Optimal Feature Selection for Decision Robustness in Bayesian Networks

Authors: YooJung Choi, Adnan Darwiche, Guy Van den Broeck

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on Naive Bayes, as well as more general networks, show the efficacy and distinct behavior of this decision-making approach.
Researcher Affiliation Academia Yoo Jung Choi, Adnan Darwiche, and Guy Van den Broeck Computer Science Department University of California, Los Angeles
Pseudocode Yes Algorithm 1 SDPd,T (X | Y, e) and Algorithm 2 FS-SDD(Q, d, b)
Open Source Code No The paper does not provide concrete access to source code for the methodology described in this paper. It mentions a third-party tool, SAMIAM, but not its own code.
Open Datasets Yes We evaluated our system on Naive Bayes networks from the UCI repository [Bache and Lichman, 2013], BFC (http://www.berkeleyfreeclinic. org/), and CRESST (http://www.cse.ucla.edu/).
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning.
Hardware Specification Yes a 2.6GHz Intel Xeon E5-2670 CPU with 4GB RAM was used.
Software Dependencies No The paper mentions using 'jointree inference as implemented in SAMIAM' but does not provide a specific version number for SAMIAM or any other software dependencies with versions.
Experiment Setup Yes For each network, we find the optimal subset for E-SDP with the budget set to 1/3 the number of features. In all experiments, the cost of each feature is 1, timeout is 1 hour, and a 2.6GHz Intel Xeon E5-2670 CPU with 4GB RAM was used.