Gradient Method for Continuous Influence Maximization with Budget-Saving Considerations

Authors: Wei Chen, Weizhong Zhang, Haoyu Zhao43-50

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

Reproducibility Variable Result LLM Response
Research Type Experimental We test our algorithms on a real-world dataset and validate its effectiveness comparing with other algorithms.
Researcher Affiliation Collaboration 1Microsoft Research, Beijing, China 2,3IIIS, Tsinghua University, Beijing, China weic@microsoft.com, {zwz15, zhaohy16}@mails.tsinghua.edu.cn
Pseudocode Yes Algorithm 1 Grad-RIS: Gradient-RIS Meta-Algorithm for CIM-BS. and Algorithm 2 Sampling Procedure.
Open Source Code No The paper mentions a full technical report for proofs and experiment results, but does not state that the source code for the described methodology is publicly available or provide a link to it.
Open Datasets Yes We test on the DM network, which is a network of data mining researchers extracted from the Arnet Miner archive (arnetminer.org), with 679 nodes and 3,374 edges, and edge weights are learned from a topic affinity model and obtained from the authors (Tang et al. 2009).
Dataset Splits No The paper uses the DM network for testing but does not specify any explicit training, validation, or test dataset splits (e.g., percentages or sample counts).
Hardware Specification No The paper does not provide specific details about the hardware used, such as GPU or CPU models, memory, or cloud instance specifications.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies used in the experiments.
Experiment Setup Yes For parameter settings, we set ε = 0.1 and ℓ= 1 for all algorithms. For Greedy-RIS, we set the greedy step size to be 0.1 on each dimension.