Federated learning (FL) enables collaborative medical imaging training without sharing raw data. However, existing frameworks treat privacy, interpretability, and cross-site explanation consistency as separate objectives. We present FedXAI, a unified framework that substantially mitigates this trilemma within a single architecture. FedXAI introduces three components: (i) Self-Explainable Federated Architecture (SEFA), which integrates an EfficientNet-B0 backbone with a 32-dimensional hybrid concept-bottleneck layer anchored to RadLex radiological ontology terms; (ii) Federated Explanation Aggregation Protocol (FEAP), which extends server-side aggregation with a cosine-consistency penalty to align client explanation spaces; and (iii) the Privacy-Preserving Explanation Verification (PPEV) module, which audits cross-client explanation quality via the subsampled Gaussian mechanism with Rényi Differential Privacy (RDP) accounting. Evaluated on the NIH ChestX-ray14 dataset with non-IID Dirichlet partitioning ( α = 0.5 ) across five simulated hospital clients, FedXAI achieves a mean AUC of 0.7349, outperforming FedAvg (0.7193), FedProx (0.7241), SCAFFOLD (0.7268), FedBN (0.7285), and MOON (0.7301). Simultaneously, it increases cross-client explanation consistency from 83.6 (ε ,δ ) -differential privacy for the explanation-audit channel, certifying ε = 0.1394 at δ = 10^-5 . Model parameter transmission follows the standard FL architectural separation, while end-to-end DP-SGD training is left for future work. On the benchmark studied here, FedXAI demonstrates that privacy, diagnostic accuracy, and interpretability in federated medical imaging can be advanced simultaneously through principled architectural integration.
In the mining industry, unsafe worker behaviors pose significant safety risks. Recent advances in deep learning have improved unsafe behavior recognition; however, challenges remain in achieving both real-time performance and high accuracy under complex mining conditions, as well as in the availability of dedicated datasets. To address these issues, we introduce a comprehensive miner unsafe behavior dataset and propose the Mining Industry Unsafe Behaviors Monitoring Framework (MIUBM-Net), which integrates STFNet-A for typical unsafe behavior detection and Alpha-SDL-Pose, based on Dual Non-Local Attention (DNLA), for posture-related unsafe behavior recognition. STFNet-A achieves 96.9
Despite their success, Deep Learning (DL) models are susceptible to spurious correlations. These are accidental correlations between non-predictive features of the training dataset and the target label, leading to models that do not generalise well to samples without such spurious correlations. We propose to address this failure mode by extending and improving an existing method for spurious correlation robustness — UnLearning from Experience (ULE). ULE trains two models in parallel; a biased model is encouraged to learn the spurious correlations, while a separate debiased model is trained to solve the same task while avoiding learning the same behaviour as the first, thus avoiding learning the spurious correlations. A weakness of ULE is that it treats every training example identically, regardless of whether or not it contains a spurious correlation. Therefore, ULE does not make optimal use of the training data, leading to worse-than-necessary performance. To address this weakness, we introduce Weighted UnLearning from Experience (wULE), which modifies the original ULE loss function to reweight the components depending on whether a training sample likely contains spurious correlations. Hence, we explore two methods for identifying training samples likely to contain spurious correlations. We test our approach using several well-known spurious correlation robustness benchmarks — Waterbirds, CelebA, UrbanCars and MultiNLI. Our novel wULE method outperforms the original ULE in all cases and achieves Worst-Group Accuracy (WGA) results comparable to the best methods in the spurious correlation robustness literature.
We study parameter inference in simulation-based stochastic models where the analytical form of the likelihood is unknown. The main difficulty is that score evaluation as a ratio of noisy Monte Carlo estimators induces bias and instability, which we overcome with a ratio-free nested multi-time-scale (NMTS) stochastic approximation (SA) method that simultaneously tracks the score and drives the parameter update. We provide a comprehensive theoretical analysis of the proposed NMTS algorithm for solving likelihood-free inference problems, including strong convergence, asymptotic normality, and convergence rates. We show that our algorithm can eliminate the original asymptotic bias O (√(1/N) ) and accelerate the convergence rate from O (β _k+√(1/N) ) to O (β _k/α _k+√(α _k/N) ) , where N is the fixed batch size, α _k and β _k are decreasing step sizes with α _k , β _k , β _k/α _k→ 0 . With proper choice of α _k and β _k , our convergence rates can match the optimal rate in the multi-time-scale SA literature. Numerical experiments demonstrate that our algorithm can improve the estimation accuracy by one to two orders of magnitude at the same computational cost, making it efficient for parameter estimation in stochastic systems.
ML is playing an increasingly crucial role in estimating causal effects of treatments on outcomes from observational data. Many ML methods (‘causal estimators’) have been proposed for this task. All of these methods, as with any ML approach, require extensive hyperparameter tuning. For non-causal predictive tasks, there is a consensus on the choice of tuning metrics (e.g. mean squared error), making it simple to compare models. However, for causal inference tasks, such a consensus is yet to be reached, making a any comparison of causal models difficult. On top of that, there is no ideal metric on which to tune causal estimators, so one must rely on proxies. Furthermore, the fact that model selection in causal inference involves multiple components (causal estimator, ML regressor, hyperparameters, metric), complicates the issue even further. In order to evaluate the importance of each component, we perform an extensive empirical study on their combination. Our experimental setup involves many commonly used causal estimators, regressors (‘base learners’ henceforth) and metrics applied to four well-known causal inference benchmark datasets. Our results show that hyperparameter tuning increased the probability of reaching state-of-the-art performance in average ( 65%→ 81% ) and individualised ( 50%→ 57% ) effect estimation with only commonly used estimators. We also show that the performance of standard metrics can be inconsistent across different scenarios. Our findings highlight the need for further research to establish whether metrics uniformly capable of state-of-the-art performance in causal model evaluation can be found.
