Towards Reducing Biases in Combining Multiple Experts Online

Authors: Yi Sun, Iván Ramírez Díaz, Alfredo Cuesta Infante, Kalyan Veeramachaneni

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also demonstrate the performance of the algorithm on real data sets commonly used by the fairness community.
Researcher Affiliation Academia Yi Sun1 , Iv an Ram ırez D ıaz1 , Alfredo Cuesta-Infante2 and Kalyan Veeramachaneni1 1 MIT 2University Rey Juan Carlos {yis, iramdia}@mit.edu, alfredo.cuesta@urjc.es, kalyan@csail.mit.edu
Pseudocode No The paper includes 'Figure 1: This figure shows how G-FORCE process an input pair (x, z)', which illustrates the algorithm's mechanism through a diagram and descriptive steps, but it is not presented as formal pseudocode or a clearly labeled algorithm block.
Open Source Code No The paper does not provide any explicit statements about releasing source code for the described methodology, nor does it include a link to a code repository.
Open Datasets Yes We consider the Adult, German Credit and COMPAS datasets, all of which are commonly used by the fairness community.
Dataset Splits No The paper states, 'These classifiers are trained using 70% of the data set. The remaining 30% of the dataset is set aside to simulate the online arrival of individuals,' but does not explicitly describe a separate validation split or cross-validation setup.
Hardware Specification No The paper does not provide specific details regarding the hardware (e.g., CPU, GPU models, or memory) used to conduct the experiments.
Software Dependencies No The paper lists the types of classifiers used (Logistic Regression, SVM, Decision Tree, MLP), but does not specify the software libraries or their version numbers used for implementation or experimentation.
Experiment Setup Yes We use η = 0.35 in experiments. For each dataset, we repeat the experiments 100 times, each with 10000 samples from a specific distribution setting. We repeated the experiments 1000 times for German and COMPAS, as well as 10 times for Adult, by randomizing the arrival sequence of individuals.