Heterogeneous Peer Effects in the Linear Threshold Model

Authors: Christopher Tran, Elena Zheleva4175-4183

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experimental results on synthetic and realworld datasets show that our proposed models can better predict individual-level thresholds in the Linear Threshold Model and thus more precisely predict which nodes will get activated over time.
Researcher Affiliation Academia Christopher Tran, Elena Zheleva Department of Computer Science, University of Illinois at Chicago Chicago, IL {ctran29, ezheleva}@uic.edu
Pseudocode Yes Pseudocode for ST-Learner is available in the Appendix.
Open Source Code Yes The proof is in the Appendix2. 2https://github.com/edgeslab/hpe-ltm
Open Datasets Yes The Hateful Users dataset is a retweet network from Twitter, with 200 most recent tweets for each user (Ribeiro et al. 2018). ... Higgs Boson. This dataset is based on the announcement of the Higgs-boson-like particle at CERN on July 4, 2012. ... (De Domenico et al. 2013).
Dataset Splits No The paper mentions 'training data' and refers to using 'a validation set' for the CT-HV method. However, it does not explicitly provide specific percentages, sample counts, or methodology for the train/validation/test splits of the datasets used in their experiments.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch versions).
Experiment Setup Yes We set the number of nodes to 1000, and for each node, we randomly generate 100 node attributes from a Gaussian, N(0, 1). ... 50 nodes are randomly activated, and diffusion events are generated based on LTM for 8 time steps.