Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Bayesian Nonparametric Multilevel Clustering with Group-Level Contexts
Authors: Tien Vu Nguyen, Dinh Phung, Xuanlong Nguyen, Swetha Venkatesh, Hung Bui
ICML 2014 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real-world datasets demonstrate the advantage of utilizing context information via our model in both text and image domains. (Abstract) |
| Researcher Affiliation | Collaboration | Vu Nguyen EMAIL Center for Pattern Recognition and Data Analytics (PRa DA), Deakin University, AustraliaDinh Phung EMAIL Center for Pattern Recognition and Data Analytics (PRa DA), Deakin University, AustraliaXuan Long Nguyen EMAIL Department of Statistics, University of Michigan, Ann Arbor, USASvetha Venkatesh EMAIL Center for Pattern Recognition and Data Analytics (PRa DA), Deakin University, AustraliaHung Hai Bui EMAIL Laboratory for Natural Language Understanding, Nuance Communications, Sunnyvale, USA |
| Pseudocode | No | The paper describes the generative process and inference steps (collapsed Gibbs sampling) in paragraph form, but it does not include a distinct 'Pseudocode' or 'Algorithm' block or figure. |
| Open Source Code | No | The paper does not provide a direct link to its source code or explicitly state that the code for the described methodology is publicly released. |
| Open Datasets | Yes | For NUS-WIDE we use a subset of the 13-class animals comprising of 3,411 images (2,054 images for training and 1357 images for testing) with off-the-shelf features including 500-dim bag-of-word SIFT vector and 1000-dim bag-of-tag annotation vector. downloaded from http://www.ml-thu.net/ jun/data/ |
| Dataset Splits | Yes | For NUS-WIDE... (2,054 images for training and 1357 images for testing)... We use NIPS and PNAS datasets with 90% for training and 10% for held-out perplexity evaluation. |
| Hardware Specification | No | The paper does not mention any specific hardware components (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions statistical models like 'Multinomial with Dirichlet prior' and 'Gaussian' and the 'collapsed Gibbs sampling' procedure, but it does not specify any software packages or libraries with version numbers. |
| Experiment Setup | Yes | We ran collapsed Gibbs for 500 iterations after 100 burn-in samples. (Section 4.2) |