Given a non-negative integer \ell, the k-median with outliers problem extends the standard k-median problem by allowing the removal of up to \ell points and minimizing the clustering cost over the remaining ones. Algorithmic development in this setting remains an active area of research due to its relevance in processing noisy data. In this paper, we present a sampling-based reduction from the k-median with outliers problem to its outlier-free counterpart. The reduction incurs a multiplicative overhead of (kℓ⁻¹ + ε⁻¹)^O(ℓ) in the running time: it yields (kℓ⁻¹ + ε⁻¹)^O(ℓ) outlier-free instances, a solution to one of which can be directly transformed into a solution to the original instance with an arbitrarily small loss in the approximation ratio. This improves upon the previously known reduction with an overhead of ((k + ℓ)ε⁻¹)^O(ℓ). As applications, we obtain faster fixed-parameter tractable (FPT) algorithms with tight approximation guarantees for the k-median with outliers problem under various metric spaces. Furthermore, our approach naturally generalizes to constrained variants of the problem where additional constraints are imposed on the cluster sizes, and yields similar improvements in their FPT approximations.

In modern power systems, the day-ahead Energy Resource Management (ERM) problem, particularly under high penetration of Distributed Energy Resources (DERs), often becomes a high-dimensional challenge due to the uncertainties inherent in renewable generation, load consumption, and market prices. The complex, nested relationships between input control vectors and system outputs effectively transform these problems into black-box models, where only inputs and outputs are observable. This poses significant challenges for optimization algorithms, especially in terms of computational efficiency, under conditions of costly function evaluations and a limited number of evaluations. To address these challenges, this study proposes an anisotropic random-feature Extreme Learning Machine (ELM) surrogate integrated with evolutionary algorithms, designed for high-dimensional optimization problems under uncertainty. By incorporating variable-level scaling and anisotropic transformations, the proposed surrogate dynamically adapts to the heterogeneous correlations across different dimensions, thereby enhancing optimization efficiency while maintaining the rapid training and generalization capabilities of ELM. Experiments on the GECCO competition platform and widely used large-scale benchmark suites show that the proposed method achieves superior solution quality compared with state-of-the-art evolutionary algorithms.

Day-ahead energy resource management faces uncertainty in renewables, demand, prices, and EV operations, yet existing methods often struggle with high dimensionality and expensive evaluations. This paper develops a Dual-layer Synchronous optimization framework that integrates a Ring Cellular Encode-Decode UMDA with an anisotropic radial basis function surrogate (DLRC-ARBF). The lower layer encodes decision variables and samples from univariate marginal distributions, which reduces the effective selection in each dimension while maintaining population diversity. In parallel, the upper layer learns dimension-specific length scales with an ARBF model to capture axis-dependent variability and to generate directionally scaled candidate solutions around elites. Both layers synchronously propose offspring each generation, and their joint subpopulations are evaluated on the true objective. The results show that DLRC-ARBF surpasses all other participants on the IEEE CEC/GECCO 2025 competition benchmark under the same evaluation budget, achieving the best overall performance.

Human leukocyte antigen (HLA) molecules play a pivotal role in antigen presentation. Tumor cells present neoantigens on the cell surface via HLA molecules, thereby activating cytotoxic T cells and eliciting immune responses. This process offers critical opportunities for cancer immunotherapy and tumor vaccine development. However, the identification of tumor neoantigens remains challenging due to limitations in data scale, prediction accuracy, and cross-species compatibility of existing methods. To address these challenges, we developed TransBindpMHCI, a transformer-based pan-specific major histocompatibility complex (MHC) peptide binding prediction model. By employing 1,404,492 mass spectrometry-screened MHC-presented peptides for modeling, the model directly captures the authentic processes of peptide generation and presentation. Its dual-tier transformer encoder architecture significantly enhances feature extraction capabilities for peptide-MHC binding patterns while reducing computational complexity. Furthermore, TransBindpMHCI extends prediction coverage to peptides spanning 8–15 amino acids and achieves cross-species compatibility for both human and murine MHC-I molecules. Comprehensive evaluations demonstrate that TransBindpMHCI outperforms existing methods in accuracy, computational efficiency, and generalizability, enabling the identification of more immunogenic neoantigens. This model holds substantial promise for advancing tumor neoantigen validation and personalized vaccine design.

As a key application of the Agricultural Internet of Things (AIoT), multimodal agriproduct anomaly detection faces severe privacy and security challenges. Existing federated learning (FL) methods struggle to capture fine-grained cross-modal correlations and to address the modality under-optimization problem, thereby limiting both detection accuracy and privacy levels. To this end, this paper proposes a privacy-preserving federated multimodal agriproduct anomaly detection scheme in AIoT based on modality-under-optimized knowledge distillation (PAMAD), achieving high-utility anomaly detection with enhanced privacy protection. Specifically, we develop a hierarchical privacy protection method for multimodal fine-grained alignment fusion based on meta-learning (HPPMF), which effectively captures cross-modal semantic correlations and protects the privacy of fused features. In addition, we propose a multi-task pre-training algorithm based on modality-under-optimized knowledge distillation (MTLMKD) to alleviate modal imbalance. We further design a pre-training dynamic protection algorithm based on adaptive gradient quantization (PDAGC) to ensure model security. Subsequently, a multimodal agriproduct anomaly detection method with a self-supervised denoising encoder (MAPADSE) is introduced to improve detection accuracy under noisy conditions. Rigorous security analysis demonstrates that the PAMAD scheme satisfies differential privacy. Experimental results show that, compared with existing state-of-the-art methods, our PAMAD scheme improves AUROC and accuracy by 7.56% and 8.71%, respectively, achieving a desirable balance between privacy protection and anomaly detection accuracy in AIoT services.

With the rapid surge in industrial data, cloud computing has been integrated into Industrial Internet of Things (IIoT) systems to store, compute, and share massive data. In this process, privacy and data integrity are core concerns. Oblivious RAM (i.e., ORAM) is a technology widely applied to defend against cloud storage access pattern attacks. However, most existing ORAM systems do not consider the integration of data integrity verification technology. Although there are integrity verification systems integrated into conventional Path ORAM and Ring ORAM, they are not suitable for existing new ORAM systems. And the existing data integrity verification ORAM system still has the problem of excessive performance overhead. To address these challenges, this article proposes a novel high-performance data integrity ORAM system, VM-ORAM. Optimizes the ORAM integrity verification process by integrating dynamic scheduling and multipath eviction strategies, thereby minimizing performance loss. The comprehensive analysis and experimental results of this article show that VM-ORAM system not only defends against data tampering attacks, but also maintains high performance of the system.

To meet the high performance requirement of real time and critical applications in industrial Internet of Things, modern lossless ethernet data center networks (DCNs) deployed with remote direct memory access and priority-based flow control (PFC) are dedicated to delivering low latency and high bandwidth. However, existing load balancing schemes either lack sub-round-trip-time congestion sensing or fail to accurately detect and reroute flows that cause congestion in PFC-enabled lossless DCNs. Therefore, we propose LBoDSN, an in-network load balancing for lossless DCNs using direct switch notification (DSN) for fast congestion flow detection, to address above challenges. LBoDSN tracks the evolution of ingress queue lengths at destination switches to anticipate the initiation of PFC pause, precisely identifies congested flows before PFC pause, and then sends DSNs to source switches to perform rerouting. After rerouting, the congestion notification packet associated with the previous path is selectively discarded to improve transmission performance. Experiments under realistic workloads reveal that, LBoDSN outperforms CONGA by 13%–65%, and 25%–80% in average and tail Flow Completion Times (FCTs), respectively. Compared to ConWeave, LBoDSN achieves approximately 9% improvement in both average and tail FCTs, while reducing switch queue consumption for reordering.

Skeleton-based human action recognition (HAR) is greatly affected by abnormal situations in real-world scenarios, like occlusions and performance limitations of motion capture devices. Although recent research has enhanced the robustness of recognition by incorporating occlusion simulation in model training, it is still insufficient to effectively handle the complex and diverse abnormal situations in real-world scenarios. To address this issue, we propose SCCEAP, a novel framework combining fine-grained Skeleton Compression and Complementary Enhanced Adaptive feature fusion with the supervision of branch-stage text Prompts, for robust skeleton-based HAR. Our contributions lie in three aspects. First, the fine-grained skeleton compression is designed to generate multi-granularity skeleton sequences with diverse spatial details by fusing joints in the human skeleton according to their joint reliabilities and correlations. Then, we devise the complementary enhanced adaptive feature fusion, which utilizes motion details and stable semantic descriptions of motion features of the uncompressed and compressed skeleton sequences respectively, for complementary enhancement and adaptive feature fusion. Third, the branch-stage composite text-prompt supervision is performed to integrate both branch-wise and stage-wise text-prompt supervision for improving the ability to learn fine-grained spatiotemporal relationships of motion features. Experiments on three benchmark datasets-NTU RGB+D, NTU RGB+D 120, and Kinetics-400-demonstrate that SCCEAP achieves the state-of-the-art (SOTA) results, excelling on both normal and noisy skeleton data.

Traffic flow prediction, as a typical application of Industrial Internet of Things (IIoT) in urban infrastructure, faces critical security challenges. Existing privacy-preserving methods in two-tier federated learning (FL) frameworks primarily focus on dense data while neglecting privacy vulnerabilities in massive sparse traffic flow collected by clients, failing to effectively protect both high-sparsity traffic flow and federated pretrained models against privacy leakage risks. Therefore, this article proposes a novel three-tier FL framework-based privacy-preserving sparse traffic flow prediction (TFLST) scheme, achieving dual protection of sparse traffic flow and model parameters with high-precision prediction. Specifically, we innovatively design a spatiotemporal self-attention transformer-based Gestalt sparse key cell selection (STGSC) method to efficiently extract sparse key cells with high spatiotemporal correlations. Additionally, an adaptive truncated Gaussian mechanism-based local sparse traffic flow protection (ATLSP) algorithm is proposed, which dynamically allocates privacy budgets according to sparse correlations to achieve high-utility sparse data protection. A dynamic spatiotemporal matrix completion-based GCN pretraining protection (DSMGP) method is adopted to enhance the spatiotemporal features of sparse data efficiently, protect model parameter privacy, and improve FL training accuracy. Subsequently, we introduce a spatiotemporal self-supervised learning-based multiobjective weighted traffic flow prediction (SMWTP) method to achieve high-accuracy traffic flow prediction. Rigorous security analysis proves that our scheme satisfies differential privacy requirements. Experimental results on four real-world datasets show that our TFLST scheme reduces prediction errors by 6.21% compared to state-of-the-art methods, effectively balancing data privacy and utility.

The morphological diversity, referring to the variations in traffic network topologies defined in this paper, often emerges and brings difficulties in successfully transferring a pre-trained prediction model from one traffic network to another. Moreover, most existing research primarily assumes that traffic data in source and target networks follow independent and identically distributed (i.i.d.) patterns, which is usually not consistent with real-world situations, particularly when considering morphological diversity. For this inconsistency, many efforts have been made, but they mainly concentrate on temporal aspects, which significantly differ from traffic prediction due to spatial and temporal correlations among road segments, influenced by variations in road topology and traffic behavior. This paper introduces a causality-based spatiotemporal out-of-distribution (OOD) generalization method, which is adaptable to most GNNs for diverse, large-scale, dynamic traffic systems with zero-shot. Furthermore, to enhance the generalization and adaptability of the proposed method, we introduce graph matching and equal-sized graph partitioning to alleviate spatial shift between the source and target traffic networks, reduce and align the scale of the networks. Experiments carried out on traffic flow datasets demonstrate that our method significantly improves the performance of various GNN-based traffic predictors in the situation of morphological diversity, achieving a maximum reduction in MAE of 33.08%. Compared to other OOD-driven baselines, our approach also shows a notable improvement, with up to a 40.58% decrease in MAE.

The representative k-median problem generalizes the classical clustering formulations in that it partitions the data points into several disjoint demographic groups and poses a lower-bound constraint on the number of opened facilities from each group, such that all the groups are fairly represented by the opened facilities. Due to its simplicity, the local-search heuristic that optimizes an initial solution by iteratively swapping at most a constant number of closed facilities for the same number of opened ones (denoted by the O(1)-swap heuristic) has been frequently used in the representative k-median problem. Unfortunately, despite its good performance exhibited in experiments, whether the O(1)-swap heuristic has provable approximation guarantees for the case where the number of groups is more than 2 remains an open question for a long time. As an answer to this question, we show that the O(1)-swap heuristic (1) is guaranteed to yield a constant-factor approximation solution if the number of groups is a constant, and (2) has an unbounded approximation ratio otherwise. Our main technical contribution is a new approach for theoretically analyzing local-search heuristics, which derives the approximation ratio of the O(1)-swap heuristic via linearly combining the increased clustering costs induced by a set of hierarchically organized swaps.

The network load balancing mechanism plays a pivotal role in enhancing transmission performance in modern cloud data centers. Conventional flowlet-based approaches at host side offer a balance between performance and deployment simplicity. However, their passive load balancing strategy restricts rerouting opportunities, and lacks precision in congestion detection as it necessitates at least one round-trip time (RTT) to acquire end-to-end congestion feedback. To overcome the performance loss caused by the above limitations, we propose BurstLoader, an enhanced flowlet-based mechanism that adapts to varying traffic burst intensities and improves congestion detection accuracy. BurstLoader proactively reroutes congested flows when no new flowlets are detected, while simultaneously avoiding the rerouting of flowlets that are in good transmission states. Furthermore, BurstLoader incorporates delay and its gradient for a more nuanced and precise congestion detection. The extensive experiments demonstrate that BurstLoader achieves a significant reduction in flow completion time (FCT) by up to 48% compared to other flowlet-based solutions deployed at the end host, while maintaining competitive performance even against schemes that require custom switches under realistic workloads.

The alignment of Image Quality Assessment (IQA) models with diverse human preferences remains a challenge, owing to the variability in preferences for different types of visual content, including user-generated content and AI-Generated Content (AIGC), etc. Despite the significant success of existing IQA methods in assessing specific visual content by leveraging knowledge from pre-trained models, the intricate factors impacting final ratings and the specially designed network architecture of these methods result in gaps in their ability to accurately capture human preferences for novel visual content. To address this issue, we propose Align-IQA, a novel framework that aims to generate visual quality scores aligned with diverse human preferences for various types of visual content. Align-IQA contains two key designs: (1) A customizable quality-aware guidance injection module. By injecting specializable quality-aware prior knowledge into general-purpose pre-trained models, the proposed module guides the acquisition of quality-aware features and allows for various adjustments of features to be consistent with diverse human preferences for different types of visual content. (2) A multi-scale feature aggregation module. By simulating the multi-scale mechanism in the human visual system, the proposed module enables the extraction of a more comprehensive representation of quality-aware features from the human perception perspective. Extensive experimental results demonstrate that Align-IQA achieves better or comparable performance to State-Of-The-Art (SOTA) methods. Notably, Align-IQA outperforms the previous best results on AIGC datasets, achieving Pearson's Linear Correlation Coefficients (PLCCs) of 0.890 (+3.73%) on AGIQA-1K and 0.924 (+1.99%) on AGIQA-3K. Additionally, Align-IQA reduces training parameters by 72.26% and inference overhead by 78.12%, while maintaining SOTA performance.

Fair-range clustering extends classical clustering formulations by associating each data point with one or more demographic labels. It imposes lower and upper bound constraints on the number of facilities opened for each label, ensuring fair representation of all demographic groups by the selected facilities. In this paper we focus on the fair-range $k$-median and $k$-means problems in Euclidean spaces. We give $(1+\varepsilon)$-approximation algorithms with fixed-parameter tractable running times for both problems, parameterized by the numbers of opened facilities and demographic labels. For Euclidean metrics, these are the first parameterized approximation schemes for the problems, improving upon the previously known $O(1)$-approximation ratios given by Thejaswi et al. (KDD 2022).

In a radar system, clutter means any echoes which are not scattered by the wanted target. Usually, the radar clutter map stores an average level for each point or cell in the range-azimuth coordinates as the reference value. A target is then detected in a range-azimuth region if the new echo value in that region exceeds the average background level. In visual computing domain, background model is employed for foreground segmentation, motion detection, salient feature detection, etc. A few kinds of background models are built on each pixel of the sequential images, including the recently popular non-parametric model. In this paper, we proposes a non-parametric background model to implement the radar clutter map. A set of intensity values, which are selected in the past in each pixel location, are stored as the initial clutter model. Then, the new value of a pixel is classified as foreground stemming from a moving target, if the value was stronger than those of the reference samples in the recorded set Clutter model updating is based on randomly choosing in temporal and substituting background pixel values in spatial. Proposed model is proved to be efficient and effective in a moving vehicle detecting application. Also it is compared to a broadly used clutter map method which employs averaging in temporal.

In civil engineering, usually the methods used to estimate the thickness of thin pavements consider flat interfaces for simplification. In this paper, the roughness of the surfaces is taken into account. First, the amplitudes of the first two echoes from the rough thin pavement are calculated from a rigorous electromagnetic method, the PILE method. A comparison is then made with the flat interface case, and their differences in the electromagnetic backscattering are highlighted. Eventually, the influence of the pavement roughness on the pavement thickness estimation is investigated by using the Maximum Likelihood Method.