Fairness Interventions as (Dis)Incentives for Strategic Manipulation

Authors: Xueru Zhang, Mohammad Mahdi Khalili, Kun Jin, Parinaz Naghizadeh, Mingyan Liu

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We examine our theoretical findings using both synthetic and real-world datasets (Sec. 8).
Researcher Affiliation Collaboration 1Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA. 2Yahoo! Inc., the author is also with The Ohio State University. 3Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA. 4Integrated Systems Engineering & Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We conduct experiments on both a Gaussian synthetic dataset, and the FICO scores dataset (Reserve, 2007).
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 No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes We consider manipulation costs following either uniform (Cs U[0, c]) or beta distributions (Cs Beta(v, w)).