Search Results (4,994)

Learning from heterogeneous graphs under the constraints of both data scarcity and data privacy presents a significant challenge. While graph prompt learning offers a pathway for efficient few-shot adaptation, and federated learning provides a paradigm for decentralized training, their direct integration for heterogeneous graphs is non-trivial due to structural complexity and the need for rigorous privacy guarantees. This paper proposes FedHGPrompt, a novel federated framework that bridges this gap through a cohesive architectural design. Our approach introduces a three-layer model: a unification layer employing dual templates to standardize heterogeneous graphs and tasks, an adaptation layer utilizing trainable dual prompts to steer a frozen pre-trained model for few-shot learning, and a privacy layer integrating a cryptographic secure aggregation protocol. This design ensures that the central server only accesses aggregated updates, thereby cryptographically safeguarding individual client data. Extensive evaluations on three real-world heterogeneous graph datasets (ACM, DBLP, and Freebase) demonstrate that FedHGPrompt achieves superior few-shot learning performance compared to existing federated graph learning baselines (including FedGCN, FedGAT, FedHAN, and FedGPL) while maintaining strong privacy assurances and practical communication efficiency. The framework establishes an effective approach for collaborative learning on distributed, heterogeneous graph data where privacy is paramount. Full article

Reconstructing original cusp dimensions in worn molars represents a fundamental challenge across dentistry, anthropology, and paleontology, as dental wear obscures critical morphological information. In this proof-of-concept study, we present a standardized machine learning pipeline for predicting original cusp height, specifically the horn tips of the enamel–dentine junction (EDJ), in worn lower molars using three-dimensional morphometric data from micro-computed tomography (micro-CT). We analyzed 40 permanent lower first (M1) and second (M2) molars from four hominin groups, systematically evaluated across three wear stages: original, moderately worn (worn1), and severely worn (worn2). Morphometric variables including height, area, and volume were quantified for each cusp, with Random Forest and multiple linear regression models developed individually and combined through ensemble methods. To mimic realistic reconstruction scenarios while preserving a known ground truth, models were trained on unworn specimens (original EDJ morphology) and tested on other teeth after digitally simulated wear (worn1 and worn2). Predictive performance was evaluated using root mean square error (RMSE) and coefficient of determination (R²). Our results demonstrate that under moderate wear (worn1), the ensemble models achieved normalized RMSE values between 11% and 17%. Absolute errors typically below 0.25 mm for most cusps, with R² values up to ~0.69. Performance deteriorated under severe wear (worn2), particularly for morphologically variable cusps such as the hypoconid and entoconid, but generally remained within sub-millimetric error ranges for several structures. Random Forests and linear models showed complementary strengths, and the ensemble generally offered the most stable performance across cusps and wear states. To enhance transparency and accessibility, we provide a comprehensive, user-friendly software pipeline including pre-trained models, automated prediction scripts, standardized data templates, and detailed documentation. This implementation allows researchers without advanced machine learning expertise to explore EDJ-based reconstruction from standard morphometric measurements in new datasets, while explicitly acknowledging the limitations imposed by our modest and taxonomically unbalanced sample. More broadly, the framework represents an initial step toward predicting complete crown morphology, including enamel thickness, in worn or damaged teeth. As such, it offers a validated methodological foundation for future developments in cusp and crown reconstruction in both clinical and evolutionary dental research. Full article

The widespread adoption of electric vehicles (EVs) has posed significant challenges to the security of distribution grid loads. To address issues such as increased grid load fluctuations, rising user charging costs, and rapid load surges around midnight caused by uncoordinated nighttime charging of household electric vehicles in communities, this paper first models electric vehicle charging behavior as a Markov Decision Process (MDP). By improving the state-space sampling mechanism, a continuous space mapping and a priority mechanism are designed to transform the charging scheduling problem into a continuous decision-making framework while optimizing the dynamic adjustment between state and action spaces. On this basis, to achieve synergistic load forecasting and charging scheduling decisions, a forecast-augmented deep reinforcement learning method integrating Gated Recurrent Unit and Twin Delayed Deep Deterministic Policy Gradient (GRU-TD3) is proposed. This method constructs a multi-objective reward function that comprehensively considers time-of-use electricity pricing, load stability, and user demands. The method also applies a single-objective pre-training phase and a model-specific importance-sampling strategy to improve learning efficiency and policy stability. Its effectiveness is verified through extensive comparative and ablation validation. The results show that our method outperforms several benchmarks. Specifically, compared to the Deep Deterministic Policy Gradient (DDPG) and Particle Swarm Optimization (PSO) algorithms, it reduces user costs by 11.7% and the load standard deviation by 12.9%. In contrast to uncoordinated charging strategies, it achieves a 42.5% reduction in user costs and a 20.3% decrease in load standard deviation. Moreover, relative to single-objective cost optimization approaches, the proposed algorithm effectively suppresses short-term load growth rates and mitigates the “midnight peak” phenomenon. Full article

The radiosensitivity of cancer patients determines the efficacy of radiotherapy, and patients with low radiosensitivity cannot benefit from radiotherapy. Therefore, accurately predicting radiosensitivity before treatment is essential for personalized and precise radiotherapy. However, most existing studies rely solely on genomic and clinical features, neglecting the tumor microenvironmental information embedded in histopathological images, which limits prediction accuracy. To address this issue, we propose Resfusion, a deep multimodal fusion framework that integrates patient-level gene expression profiles, clinical records, and histopathological images for tumor radiosensitivity prediction. Specifically, the pre-trained large-scale pathology model is used as an image encoder to extract global representations from whole-slide pathological image. Radiosensitivity-related genes are selected using an autoencoder combined with univariate Cox regression, while clinically relevant variables are manually curated. The three modalities are first concatenated and then refined through a self-attention-based module, which captures inter-feature dependencies within the fused representation and highlights complementary information across modalities. The model was evaluated using five-fold cross-validation on two common tumor datasets suitable for radiotherapy: the Breast Invasive Carcinoma (BRCA) dataset (282 patients in total, with each fold partitioned into 226 training samples and 56 validation samples) and the Head and Neck Squamous Cell Carcinoma (HNSC) dataset (200 patients in total, with each fold partitioned into 161 training samples and 39 validation samples). The average AUC values obtained from the five-fold cross-validation reached 76.83% and 79.49%, respectively. Experimental results demonstrate that the Resfusion model significantly outperforms unimodal methods and existing multimodal fusion methods, verifying its effectiveness in predicting the radiosensitivity of tumor patients. Full article

Deceptive and evolving conversations on online platforms threaten trust, security, and user safety, particularly when concept drift obscures malicious intent. Large Language Models (LLMs) offer strong natural language reasoning but remain unreliable in risk-sensitive scenarios due to contextual ambiguity and hallucinations. This article introduces a domain knowledge-enhanced Dual-LLM framework that integrates structured cues with pretrained models to improve fraud detection and drift classification. The proposed approach achieves 98% accuracy on benchmark datasets, significantly outperforming zero-shot LLMs and traditional classifiers. The results highlight how domain-grounded prompts enhance both accuracy and interpretability, offering a trustworthy path for applying LLMs in safety-critical applications. Beyond advancing the state of the art in fraud detection, this work has the potential to benefit domains such as cybersecurity, e-commerce, financial fraud prevention, and online content moderation. Full article

Conventional object detectors represent each object by a deterministic bounding box, regressing its center and size from RGB images. However, such discrete parameterization ignores the inherent uncertainty in object appearance and geometric projection, which can be more naturally modeled as a probabilistic density field. Recent works have introduced Gaussian-based formulations that treat objects as distributions rather than boxes, yet they remain limited to 2D images or require late fusion between image and depth modalities. In this paper, we propose a unified Gaussian-based framework for direct 3D object detection from RGB-D inputs. Our method is built upon a vision transformer backbone to effectively capture global context. Instead of separately embedding RGB and depth features or refining depth within region proposals, our method takes a full four-channel RGB-D tensor and predicts the mean and covariance of a 3D Gaussian distribution for each object in a single forward pass. We extend a pretrained vision transformer to accept four-channel inputs by augmenting the patch embedding layer while preserving ImageNet-learned representations. This formulation allows the detector to represent both object location and geometric uncertainty in 3D space. By optimizing divergence metrics such as the Kullback–Leibler or Bhattacharyya distances between predicted and target distributions, the network learns a physically consistent probabilistic representation of objects. Experimental results on the SUN RGB-D benchmark demonstrate that our approach achieves competitive performance compared to state-of-the-art point-cloud-based methods while offering uncertainty-aware and geometrically interpretable 3D detections. Full article

In nanometer integrated-circuit (IC) manufacturing, advanced technology scaling has intensified the effects of process variations on circuit reliability and performance. Random fluctuations in parameters such as threshold voltage, channel length, and oxide thickness further degrade design margins and increase the likelihood of functional failures. These variations often lead to rare circuit failure events, underscoring the importance of accurate yield estimation and robust design methodologies. Conventional Monte Carlo yield estimation is computationally infeasible as millions of simulations are required to capture failure events with extremely low probability. This paper presents a novel reliability-based circuit design optimization framework that leverages deep transfer learning to improve the efficiency of repeated yield analysis in optimization iterations. Based on pre-trained neural network models from prior design knowledge, we utilize model fine-tuning to accelerate importance sampling (IS) for yield estimation. To improve estimation accuracy, adversarial perturbations are introduced to calibrate uncertainty near the model decision boundary. Moreover, we propose a cascaded batch Bayesian optimization (CBBO) framework that incorporates a smart initialization strategy and a localized penalty mechanism, guiding the search process toward high-yield regions while satisfying nominal performance constraints. Experimental validation on SRAM circuits and amplifiers reveals that CBBO achieves a computational speedup of 2.02×–4.63× over state-of-the-art (SOTA) methods, without compromising accuracy and robustness. Full article

Extreme summarization generates very short summaries, typically a single sentence, answering the question “What is the document about?”. Although large language models perform well in text generation, fine-tuning them for summarization often requires substantial computational resources that are unavailable to many researchers. In this study, we present an effective method for instruction-tuning open decoder-only large language models under limited GPU resources. The proposed approach combines parameter-efficient fine-tuning techniques, such as Low-Rank Adaptation (LoRA), with quantization to reduce memory requirements, enabling training on a single consumer-grade GPU. We fine-tuned a pre-trained decoder-only model on the XSum dataset using an instruction-following format. Experimental results demonstrate that the proposed decoder-only approach achieves competitive performance on the XSum dataset under strict GPU memory constraints. On the full test set, the proposed 2G–1R pipeline attains ROUGE-1/2/L F1 scores of 46.0/22.0/37.0 and a BERTScore F1 of 0.917, outperforming the individual generator models in lexical overlap and semantic similarity. Evaluation was conducted using traditional overlap-based metrics (ROUGE) and semantic metrics, including BERTScore and G-Eval. While remaining competitive in ROUGE compared to strong encoder–decoder baselines, the pipeline consistently produces summaries with higher semantic quality. These findings demonstrate that large decoder-only language models can be efficiently fine-tuned for extreme summarization on limited consumer-grade hardware without sacrificing output quality. Full article

Speaker change detection (SCD) in long, multi-party meetings is essential for diarization, Automatic speech recognition (ASR), and summarization, and is now often performed in the space of pre-trained speech embeddings. However, unsupervised approaches remain dominant when timely labeled audio is scarce, and their behavior under a unified modeling setup is still not well understood. In this paper, we systematically compare two representative unsupervised approaches on the multi-talker audio meeting corpus: (i) a clustering-based pipeline that segments and clusters embeddings/features and scores boundaries via cluster changes and jump magnitude, and (ii) a multi-scale jump-based detector that measures embedding discontinuities at several window lengths and fuses them via temporal clustering and voting. Using a shared front-end and protocol, we vary the underlying features (ECAPA, WavLM, wav2vec 2.0, MFCC, and log-Mel) and test the model’s robustness under additive noise. The results show that embedding choice is crucial and that the two methods offer complementary trade-offs: the pipeline yields low false alarm rates but higher misses, while the multi-scale detector achieves relatively high recall at the cost of many false alarms. Full article

Deep learning models based on supervised learning rely heavily on large annotated datasets and particularly in the context of medical image segmentation, the requirement for pixel-level annotations makes the labeling process labor-intensive, time-consuming and expensive. To overcome these limitations, self-supervised learning (SSL) has emerged as a promising alternative that learns generalizable representations from unlabeled data; however, existing SSL frameworks often employ highly parameterized encoders that are computationally expensive and may lack robustness in label-scarce settings. In this work, we propose a scattering-based SSL framework that integrates Wavelet Scattering Networks (WSNs) and Parametric Scattering Networks (PSNs) into a Bootstrap Your Own Latent (BYOL) pretraining pipeline. By replacing the initial stages of the BYOL encoder with fixed or learnable scattering-based front-ends, the proposed method reduces the number of learnable parameters while embedding translation-invariant and small deformation-stable representations into the SSL pipeline. The pretrained encoders are transferred to a U-Net and fine-tuned for cardiac image segmentation on two datasets with different imaging modalities, namely, cardiac cine MRI (ACDC) and cardiac CT (CHD), under varying amounts of labeled data. Experimental results show that scattering-based SSL pretraining consistently improves segmentation performance over random initialization and ImageNet pretraining in low-label regimes, with particularly pronounced gains when only a few labeled patients are available. Notably, the PSN variant achieves improvements of 4.66% and 2.11% in average Dice score over standard BYOL with only 5 and 10 labeled patients, respectively, on the ACDC dataset. These results demonstrate that integrating mathematically grounded scattering representations into SSL pipelines provides a robust and data-efficient initialization strategy for cardiac image segmentation, particularly under limited annotation and domain shift. Full article

Background: Hip joint disorders exhibit diverse and overlapping radiological features, complicating early diagnosis and limiting the diagnostic value of single-modality imaging. Isolated imaging or clinical data may therefore inadequately represent disease-specific pathological characteristics. Methods: This retrospective study included 605 hip joints from Center A (2018–2024), comprising normal hips, osteoarthritis, osteonecrosis of the femoral head (ONFH), and femoroacetabular impingement (FAI). An independent cohort of 24 hips from Center B (2024–2025) was used for external validation. A multimodal deep learning framework was developed to jointly analyze radiographs, CT volumes, and clinical texts. Features were extracted using ResNet50, 3D-ResNet50, and a pretrained BERT model, followed by attention-based fusion for four-class classification. Results: The combined Clinical+X-ray+CT model achieved an AUC of 0.949 on the internal test set, outperforming all single-modality models. Improvements were consistently observed in accuracy, sensitivity, specificity, and decision curve analysis. Grad-CAM visualizations confirmed that the model attended to clinically relevant anatomical regions. Conclusions: Attention-based multimodal feature fusion substantially improves diagnostic performance for hip joint diseases, providing an interpretable and clinically applicable framework for early detection and precise classification in orthopedic imaging. Full article

Deep vision foundation models such as DINOv3 offer strong visual representation capacity, but their direct deployment in medical image segmentation remains difficult due to the limited availability of annotated clinical data and the computational cost of full fine-tuning. This study proposes an adaptation framework called StrDiSeg that integrates lightweight bottleneck adapters between selected transformer layers of DINOv3, enabling task-specific learning while preserving pretrained knowledge. An attention-enhanced U-Net decoder with multi-scale feature fusion further refines the representations. Experiments were performed on two publicly available ischemic stroke lesion segmentation datasets—AISD (Non Contrast CT) and ISLES22 (DWI). The proposed method achieved Dice scores of 0.516 on AISD and 0.824 on ISLES22, outperforming baseline models and demonstrating strong robustness across different clinical imaging modalities. These results indicate that adapter-based fine-tuning provides a practical and computationally efficient strategy for leveraging large pretrained vision models in medical image segmentation. Full article

Remaining useful life (RUL) prediction is central to predictive maintenance, but acquiring sufficient run-to-failure data remains challenging. To better exploit limited labeled data, this study investigates a pipeline combining an unsupervised autoencoder (AE) and supervised LSTM regression on the NASA C-MAPSS dataset. Building on an AE-LSTM baseline, we analyze how window size and batch size affect accuracy and training efficiency. Using the FD001 and FD004 subsets with training-capped RUL labels, we perform multi-seed experiments over a wide grid of window lengths and batch sizes. The AE is pre-trained on normalized sensor streams and reused as a feature extractor, while the LSTM head is trained with early stopping. Performance was assessed using RMSE, C-MAPSS score, and training time, reporting 95% confidence intervals. Results show that fine-tuning the encoder with a batch size of 128 yielded the best mean RMSE of 13.99 (FD001) and 28.67 (FD004). We obtained stable optimal window ranges (40–70 for FD001; 60–80 for FD004) and found that batch sizes of 64–256 offer the best accuracy–efficiency trade-off. These optimal ranges were further validated using Particle Swarm Optimization (PSO). These findings offer practical recommendations for tuning AE-LSTM-based RUL prediction models and demonstrate that performance remains stable within specific hyperparameter ranges. Full article

Prostate cancer is diagnosed through a comprehensive study of histopathology slides, which takes time and requires professional interpretation. To minimize this load, we developed a semi-supervised learning technique that combines transformer-based representation learning and a custom TransUNet classifier. To capture a wide range of morphological structures without manual annotation, our method pretrains DINOv2 on 10,000 unlabeled prostate tissue patches. After receiving the transformer-derived features, a bespoke CNN-based decoder uses residual upsampling and carefully constructed skip connections to merge data from many spatial scales. Expert pathologists identified only 20% of the patches in the whole dataset; the remaining unlabeled samples were contributed by using a consistency-driven learning method that promoted reliable predictions across various augmentations. The model received precision and recall scores of 91.81% and 89.02%, respectively, and an accuracy of 93.78% on an additional test set. These results exceed the performance of a conventional U-Net and a baseline encoder–decoder network. All things considered, the localized CNN (Convolutional Neural Network) decoding and global transformer attention provide a reliable method for prostate cancer classification in situations with little annotated data. Full article

Reversible protein phosphorylation is an important regulatory mechanism in cellular signalling and disease, regulated by the opposing actions of kinases and phosphatases. Modern computer methods predict kinase–substrate or phosphatase–substrate interactions in isolation and lack specificity for biological conditions, neglecting triadic regulation. We present SPINET-KSP, a multi-modal LLM–Graph foundation model engineered for the prediction of kinase–substrate–phosphatase (KSP) triads with contextual awareness. SPINET-KSP integrates high-confidence interactomes (SIGNOR, BioGRID, STRING), structural contacts obtained from AlphaFold3, ESM-3 sequence embeddings, and a 512-dimensional cell-state manifold with 1612 quantitative phosphoproteomic conditions. A heterogeneous KSP graph is examined utilising a cross-attention Graphormer with Reversible Triad Attention to mimic kinase–phosphatase antagonism. SPINET-KSP, pre-trained on 3.41 million validated phospho-sites utilising masked phosphorylation modelling and contrastive cell-state learning, achieves an AUROC of 0.852 for kinase-family classification (sensitivity 0.821, specificity 0.834, MCC 0.655) and a Pearson correlation coefficient of 0.712 for phospho-occupancy prediction. In distinct 2025 mass spectrometry datasets, it identifies 72% of acknowledged cancer-resistance triads within the top 10 rankings and uncovers 247 supplementary triads validated using orthogonal proteomics. SPINET-KSP is the first foundational model for simulating context-dependent reversible phosphorylation, enabling the targeting of dysregulated kinase-phosphatase pathways in diseases. Full article