Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection-猫眼课题宝

DOI：

发表时间：

2023

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Shuyang Yu;Junyuan Hong;Haotao Wang;Zhangyang Wang;Jiayu Zhou

深层神经网络在许多挑战预测任务中取得了巨大的成功，但它们经常遭受分布（OOD）样本的痛苦，以高度的确定性误导了它们，但最近的进步表明了OOD检测性能，但是OOD检测结果在联合学习（FL）中，即使许多安全敏感应用程序，例如自动驾驶和语音识别，也很大程度上被忽略了授权通常是使用FL进行数据隐私问题的培训。，这样的大规模OOD培训数据可能是昂贵的甚至是不可行的，尤其是对于资源有限的本地设备而言，FL中的臭名昭著的挑战是数据。异质性在每个客户中分布非差异（非IID）。来自其他客户的IID数据（看不见的外部类）可以用作真正的OOD样本的替代品。），学习一个类别的生成器来综合虚拟外部阶级OOD样本，并维持数据的确定性和通信效率。

Deep neural networks have witnessed huge successes in many challenging prediction tasks and yet they often suffer from out-of-distribution (OoD) samples, misclassifying them with high conﬁdence. Recent advances show promising OoD detection performance for centralized training, and however, OoD detection in federated learning (FL) is largely overlooked, even though many security sensitive applications such as autonomous driving and voice recognition authorization are commonly trained using FL for data privacy concerns. The main challenge that prevents previous state-of-the-art OoD detection methods from being incorporated to FL is that they require large amount of real OoD samples. However, in real-world scenarios, such large-scale OoD training data can be costly or even infeasible to obtain, especially for resource-limited local devices. On the other hand, a notorious challenge in FL is data heterogeneity where each client collects non-identically and independently distributed (non-iid) data. We propose to take advantage of such heterogeneity and turn the curse into a blessing that facilitates OoD detection in FL. The key is that for each client, non-iid data from other clients (unseen external classes) can serve as an alternative to real OoD samples. Speciﬁcally, we propose a novel Federated Out-of-Distribution Synthesizer (F OSTER ), which learns a class-conditional generator to synthesize virtual external-class OoD samples, and maintains data conﬁdentiality and communication efﬁciency required by FL. Experimental results show that our method outperforms the state-of-the-art for

Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection

文献摘要

相似文献