提出新方法提升联邦学习在分布外数据下的泛化能力
FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD
- 通过建模不变与可变特征间的弱因果关系，联合学习双重表示
- 在CIFAR-10和CIFAR-100上分别比最优基线高出3.04%和8.11%
- 适用于隐私敏感场景中应对数据分布偏移的模型部署
随着对数据隐私保护需求的增长和计算基础设施的进步，联邦学习（FL）已成为一种主流的分布式学习范式。然而，数据分布差异（如协变量偏移和语义偏移）严重制约了其在真实场景中的可靠性。为此，本文提出FedSDWC，一种融合不变与可变特征的因果推断方法。该方法通过建模不变特征与可变特征之间的弱因果影响，推断出因果语义表示，有效克服了现有不变学习方法在准确捕捉不变特征及直接构建因果表示方面的局限。该方法显著提升了联邦学习的泛化能力和分布外（OOD）数据检测性能。理论上，我们在特定条件下推导了FedSDWC的泛化误差界，并首次建立了其与客户端先验分布的关系。大量实验在多个基准数据集上验证了其优越性：例如，在CIFAR-10上平均优于次优基线FedICON 3.04%，在CIFAR-100上提升达8.11%。
原文摘要 · Abstract (English)
Amid growing demands for data privacy and advances in computational infrastructure, federated learning (FL) has emerged as a prominent distributed learning paradigm. Nevertheless, differences in data distribution (such as covariate and semantic shifts) severely affect its reliability in real-world deployments. To address this issue, we propose FedSDWC, a causal inference method that integrates both invariant and variant features. FedSDWC infers causal semantic representations by modeling the weak causal influence between invariant and variant features, effectively overcoming the limitations of existing invariant learning methods in accurately capturing invariant features and directly constructing causal representations. This approach significantly enhances FL's ability to generalize and detect OOD data. Theoretically, we derive FedSDWC's generalization error bound under specific conditions and, for the first time, establish its relationship with client prior distributions. Moreover, extensive experiments conducted on multiple benchmark datasets validate the superior performance of FedSDWC in handling covariate and semantic shifts. For example, FedSDWC outperforms FedICON, the next best baseline, by an average of 3.04% on CIFAR-10 and 8.11% on CIFAR-100.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。