arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.06171cs.LGcs.AIcs.DC
收藏

从不可信源学习的概率推理

Probabilistic Inference for Learning from Untrusted Sources

IBM Research(IBM研究院)

Duc Thien Nguyen, Shiau Hoong Lim, Laura Wynter, Desmond Cai

摘要:

联邦学习带来了更快的学习、更好的解决方案以及当来自不同方的异构数据增加多样性时更大的转移倾向的潜在好处。然而,由于联邦学习任务往往是大型和复杂的,并且训练时间不可忽略,因此聚合算法对非IID数据和受损方具有鲁棒性是很重要的。这种鲁棒性依赖于识别和适当加权不兼容方的能力。最近的工作假设有一个\textit{reference dataset},通过它可以执行识别。我们考虑的设置中没有这样的参考数据集是可用的;相反,双方的质量和适用性需要是\textit{inferred}。我们通过从众包预测和协同过滤中带来想法来做到这一点,在这种情况下,人们必须从质量未知的参与者那里推断出未知的基本事实。我们提出了新的联邦学习聚合算法的基础上贝叶斯推理,适应各方的质量。经验上,我们表明,算法优于标准和强大的聚合在联邦学习的合成和真实数据。

英文摘要:

Federated learning brings potential benefits of faster learning, better solutions, and a greater propensity to transfer when heterogeneous data from different parties increases diversity. However, because federated learning tasks tend to be large and complex, and training times non-negligible, it is important for the aggregation algorithm to be robust to non-IID data and corrupted parties. This robustness relies on the ability to identify, and appropriately weight, incompatible parties. Recent work assumes that a \textit{reference dataset} is available through which to perform the identification. We consider settings where no such reference dataset is available; rather, the quality and suitability of the parties needs to be \textit{inferred}. We do so by bringing ideas from crowdsourced predictions and collaborative filtering, where one must infer an unknown ground truth given proposals from participants with unknown quality. We propose novel federated learning aggregation algorithms based on Bayesian inference that adapt to the quality of the parties. Empirically, we show that the algorithms outperform standard and robust aggregation in federated learning on both synthetic and real data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑