AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Incentives in Private Collaborative Machine Learning

Rachael Hwee Ling Sim, Yehong Zhang, Trong Nghia Hoang, Xinyi Xu, Bryan Kian Hsiang Low, Patrick Jaillet

NeurIPS 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
weaken party 2's DP guarantee (increase epsilon_2 from 0.004 to 12.5)Bayesian surprise valuation with rho-Shapley reward · Syn, CaliH, Diabparty 2 valuation v_2, Shapley value, attained reward r_2Improved
strengthen party 2's DP guarantee (decrease epsilon_2)grand coalition and party 2 individual models · Syn, CaliH, DiabMNLP (lower is better)Hurt
enforce privacy-valuation/reward trade-off: MNLP_r of reward rises as epsilon_2 decreasesproposed scheme · Syn, CaliH, DiabMNLP_r of party 2's model rewardHurt
join collaboration (reward model) instead of training alone, as epsilon_2 decreasesparty 2 · Syn, CaliH, DiabMNLP_r vs MNLP_iImproved
exception: privacy-utility monotonicity under validation-based valuationvalidation-set-based valuation · DiabMNLP vs epsilon_2No clear effect
replace noise addition (tau_i) with likelihood tempering (kappa_i) for reward control (ablation)reward control mechanism · Synmonotonicity of r_iImproved
replace noise addition with likelihood tempering (ablation)reward control mechanism · Synsimilarity r'_i to grand coalition posterior at same r_iImproved
replace noise addition with likelihood tempering (ablation)reward control mechanism · Syn, CaliH, DiabMNLP_r (lower is better)Improved
replace noise addition with likelihood tempering (ablation)reward control mechanism · Syn, CaliH, Diabvariance of MNLP_rImproved
other parties choose weaker privacy (epsilon = 2 instead of 0.2)party 2 utility gain · appendix experimentsparty 2 utility gainImproved
use non-noise-aware inference instead of DP noise-aware inference (ablation)valuation function · appendixprivacy-valuation trade-offHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy