MUVIR: Multi-View Rare Category Detection

Authors: Dawei Zhou, Jingrui He, K. Seluk Candan, Hasan Davulcu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on both synthetic and real data sets demonstrate the effectiveness of the proposed framework, especially in the presence of irrelevant views.
Researcher Affiliation Academia Dawei Zhou, Jingrui He, K. Seluk Candan, Hasan Davulcu Arizona State University Tempe, Arizona {dzhou23,jingrui.he,candan,hdavulcu}@asu.edu
Pseudocode Yes Algorithm 1 MUVIR Algorithm; Algorithm 2 MUVIR-LI Algorithm
Open Source Code No The paper does not provide any statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes In this section, we will present the results of our algorithm on both synthetic data sets and real data sets in multiple special scenarios... Adult data set contains 48842 instances and 14 features of each example... Statlog contains 58000 examples and 7 classes.
Dataset Splits No The paper discusses dataset sizes and modifications (e.g., downsampling minority class) but does not specify train/validation/test splits, sample counts for each, or cross-validation methods.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions using 'kernel density estimation' and refers to existing techniques like GRADE and NNDM but does not specify any software names with version numbers for implementation or dependencies.
Experiment Setup Yes In Section 4, we study the impact of the parameter d on the performance of MUVIR, and show that in general, d (0, 1.5] will lead to reasonable performance... In this experiment, we will focus on analyzing the impact from degree d and upper bound prior p.