Summary of Bgtplanner: Maximizing Training Accuracy For Differentially Private Federated Recommenders Via Strategic Privacy Budget Allocation, by Xianzhi Zhang et al.
BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
by Xianzhi Zhang, Yipeng Zhou, Miao Hu, Di Wu, Pengshan Liao, Mohsen Guizani, Michael Sheng
First submitted to arxiv on: 4 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper addresses the issue of privacy leakage in federated recommenders by proposing a novel approach called BGTplanner, which strategically allocates the privacy budget for each round of training. The BGTplanner uses Gaussian process regression and historical information to predict the change in recommendation accuracy with a certain allocated privacy budget, and then makes decisions using Contextual Multi-Armed Bandit (CMAB) to reconcile current improvement and long-term privacy constraints. The authors demonstrate that BGTplanner achieves an average improvement of 6.76% in training performance compared to state-of-the-art baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps keep your personal information safe online by creating a new way for computers to work together without sharing too much about you. It’s like a team project where everyone contributes, but nobody reveals their whole plan. The problem is that this teamwork doesn’t always get the best results because it has to be secret. To fix this, the paper introduces a smart system called BGTplanner that decides how much to share each time. This helps get better results and keeps your information safe. |
Keywords
» Artificial intelligence » Regression
