Dynamic Network Model from Partial Observations

Authors: Elahe Ghalebi, Baharan Mirzasoleiman, Radu Grosu, Jure Leskovec

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We show the effectiveness of our approach using extensive experiments on synthetic as well as real-world networks.
Researcher Affiliation Academia Elahe Ghalebi TU Wien eghalebi@cps.tuwien.ac.at Baharan Mirzasoleiman Stanford University baharanm@cs.stanford.edu Radu Grosu TU Wien radu.grosu@tuwien.ac.at Jure Leskovec Stanford University jure@cs.stanford.edu
Pseudocode Yes Algorithm 1 EXTRACT_OBSERVATIONS Input: Set of cascades {tc1, , tc|C|}, sample size q. Output: Extracted multiset of edges X from cascades. ... Algorithm 2 UPDATE_NETWORK_MODEL Input: Model M(c1:M, p1:M, β1:N), set of cascades {tc1, , tc|C|}. Output: Updated model M (c1:M, p1:M, β1:N) ... Algorithm 3 DYNAMIC_NETWORK_INFERENCE (DYFERENCE) Input: Set of infection times {tc1, , tc|C|}, interval length w. Output: Updated network model Mt at times t = iw.
Open Source Code No The paper does not provide an explicit statement about open-source code availability or a link to a code repository.
Open Datasets Yes (1) Twitter [37] contains the diffusion of URLs on Twitter during 2010 and the follower graph of users. ... (2) Memes [38] contains the diffusion of memes from March 2011 to February 2012 over online news websites;
Dataset Splits Yes We use the infection times in the first 80% of the total time interval for training, and the remaining 20% for the test.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes In all the experiments we use a sample size of q = |Ec| 1 for all the cascades c C. We further consider a window of length w = 1 day in our dynamic network inference experiments in Fig 1 and w = 2-years in Table 3.