Co-exposure Maximization in Online Social Networks

Authors: Sijing Tu, Cigdem Aslay, Aristides Gionis

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

Reproducibility Variable Result LLM Response
Research Type Experimental We experimentally demonstrate the quality of our proposal on real-world social networks.Finally, we experimentally evaluate our algorithm on several real-world datasets and demonstrate its superiority over several baselines.We evaluate our method against different baselines on real-world networks.
Researcher Affiliation Academia Sijing Tu Department of Computer Science KTH Royal Institute of Technology Stockholm, Sweden sijing@kth.se Cigdem Aslay Department of Computer Science Aarhus University Aarhus, Denmark cigdem@cs.au.dk Aristides Gionis Department of Computer Science KTH Royal Institute of Technology Stockholm, Sweden argioni@kth.se
Pseudocode Yes Algorithm 1: Pairs-Greedy
Open Source Code Yes Omitted proofs and implementation are provided as supplementary material.
Open Datasets Yes Datasets. We use the following networks: Flixster [6], Last.FM [5], Net HEPT [13], and Wiki Vote [30]. Basic statistics of these networks are reported in the supplementary.
Dataset Splits No The paper does not specify training, validation, and test dataset splits (e.g., percentages or exact counts) for reproducibility. It uses the term 'validation' in the context of a statistical test for estimating a lower bound, not for data partitioning.
Hardware Specification Yes Our experiments are performed on a server with a 2 × 10 core Xeon E5 2680 v2 2.80 GHz processor, with 256 GB memory.
Software Dependencies No The paper mentions various models and baselines but does not list specific software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes The confidence and accuracy parameters are set to ℓ = 1 and ϵ = 0.2. Our method takes as input seed budgets kr and kb... To ensure a fair comparison, we first execute Balance Exposure with varying k = 50, 100, 150, 200, and use the returned values kr and kb as input for the other methods. We fix τ = 2 and kr = 20.