Balancing Relevance and Diversity in Online Bipartite Matching via Submodularity

Authors: John P. Dickerson, Karthik Abinav Sankararaman, Aravind Srinivasan, Pan Xu1877-1884

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also run experiments on real-world and synthetic datasets to validate our algorithms.
Researcher Affiliation Academia John P. Dickerson, Karthik Abinav Sankararaman, Aravind Srinivasan, Pan Xu {john, kabinav, srin, panxu}@cs.umd.edu University of Maryland, College Park, MD, USA
Pseudocode Yes Algorithm 1 A CR-based algorithm (CR-ALG)... Algorithm 2 An MMP-based online algorithm (MMP-ALG)
Open Source Code Yes Full code can be found at https://bitbucket.org/karthikabinav/ submodularmatching/src/master/
Open Datasets Yes We use the Movie Lens dataset (Harper and Konstan 2016) for our purposes10.
Dataset Splits No The paper mentions preprocessing steps like using collaborative filtering to complete a matrix of ratings, but it does not explicitly provide details about training, validation, or test dataset splits for its own experiments.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper provides a link to the code, but it does not explicitly list specific software components with version numbers in the text to describe ancillary software dependencies for reproducibility.
Experiment Setup Yes First, we compare our algorithms against the baselines by varying two parameters B and η. B represents the number of times we can match a movie to an user and η represents the number of movies matched to any user on arrival (in the theory B = 1, η = 1, but we experiment with different values)... For every user we choose a random arrival probability (ensuring that the sum of arrival probabilities equals 1).