Stochastic Blockmodeling for Online Advertising
Authors: Li Chen, Matthew Patton
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the effectiveness of our proposed algorithms on simulation and the AOL website dataset. Experiments Clustering Validation For simulation, we measure clustering performance using the adjusted rand index (ARI) (Hubert and Arabie 1985). For real data experiment, one challenge for clustering validation is the lack of ground truth. |
| Researcher Affiliation | Collaboration | Li Chen Department of Applied Mathematics and Statistics Johns Hopkins University Baltimore, MD 21210 lichen.jhu1@gmail.com Matthew Patton AOL Advertising.com 1020 Hull St Baltimore, MD 21230 matthew.patton@teamaol.com |
| Pseudocode | Yes | Algorithm 1 The BIC-based Vertex Clustering Approach Input: An input square matrix M of order n, an integer K 1, and an embedding dimension D. Step 1 : Compute the first D orthonormal eigenpairs of M, denoted by (UM, SM) Rn D RD. Step 2: Define the D-dimensional embedding of M to be ˆ M := UMS1/2 M . Step 3: for k in 1 : K do Fit Gaussian mixture models with different covariance types and k clusters to ˆ M, and compute the BIC. end for Step 4: Cluster the vertices using the optimal model selected via the maximum BIC. |
| Open Source Code | No | The paper mentions "See https://sites.google.com/site/lichenjhuresearch/home for details." which is a personal website and does not explicitly state that the source code for the methodology is provided there, nor is it a specific code repository. |
| Open Datasets | No | The paper mentions the "AOL website dataset" but does not provide concrete access information (link, DOI, repository, or citation) for public availability. |
| Dataset Splits | No | The paper describes the AOL dataset used as "of size 1569 x 1569" but does not provide specific training, validation, or test dataset splits needed to reproduce the experiment. |
| Hardware Specification | No | No specific hardware details (like GPU/CPU models, processor types, or memory) used for running experiments are mentioned in the paper. |
| Software Dependencies | No | No specific ancillary software details (like library or solver names with version numbers) are mentioned in the paper. |
| Experiment Setup | No | The paper describes the general algorithm steps but does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size) or detailed training configurations. |