Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 1462-1473· 0 citations· 21 references
TL;DR
DC-FNCD (Divide-and-Conquer based Federated Nonlinear Causal Discovery) is proposed, which decomposes the global problem into independent per-variable neighborhood learning tasks, enabling lossless federated aggregation without raw data exchange.
Abstract
Federated causal discovery aims to learn causal structures from distributed data without sharing raw samples. Existing federated nonlinear methods adopt a monolithic global strategy that optimizes the entire graph simultaneously, suffering from catastrophic error propagation: a single misidentified edge cascades through the global structure, severely degrading accuracy under heterogeneous and limited local data. We propose DC-FNCD (Divide-and-Conquer based Federated Nonlinear Causal Discovery), which decomposes the global problem into independent per-variable neighborhood learning tasks. The core mechanism is a characteristic function-based conditional independence test whose empirical statistics admit exact linear decomposition across clients, enabling lossless federated aggregation without raw data exchange. Local neighborhoods are merged via conflict-aware skeleton construction and oriented through federated additive noise model testing. Extensive experiments demonstrate that DC-FNCD significantly outperforms state-of-the-art federated baselines. The source code is available at https://github.com/Xianjie-Guo/DC-FNCD.
This work proposes a FedIGL framework based on invariant learning, which effectively disrupts spurious correlations and further mines the invariant factors across different distributions, and proposes a novel Bi-Gradient Regularization strategy that introduces gradient constraints to guide the model in identifying client-agnostic and client-specific subgraph patterns for better graph representations.
Lingren Wang, Wenxuan Tu, Jiaxin Wang et al.· Neural Information Processin...· 2 citations
Federated learning (FL) collaboratively trains models across networked industrial Internet of Things (IIoT) terminals. However, statistical heterogeneity in IIoT data often hinders the performance of global models. Current FL methods typically focus on single-level representation alignment and fail to exploit gradient-guided semantic feedback across hierarchical layers. To address statistical heterogeneity, we propose federated hierarchical prototype learning (FedHiPL), which models local representations with Gaussian prototypes and improves global learning through hierarchical prototype calibration. First, FedHiPL performs multilevel prototype alignment based on symmetric Kullback–Leibler divergence to enforce representation consistency across layers. Second, FedHiPL calibrates the local decision head by balancing local and global decision objectives with decision consistency constraints. Third, FedHiPL rectifies global prototypes through a gradient-guided hierarchical calibration module to maintain structural consistency across network layers. Experiments on a custom-constructed distributed cluster demonstrate that FedHiPL achieves 93.24% accuracy on Edge-IIoT and 72.36% accuracy on UNSW-NB15 under strong statistical heterogeneity, outperforming the representative prototype-based baseline FedProto by 6.06% and 15.80%, respectively.
Fang Li, Zhi-Cheng Chen, Jinghao Liu et al.· IEEE Internet of Things Jour...· 0 citations
FedTopo is proposed, a relation-level framework that encodes global knowledge as class relation topology, capturing how classes relate within each client rather than where they lie in feature space.
Zhaoyang Ma, Zhihao Wu, Xin Gao et al.· 0 citations
A novel FL framework is presented, FedPhoenix, that stochastically re-sets partial parameters in each round to destroy some features of the global model, guiding FL training to learn multiple generalized features for inference rather than specific overfitting features.
Jiahao Wu, Ming Hu, Yanxin Yang et al.· Advances in Neural Informati...· 1 citation
