Rank Aggregation via Heterogeneous Thurstone Preference Models
Authors: Tao Jin, Pan Xu, Quanquan Gu, Farzad Farnoud4353-4360
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the proposed HTM model and algorithm on both synthetic and real data, demonstrating that it outperforms existing methods. We conduct thorough experiments on both synthetic and real world data to validate our theoretical results and demonstrate the superiority of our proposed model and algorithm. |
| Researcher Affiliation | Academia | Tao Jin,1 Pan Xu,2 Quanquan Gu,2 Farzad Farnoud1 1University of Virginia, 2University of California, Los Angeles {taoj, farzad}@virginia.edu, {panxu, qgu}@cs.ucla.edu |
| Pseudocode | Yes | Algorithm 1 HTMs with Alternating Gradient Descent |
| Open Source Code | No | The paper does not provide any explicit statements about the availability of source code or links to repositories. |
| Open Datasets | Yes | The first one named Reading Level (Chen et al. 2013) contains English text excerpts whose reading difficulty level is compared by workers. |
| Dataset Splits | No | The paper discusses data generation and training, but does not specify details regarding train/validation/test dataset splits, percentages, or cross-validation setup for reproducibility. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies or version numbers for the tools and libraries used in the experiments. |
| Experiment Setup | Yes | input: learning rates η1, η2 > 0, initial points s(0) and γ(0) ... number of iteration T... We set number of items n = 20, number of users m = 9... We vary γA in the range of {2.5, 5, 10} and γB in the range of {0.25, 1, 2.5}... Each pair of items is sent to the user 2 times for evaluation and is observed in the training dataset with probability α (0, 1)... we only present the experimental results with α = 0.4... The experiment is repeated 100 times with different random seeds. We initialize s and γ, as s(0) = 1 and γ(0) = 1. We evaluate the performance of the methods for λ0 = 0, 1, 5, 10. |