness) following the approaches presented in [Escobar and West, 1995; Teh et al., 2006]. To have a good initialization for each discriminative models, in the first 10 iterations of the collapsed Gibbs sampler, we run our proposed models without using discriminative property. |