Non-Monotone Adaptive Submodular Maximization

Authors: Alkis Gotovos, Amin Karbasi, Andreas Krause

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We have evaluated our proposed algorithm on the two objective functions described in the previous section, namely influence maximization and maximum cut, on a few real-world data sets.
Researcher Affiliation Academia Alkis Gotovos ETH Zurich Amin Karbasi Yale University Andreas Krause ETH Zurich
Pseudocode Yes Algorithm 1 Adaptive random greedy
Open Source Code No No explicit statement or link regarding the public release of source code was found.
Open Datasets Yes For our experiments, we used networks from the KONECT2 database, which accumulates network data sets from various other sources. [...] [Mc Auley and Leskovec, 2012].
Dataset Splits No The paper does not provide explicit details about train/validation/test dataset splits for model training in a traditional sense. It mentions subsampling networks and evaluating on 'random realizations' and 'random ground sets' but no percentages or counts for distinct training, validation, and testing partitions.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments were mentioned.
Software Dependencies No No specific software dependencies with version numbers were listed (e.g., Python 3.x, TensorFlow x.x).
Experiment Setup Yes For the influence maximization objective, the influence propagation probability of each edge is chosen to be p = 0.1, and for the maximum cut objective, selecting a node cuts that node or one of its neighbors with equal probability. [...] we subsample each network down to 2000 nodes, [...] select uniformly at random a subset of 100 nodes as the ground set E, and repeat the experiments for 50 such random ground sets.