Sample Efficient Decentralized Stochastic Frank-Wolfe Methods for Continuous DR-Submodular Maximization

Authors: Hongchang Gao, Hanzi Xu, Slobodan Vucetic

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results confirm the effectiveness of the proposed methods.In addition to the theoretical considerations, we perform extensive experimental evaluation to confirm the effectiveness of our proposed methods.
Researcher Affiliation Academia Hongchang Gao , Hanzi Xu and Slobodan Vucetic Department of Computer and Information Sciences, Temple University, PA, USA {hongchang.gao, tun47067, vucetic}@temple.edu
Pseudocode Yes Algorithm 1 De SVRFW-gp
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes Here, we use two datasets: Movie Lens-1M and Movie Lens-100K 3. 3https://grouplens.org/datasets/movielens/
Dataset Splits No The paper mentions distributing data across workers ('For each case, the ratings from users are divided into all workers evenly.') but does not provide specific train/validation/test dataset splits, percentages, or methodology for partitioning the data for model training and evaluation.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library names with version numbers, needed to replicate the experiment.
Experiment Setup Yes In our experiment, we use 8 workers for Movie Lens-1M and 4 workers for Movie Lens-100K. For each case, the ratings from users are divided into all workers evenly. As for the communication graph, we use the Erdos-Renyi random graph in our experiment. The mean vertex degree in the graph is 2. For the non-diagonal entries in the weight matrix W of the communication graph, if vertex i and vertex j are connected, wij = 1/(1 + max(Di, Dj)) where Di denotes the degree of the vertex i. If there is no edge between vertex i and vertex j, wij equals to 0. For the diagonal entries, wii = 1 P j N (i) wij. ... for our methods, we use the batch size of 100 for Movie Lens-100K and 200 for Movie Lens-1M.