Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Projection-free Decentralized Online Learning for Submodular Maximization over Time-Varying Networks
Authors: Junlong Zhu, Qingtao Wu, Mingchuan Zhang, Ruijuan Zheng, Keqin Li
JMLR 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we confirm the theoretical results via various experiments on different datasets. |
| Researcher Affiliation | Academia | Junlong Zhu EMAIL School of Information Engineering Henan University of Science and Technology Luoyang, 471023, China Qingtao Wu EMAIL School of Information Engineering Henan University of Science and Technology Luoyang, 471023, China Mingchuan Zhang (Corresponding author) EMAIL School of Information Engineering Henan University of Science and Technology Luoyang, 471023, China Ruijuan Zheng EMAIL School of Information Engineering Henan University of Science and Technology Luoyang, 471023, China Keqin Li EMAIL Department of Computer Science State University of New York New Paltz, NY 12561, USA |
| Pseudocode | Yes | Algotithm 1 Decentralized Meta Frank-Wolfe Learning over Time-Varying Networks Algotithm 2 Decentralized One-Shot Frank-Wolfe Learning over Time-Varying Networks |
| Open Source Code | No | The paper does not contain any explicit statements about providing open-source code, nor does it include links to a code repository. |
| Open Datasets | Yes | In the experiments, we use two datasets, i.e., Movie Lens and Jester. Movie Lens dataset contains 1,000,000 ratings through 6,000 users for 4,000 movies. ... Jester dataset consists of 73,421 rating though 73,421 users for 100 jokes. |
| Dataset Splits | Yes | Moreover, we split all users into disjoint sets S1, S2, . . . , ST . Each set contains Um users in Movie Lens dataset and Uj in Jester dataset. Furthermore, each agent i V has access to the data of St for all t {1, . . . , T}. Therefore, each subset is denoted by Si,t. ... In addition, we set Um = 5 in Movie Lens dataset and Uj = 5 in Jester dataset, respectively. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for the experiments. It only describes the datasets, algorithms, and network topologies tested. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers used for the experiments. |
| Experiment Setup | Yes | In this experiment, we set N = 100. Moreover, Algorithm 1 (DMFW), Algorithm 2 (DOSFW) and DOGD run on the complete graph, where each node is connected with other nodes. ... In addition, we set Um = 5 in Movie Lens dataset and Uj = 5 in Jester dataset, respectively. ... Moreover, the constraint set is x [0, 1]|Bv| : 1Tx 1 . ... To this end, we construct three types of network topologies, i.e., complete graph, cycle graph, and Watts Strogatz. |