The growing presence of mobile and IoT devices has led to massive decentralized and evolving data, driving the rise of Federated Learning (FL) to enable collaborative training without data sharing. However, traditional FL assumes static data distributions, which is unrealistic for dynamic real-world environments. To address this challenge, Federated Class-Incremental Learning (FCIL) has emerged as a promising framework that enables flexible adaptation to newly introduced classes over time. Existing FCIL methods typically integrate old knowledge preservation into local client training. However, these methods cannot avoid spatial-temporal client drift caused by data heterogeneity and often incur significant computational and communication overhead, limiting practical deployment. To address these challenges simultaneously, we propose a novel approach, Spatial-Temporal Statistics Aggregation (STSA), which provides a unified framework to aggregate feature statistics both spatially (across clients) and temporally (across stages). The aggregated feature statistics are unaffected by data heterogeneity and can be used to update the classifier in closed form at each stage. Additionally, we introduce STSA-E, a communication-efficient variant that enables the server to approximate global second-order feature statistics using first-order statistics uploaded from clients. Theoretical analysis shows that it achieves similar performance to STSA with much lower communication overhead. Extensive experiments on three widely used FCIL datasets, with varying degrees of data heterogeneity, show that our method outperforms state-of-the-art FCIL methods in terms of performance, flexibility, and both communication and computation efficiency. The code is available at https://github.com/Yuqin-G/STSA.

High pitch helical Computed Tomography (CT) scanning significantly reduces radiation dose while improving temporal resolution, offering substantial clinical benefits. However, the incomplete scanning data commonly leads to artifacts in the reconstructed images, degrading image quality and potentially affecting clinical diagnosis. Existing high pitch reconstruction methods primarily operate within the image domain or combine image-domain networks with traditional iterative algorithms, yet their performance remains limited. To address such limitations, we propose Delta-Net, a deep dual-domain alternating iterative optimization network for high pitch helical CT reconstruction. We introduce a novel optimization objective and develop an alternating iterative optimization framework, where each sub iteration consists of projection domain correction and image domain refinement. To enhance generalization and robustness, deep neural networks are employed to learn domain-specific priors, which are incorporated as regularization terms, with all hyper-parameters automatically optimized during training. Specifically, the image domain residual refinement network (IRN) and projection domain consistency enhanced network (PCN) regularize the intermediate results across both domains. Additionally, to improve the capability of artifact suppression and structure restoration, a structure-aware joint loss is tailored for the optimization of Delta-Net. Quantitative and qualitative evaluations on clinical datasets demonstrate that Delta-Net outperforms other competitive methods in artifact suppression, fine structure recovery, and generalization.

Multi-source generative models have gained significant attention due to their ability to capture complex data distributions across diverse domains. However, existing approaches often struggle with limitations such as negative transfer and an over-reliance on large pre-trained models. To address these challenges, we propose a novel method that effectively handles scenarios with outlier source domains, while making weaker assumptions about the data, thus ensuring broader applicability. Our approach enhances robustness and efficiency, supported by rigorous theoretical analysis, including non-asymptotic error bounds and asymptotic guarantees. In the experiments, we validate our methods through numerical simulations and realworld data experiments, showcasing their practical effectiveness and adaptability.

Conducting valid comparative evaluations of techniques in the field of Music Information Retrieval (MIR)presents particular challenges to MIR researchers due to issues of copyright and data sharing. Further, the interdisciplinary nature of MIR research and multi-faceted nature of human music perception make the sharing and reuse of techniques and implementations for particular facets of music perception and music information retrieval tasks highly desirable. In addition the field makes use of a diverse range of file formats, software environments and toolkits for extracting, encoding and accessing MIR data and services, making reuse extremely challenging. The NEMA project aims to provide the MIR field with a high-quality, secure and extensible workflow environment to facilitate: computation over remote audio and resource collections; optimal code reuse, interoperability between data formats and types, sharing and dissemination; standardised, high-quality evaluation procedures; and the encoding of metadata, data and results in a format suitable for distributed systems.