An Algorithm for Multi-Attribute Diverse Matching

Authors: Saba Ahmadi, Faez Ahmed, John P. Dickerson, Mark Fuge, Samir Khuller

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 7 Experimental Validation & Discussion To demonstrate the effectiveness of the proposed method, we apply it to a dataset of reviewer paper matching.
Researcher Affiliation Academia Saba Ahmadi1 , Faez Ahmed2 , John P. Dickerson1 , Mark Fuge3 and Samir Khuller4 1 Department of Computer Science, University of Maryland 2 Department of Mechanical Engineering, Northwestern University 3 Department of Mechanical Engineering, University of Maryland 4 Department of Computer Science, Northwestern University
Pseudocode Yes Algorithm 1: Find optimal diverse b-matching
Open Source Code Yes The source code is made available at https://github.com/ faezahmed/diverse matching.
Open Datasets Yes We use the multi-aspect review assignment evaluation dataset [Karimzadehgan and Zhai, 2009], a benchmark dataset from UIUC.
Dataset Splits No The paper describes the dataset and how reviewers were clustered and matched, but does not provide specific training, validation, or test dataset splits (e.g., percentages or counts).
Hardware Specification Yes Finally, we compare the timing performance of our algorithm with MIQP by changing the number of papers that need to be reviewed on a Dell XPS 13 laptop with i7 processor.
Software Dependencies No The paper mentions using 'Gurobi' for the MIQP solver but does not provide its specific version number or other software dependencies with version details.
Experiment Setup Yes For the reviewer assignment problem, where each reviewer has multiple features, we want to match each paper with reviewers who are not only from different expertise areas (clusters), but also belong to different genders. ... To set up the graph for our method, we first cluster the reviewers into 5 clusters based on their topic vectors using spectral clustering. ... We set the constraints such that each paper matches with exactly 4 reviewers, and no reviewer is allocated more than 1 paper. ... We set λ0 = λ1 = λ2 = 1 for our experiments.