A Novel Data Representation for Effective Learning in Class Imbalanced Scenarios

Authors: Sri Harsha Dumpala, Rupayan Chakraborty, Sunil Kumar Kopparapu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on several benchmark datasets clearly indicate the usefulness of the proposed approach over the existing state-of-the-art techniques.
Researcher Affiliation Industry Sri Harsha Dumpala, Rupayan Chakraborty and Sunil Kumar Kopparapu TCS Reseach and Innovation Mumbai, India {d.harsha, rupayan.chakraborty, sunilkumar.kopparapu}@tcs.com
Pseudocode No The paper describes its methods in narrative text and figures, but does not include any structured pseudocode or algorithm blocks.
Open Source Code No Proposed s2s L along with MLP and CSMLP techniques are implemented using Keras deep learning toolkit [KER, 2016]. There is no statement about the authors releasing their own code.
Open Datasets Yes All datasets used in this work are obtained from KEEL dataset repository [Fernandez et al., 2008].
Dataset Splits Yes For each dataset, we use 5-fold (the folds as provided in the KEEL dataset repository are directly used) cross-validation approach to compare the performance of all the methods considered for analysis. ... Hence, at any time 80% of the data is used for training (75% as train set and 5% as validation set) and remaining 20% of the data is used for testing. The validation set is used for selecting network architecture and for hyper-parameter tuning.
Hardware Specification Yes Further, the average training time (in seconds) for convergence (using i5-3210M 3.1GHz cpu with 4-GB RAM) on Yeast6 for different techniques are: 98.7 (s2s L), 38.5 (MLP), 43.7 (CS-MLP), 213.8 (CSM), 95.3 (GSVM), 146.4 (EUSB).
Software Dependencies No Proposed s2s L along with MLP and CSMLP techniques are implemented using Keras deep learning toolkit [KER, 2016]. This mentions Keras but does not provide a specific version number for it.
Experiment Setup Yes For training s2s-MLP, we use Adam algorithm with an initial learning rate of 0.001. Binary cross-entropy is used as the cost function. The batch size and other hyper-parameters are selected considering the performance on the validation set. The number of units in the hidden layer is selected empirically by varying the hidden units from 2 to 4 d (twice the length of the input layer)