Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling graph-structured data, particularly under the assumption of homophily, where connected nodes share similar attributes or class labels. However, many real-world networks exhibit heterophily, leading to the suboptimal performance of conventional GNNs. While existing heterophily-aware models primarily address feature and class differences between central and neighboring nodes, we identify a critical yet underexplored challenge: class disparities in the neighborhoods of bridge nodes—nodes that connect disparate classes. Through theoretical analysis, we demonstrate how neighborhood differences around bridge nodes increase classification difficulty. To tackle this, we propose Bridge Breaking Graph Neural Network (BBGNN), a novel approach that explicitly mitigates performance degradation in these critical regions. We introduce a bridge ratio metric to identify bridge nodes without requiring label information and design a bridge-breaking aggregation mechanism to counteract excessive smoothing in these regions. Extensive experiments across multiple benchmark datasets validate the effectiveness of BBGNN, significantly improving GNN performance in bridge node regions.

Multi-view Graph Clustering (MGC) is a crucial approach for uncovering complex data structures by leveraging multiple perspectives of data. However, existing MGC methods face two key challenges: (1) limitations in graph structure that neglect long-range dependencies, and (2) overlooking the view-cluster local structure when mining view discrepancies. To address these issues, we propose a Multi-view Graph Clustering approach based on Dual View-Cluster-Order Interactivity (DVCOI-MGC). This approach consists of three modules: (1) Multi-View Multi-Order Graph Construction, where high-order graphs are generated using matrix exponentiation to capture long-range dependencies; (2) Dual View-Cluster-Order Interactivity, which utilizes a discrete graph cut model to separately learn order-specific and view-specific clustering results from the sets of order-specific multi-view graphs and view-specific multi-order graphs, with a separate View-Cluster-Order tensor weight for each learning direction; and (3) Bidirectional Truncation Consistency Learning, which applies a sparse boolean weight vector to locally select and integrate clustering results while preserving both the view-cluster and order-cluster local structures. Additionally, we introduce an efficient iterative optimization method to solve the discrete graph cut problem and provide a theoretical analysis of its convergence and computational complexity. Extensive experiments on 8 real-world datasets demonstrate that our approach significantly improves clustering performance over 11 state-of-the-art methods.

Brain network analysis plays a crucial role in identifying distinctive patterns associated with neurological disorders. Functional magnetic resonance imaging (fMRI) enables the construction of brain networks by analyzing correlations in blood-oxygen-level-dependent (BOLD) signals across different brain regions, known as regions of interest (ROIs). These networks are typically constructed using atlases that parcellate the brain based on various hypotheses of functional and anatomical divisions. However, there is no standard atlas for brain network classification, leading to limitations in detecting abnormalities in disorders. Recent methods leveraging multiple atlases fail to ensure consistency across atlases and lack effective ROI-level information exchange, limiting their efficacy. To address these challenges, we propose the Atlas-Integrated Distillation and Fusion network (AIDFusion), a novel framework designed to enhance brain network classification using fMRI data. AIDFusion introduces a disentangle Transformer to filter out inconsistent atlas-specific information and distill meaningful cross-atlas connections. Additionally, it enforces subject- and population-level consistency constraints to improve cross-atlas coherence. To further enhance feature integration, AIDFusion incorporates an inter-atlas message-passing mechanism that facilitates the fusion of complementary information across brain regions. We evaluate AIDFusion on four resting-state fMRI datasets encompassing different neurological disorders. Experimental results demonstrate its superior classification performance and computational efficiency compared to state-of-the-art methods. Furthermore, a case study highlights AIDFusion's ability to extract interpretable patterns that align with established neuroscience findings, reinforcing its potential as a robust tool for multi-atlas brain network analysis.

In neuroscience, identifying distinct patterns linked to neurological disorders, such as Alzheimer's and Autism, is critical for early diagnosis and effective intervention. Graph Neural Networks (GNNs) have shown promising in analyzing brain networks, but there are two major challenges in using GNNs: (1) distribution shifts in multi-site brain network data, leading to poor Out-of-Distribution (OOD) generalization, and (2) limited interpretability in identifying key brain regions critical to neurological disorders. Existing graph OOD methods, while effective in other domains, struggle with the unique characteristics of brain networks. To bridge these gaps, we introduce BrainOOD, a novel framework tailored for brain networks that enhances GNNs' OOD generalization and interpretability. BrainOOD framework consists of a feature selector and a structure extractor, which incorporates various auxiliary losses including an improved Graph Information Bottleneck (GIB) objective to recover causal subgraphs. By aligning structure selection across brain networks and filtering noisy features, BrainOOD offers reliable interpretations of critical brain regions. Our approach outperforms 16 existing methods and improves generalization to OOD subjects by up to 8.5%. Case studies highlight the scientific validity of the patterns extracted, which aligns with the findings in known neuroscience literature. We also propose the first OOD brain network benchmark, which provides a foundation for future research in this field. Our code is available at https://github.com/AngusMonroe/BrainOOD.

As multi-core processor technology advances and integration levels increase, effective chip temperature management significantly impacts performance and energy efficiency. However, in high power environments, relying on traditional dynamic thermal management methods (such as adjusting voltage and frequency) is no longer sufficient to effectively control and regulate the temperature of processors. This paper introduces a reinforcement learning modeling approach based on a core thermal model, which combines a more accurate processor state model with reinforcement learning techniques. It also utilizes an adaptive dueling DQN architecture, which helps agents learn more effective thermal-aware task scheduling during the training process. Compared to other methods, this approach reduces the average and peak temperatures by at least 2.06°C and 2.47°C respectively. Additionally, under stricter time constraints, processor performance is maintained while reducing core temperature.

The dark silicon issue is a significant challenge faced by chip manufacturers today, requiring them to find ways to enhance the performance of systems with limited power consumption. This necessitates the implementation of a power distribution method to control the system’s power usage while operating within thermal safety limits. However, due to the complex nature of heterogeneous systems, there are currently limited solutions available for effectively managing the power budgeting problem in such systems. This paper presents a simple and effective power budgeting method called Boundary Search-based Power Budgeting for heterogeneous systems (BSP). Under steady-state conditions, BSP divides the original cores into thermal spots of equal size based on the side lengths of the cores. By transforming the heterogeneous system into a homogeneous system in this way, we then apply our composite power budgeting method to the partitioned system, thus achieving power budgeting for the heterogeneous system. Experiments show that BSP has simplified the heterogeneous system and maximized the power budget while ensuring system performance.

To address the challenges posed by lighting variations and fruit occlusion in open orchard environments, which significantly affect the performance of apple-harvesting robots, this study proposes an apple detection method based on the fusion of infrared thermal images and visible-light images. Firstly, An edge feature-based registration technique was employed to achieve precise alignment of infrared and visible-light images. Subsequently, an improved YOLOv8s model integrated with the SeAFusion framework was utilized to facilitate efficient apple detection. Experimental results revealed that the proposed method achieved 94.9% mean accuracy and 89.5% mean recall across diverse illumination scenarios (normal/ strong/ backlight), surpassing visible-light-only detection by 0.6%, 4.8%, and 3.5% in apple count accuracy under respective conditions. The proposed method established a robust framework for vision-based harvesting robots, significantly improving operational reliability in complex orchard environments and providing technical foundations for scalable agricultural automation.

Graph Convolutional Networks (GCNs) are predominantly tailored for graphs displaying homophily, where similar nodes connect, but often fail on heterophilic graphs. The strategy of adopting distinct approaches to learn from homophilic and heterophilic components in node-level tasks has been widely discussed and proven effective both theoretically and experimentally. However, in graph-level tasks, research on this topic remains notably scarce. Addressing this gap, our research conducts an analysis on graphs with nodes' category ID available, distinguishing intra-category and inter-category components as embodiment of homophily and heterophily, respectively. We find while GCNs excel at extracting information within categories, they frequently capture noise from inter-category components. Consequently, it is crucial to employ distinct learning strategies for intra- and inter-category elements. To alleviate this problem, we separately learn the intra- and inter-category parts by a combination of an intra-category convolution (IntraNet) and an inter-category high-pass graph convolution (InterNet). Our IntraNet is supported by sophisticated graph preprocessing steps and a novel category-based graph readout function. For the InterNet, we utilize a high-pass filter to amplify the node disparities, enhancing the recognition of details in the high-frequency components. The proposed approach, DivGNN, combines the IntraNet and InterNet with a gated mechanism and substantially improves classification performance on graph-level tasks, surpassing traditional GNN baselines in effectiveness.

Pomegranate harvesting remains a challenging task due to the fruit's tough stem, dense canopy, and sensitivity to mechanical damage. Traditional harvesting robots rely on vision-based stem localization, which increases computational complexity and reduces robustness in unstructured orchard environments. This paper presents a dual-shear ring end-effector designed to eliminate the need for precise stem detection, utilizing a self-locking shear mechanism that allows the stem to naturally align between the cutting blades. The system integrates a vision-assisted robotic manipulator for fruit detection and a torque regulation mechanism for optimized cutting force application. Experimental validation demonstrates a success rate of over 90% for stems up to 8 mm in diameter and robust performance even under partial and full occlusion conditions. The results confirm that the proposed system achieves efficient, adaptable, and damage-free harvesting, providing a viable solution for autonomous pomegranate harvesting.

Feature selection plays an important role in a wide range of applications. Most sparsity-based feature selection methods solve a relaxed$\ell _{2,p}$-norm ($0 \lt p \leq 1$) regularized problem, which often results in a sub-optimal feature subset and requires extensive effort to tune regularization parameters. Optimizing the non-convex$\ell _{2,0}$-norm constrained problem remains an open challenge. Existing optimization algorithms for solving the$\ell _{2,0}$-norm constrained problem often rely on specific data distribution assumptions and cannot guarantee global convergence. In this article, we propose an unsupervised discriminative feature selection method using$\ell _{2,0}$-norm constrained sparse projection (SPDFS) to address these challenges. Specifically, building on the principle of supervised linear discriminant analysis, fuzzy membership learning and$\ell _{2,0}$-norm constrained projection learning are jointly performed to learn a feature-wise sparse projection for unsupervised discriminative feature selection. More importantly, we follow two optimization strategies to address the NP-hard nature of the problem: a non-iterative algorithm with a globally optimal solution is derived for a special case, and an iterative algorithm with both ascent property and approximation guarantee is employed for the general case. Additionally, we explore the relationship between our model and its potential variants. Experimental results on both synthetic and real-world datasets demonstrate the superiority of the proposed method over several state-of-the-art methods in data clustering and text classification tasks. The code is available at:https://github.com/xiadongcs/SPDFS.

Feature selection plays an important role in data analysis, yet traditional graph-based methods often produce suboptimal results. These methods typically follow a two-stage process: constructing a graph with data-to-data affinities or a bipartite graph with data-to-anchor affinities and independently selecting features based on their scores. In this article, a large-scale feature selection approach based on structured bipartite graph and row-sparse projection (RS2BLFS) is proposed to overcome this limitation. RS2BLFS integrates the construction of a structured bipartite graph consisting of c connected components into row-sparse projection learning with k nonzero rows. This integration allows for the joint selection of an optimal feature subset in an unsupervised manner. Notably, the c connected components of the structured bipartite graph correspond to c clusters, each with multiple subcluster centers. This feature makes RS2BLFS particularly effective for feature selection and clustering on nonspherical large-scale data. An algorithm with theoretical analysis is developed to solve the optimization problem involved in RS2BLFS. Experimental results on synthetic and real-world datasets confirm its effectiveness in feature selection tasks.

The key challenge of multi-view graph-based clustering is to mine consistent clustering structures from multiple graphs. Existing works seek clustering decisions from either multiple spectral embeddings or multiple affinity matrices, ignoring the interactions among them. To address this problem, we propose a Bidirectional Attentive Multi-view Clustering (BAMC) model to explore a consensus space w.r.t.spectral embedding and affinity matrix simultaneously, where they can promote each other to mine richer structural information from multiple graphs. BAMC is composed of a Spectral Embedding Learning (SEL) module, an Affinity Matrix Learning (AML) module, and a Bidirectional Attentive Clustering (BAC) module. SEL seeks consensus spectral embeddings by aligning the distributions of elements sampled from subspaces spanned by multiple spectral embeddings. AML learns a consensus affinity matrix from input affinity matrices. BAC guarantees consistency between the learned consensus spectral embeddings and the affinity matrix. To balance their effects, it also assigns adaptive weights to SEL and AML's objective functions. To solve the optimization problem involved in BAMC, we propose an efficient algorithm based on the Majority-Minimization framework with an ingenious surrogate problem. Extensive experiments on several synthetic and real-world datasets demonstrate the superb performance of BAMC.

The existing multiview clustering models learn a consistent low-dimensional embedding either from multiple feature matrices or multiple similarity matrices, which ignores the interaction between the two procedures and limits the improvement of clustering performance on multiview data. To address this issue, a bidirectional probabilistic subspaces approximation (BPSA) model is developed in this article to learn a consistently orthogonal embedding from multiple feature matrices and multiple similarity matrices simultaneously via the disturbed probabilistic subspace modeling and approximation. A skillful bidirectional fusion strategy is designed to guarantee the parameter-free property of the BPSA model. Two adaptively weighted learning mechanisms are introduced to ensure the inconsistencies among multiple views and the inconsistencies between bidirectional learning processes. To solve the optimization problem involved in the BPSA model, an iterative solver is derived, and a rigorous convergence guarantee is provided. Extensive experimental results on both toy and real-world datasets demonstrate that our BPSA model achieves state-of-the-art performance even if it is parameter-free.

This work focuses on the projected clustering problem. Specifically, an efficient and parameter-free clustering model, named discriminative projected clustering (DPC), is proposed for simultaneously low-dimensional and discriminative projection learning and clustering, from the perspective of least squares regression. The proposed DPC, a constrained regression model, aims at finding both a transformation matrix and a binary indicator matrix to minimize the sum-of-squares error. Theoretically, a significant conclusion is drawn and used to reveal the connection between DPC and linear discriminant analysis (LDA). Experimentally, experiments are conducted on both toy and real-world data to validate the effectiveness and efficiency of DPC; experiments are also conducted on hyperspectral images to further verify its practicability in real-world applications. Experimental results demonstrate that DPC achieves comparable or superior results to some state-of-the-art clustering methods.

In this article, we propose a novel feature selection approach, named unsupervised feature selection with constrained$\ell _{2,0}$-norm (row-sparsity constrained) and optimized graph (RSOGFS), which unifies feature selection and similarity matrix construction into a general framework instead of independently performing the two-stage process; thus, the similarity matrix preserving the local manifold structure of data can be determined adaptively. Unlike those sparse learning-based feature selection methods that can only solve the relaxation or approximation problems by introducing sparsity regularization term into the objective function, the proposed method directly tackles the original$\ell _{2,0}$-norm constrained problem to achieve group feature selection. Two optimization strategies are provided to solve the original sparse constrained problem. The convergence and approximation guarantees for the new algorithms are rigorously proved, and the computational complexity and parameter determination are theoretically analyzed. Experimental results on real-world data sets show that the proposed method for solving a nonconvex problem is superior to the state of the arts for solving the relaxed or approximate convex problems.

Finding a consensus embedding from multiple views is the mainstream task in multiview graph-based clustering, in which the key problem is to handle the inconsistence among multiple views. In this article, we consider clustering effectiveness and practical applicability collectively, and propose a parameter-free model to alleviate the inconsistence of multiple views cleverly. To be specific, the proposed model considers the diversities of multiple views as two-layers. The first layer considers the inconsistence among different features of each view and the second layer considers linking the preembeddings of multiple views attentively. By this way, a consensus embedding can be learned via kernel method effectively and the whole learning procedure is parameter-free. To solve the optimization problem involved in the proposed model, we propose an alternative algorithm which is efficient and easy to implement in practice. In the experiments, we evaluate the proposed model on synthetic and real datasets and the experimental results demonstrate its effectiveness.

In this paper, we propose a novel approach called dependence-guided multi-view clustering (DGMC). Our model enhances the dependence between unified embedding learning and clustering, as well as promotes the dependence between unified embedding and embedding of each view. Specifically, DGMC learns a unified embedding and partitions data in a joint fashion, thus the clustering results can be directly obtained. A kernel dependence measure is employed to learn a unified embedding by forcing it to be close to different views, thus the complex dependence among different views can be captured. Moreover, an implicit-weight learning mechanism is provided to ensure the diversity of different views. An efficient algorithm with rigorous convergence analysis is derived to solve the proposed model. Experimental results demonstrate the advantages of the proposed method over the state of the arts on real-world datasets.

This paper explores a succinct kernel model for Group-Sparse Projections Learning (GSPL), to handle multiview feature selection task completely. Compared to previous works, our model has the following useful properties: 1) Strictness: GSPL innovatively learns group-sparse projections strictly on multiview data via ‘2;0-norm constraint, which is different with previous works that encourage group-sparse projections softly. 2) Adaptivity: In GSPL model, when the total number of selected features is given, the numbers of selected features of different views can be determined adaptively, which avoids artificial settings. Besides, GSPL can capture the differences among multiple views adaptively, which handles the inconsistent problem among different views. 3) Succinctness: Except for the intrinsic parameters of projection-based feature selection task, GSPL does not bring extra parameters, which guarantees the applicability in practice. To solve the optimization problem involved in GSPL, a novel iterative algorithm is proposed with rigorously theoretical guarantees. Experimental results demonstrate the superb performance of GSPL on synthetic and real datasets.

Graph-based technique is widely used in projection, clustering, and classification tasks. In this article, we propose a novel and solid framework, named unsupervised projection with graph optimization (UPGO), for both dimensionality reduction and clustering. Different from the existing algorithms which treat graph construction and projection learning as two separate steps, UPGO unifies graph construction and projection learning into a general framework. It learns the graph similarity matrix adaptively based on the relationships among the low-dimensional representations. A constraint is introduced to the Laplacian matrix to learn a structured graph which contains the clustering structure, from which the clustering results can be obtained directly without requiring any postprocessing. The structured graph achieves the ideal neighbors assignment, based on which an optimal low-dimensional subspace can be learned. Moreover, we generalize UPGO to tackle the semisupervised case, namely semisupervised projection with graph optimization (SPGO), a framework for both dimensionality reduction and classification. An efficient algorithm is derived to optimize the proposed frameworks. We provide theoretical analysis about convergence analysis, computational complexity, and parameter determination. Experimental results on real-world data sets show the effectiveness of the proposed frameworks compared with the state-of-the-art algorithms. Results also confirm the generality of the proposed frameworks.

Load forecasting in short term is very important to economic dispatch and safety assessment of power system. Although existing load forecasting in short-term algorithms have reached required forecast accuracy, most of the forecasting models are black boxes and cannot be constructed to display mathematical models. At the same time, because of the abnormal load caused by the failure of the load data collection device, time synchronization, and malicious tampering, the accuracy of the existing load forecasting models is greatly reduced. To address these problems, this article proposes a Short-Term Load Forecasting algorithm by using Improved Gene Expression Programming and Abnormal Load Recognition (STLF-IGEP_ALR). First, the Recognition algorithm of Abnormal Load based on Probability Distribution and Cross Validation is proposed. By analyzing the probability distribution of rows and columns in load data, and using the probability distribution of rows and columns for cross-validation, misjudgment of normal load in abnormal load data can be better solved. Second, by designing strategies for adaptive generation of population parameters, individual evolution of populations and dynamic adjustment of genetic operation probability, an Improved Gene Expression Programming based on Evolutionary Parameter Optimization is proposed. Finally, the experimental results on two real load datasets and one open load dataset show that compared with the existing abnormal data detection algorithms, the algorithm proposed in this article have higher advantages in missing detection rate, false detection rate and precision rate, and STLF-IGEP_ALR is superior to other short-term load forecasting algorithms in terms of the convergence speed, MAE, MAPE, RSME, and R 2 .