Semantic scene completion simultaneously reconstructs the shapes of missing regions and predicts semantic labels for the entire 3D scene. Although point cloud-based methods are more efficient than voxel-based methods, existing point cloud-based approaches largely fail to fully leverage semantic information. To address this challenge, we propose a Prototype-Guided Transformer (ProtoFormer) that encodes semantic information into a set of semantic prototypes to guide the underlying Transformer for semantic scene completion. Specifically, we leverage semantic prototypes to enhance information from both geometric and semantic perspectives, and integrate the top-K attention mechanisms to guide scene completion and semantic awareness. Extensive qualitative and quantitative experimental results demonstrate that ProtoFormer outperforms state-of-the-art approaches with low complexity.

The primary goal of 3D point cloud completion is to reconstruct complete and high-resolution point clouds from incomplete and low-resolution inputs. While some recent approaches have achieved satisfactory completion performance by incorporating additional images, there remains room for improvement in fully exploiting and utilizing the rich geometric relation information contained in parts. To address this challenge, we propose a novel Semantic Guided Part Relation-aware Network (SGPRNet) for Point Cloud Completion. Its core innovation lies in establishing part semantic relations to guide the reconstruction of structurally consistent local geometries. Specifically, we utilize Large Multi-modal Models (LMMs) to automatically generate the specific text of 3D shape, which provides detailed geometric part relations descriptions. Building upon this, we design an Orthogonal Semantic Part Transfer (OSPT) module that learns transferable semantic relations between geometric parts. Subsequently, we develop a Semantic Geometric Relation-aware Transformer (SGRFormer) to progressively refine these semantic features, enhancing point cloud representation and guiding the generation of fine local structures. In addition, we establish a point-text pairs corpus, OmniObject3D-212/34 and Text-ViPC datasets based on existing OmniObject3D and ShapeNet-ViPC datasets, incorporating the specific text. Extensive experimental results demonstrate that our method outperforms existing state-of-the-art completion methods.

Graph Neural Networks (GNNs) demonstrate promising performance in data mining yet exhibit inherent vulnerabilities to adversarial attacks. Even imperceptible perturbations degrade model performance, seriously hindering the application of GNNs in reality. In recent years, adversarial defense methods based on model architecture have gained attention for their effectiveness. However, they exhibit limited effectiveness against emerging black-box influence maximization attacks (IMAs), which aim to maximize the spread of feature perturbations through a group of influential nodes. This may leave a potential risk in real-world applications. To address this issue, we propose a Graph Adversarial Defense method based on the Hilbert-Schmidt Independence Criterion (HSIC-GAD). Specifically, the proposed method leverages hidden representations to capture the dependence between preprocessed node features and label information. On this basis, we design a regularizer that simultaneously preserves the most relevant information for downstream tasks while filtering out adversarial perturbations from the input data. A simple theoretical analysis shows that the HSIC regularizer can reduce the sensitivity of the model to adversarial inputs. Additionally, it exhibits strong universality, consistently enhancing the adversarial robustness of diverse models. Extensive experiments on real-world datasets demonstrate that HSIC-GAD outperforms state-of-the-art defense methods against IMAs.

Graph Transformers (GTs) have shown great potential in graph representation learning over the past few years. In spite of their promising performance on small graphs, how to develop a scalable and powerful architecture still remains to be explored. While some of the existing works devote to designing linear attention mechanisms, the expressiveness is confined by their smooth attention score distributions. Another impact factor of expressiveness is the inductive bias. Unfortunately, GTs generally lack strong graph-specific inductive bias, which leads to failure in capturing long-range hierarchical structures or community structures. To address the issues above, we develop a Scalable and Comprehensive Graph Transformer (SCGT). Specifically, we leverage a Focused Graph Linear Attention (FGLA) to generate a sharp distribution of attention scores. In addition, we design a Comprehensive Positional Encoding (CPE) to capture comprehensive awareness of the original node-level features. Extensive empirical results show that SCGT achieves highly competitive performance with decent efficiency on 12 datasets. Theoretical analysis demonstrates the expressiveness of our proposed method.

Cold-start sequential recommendation, where user interaction histories are sparse or minimal, remains a significant challenge in recommendation systems. Current meta-learning-based approaches rely heavily on the interaction histories of regular users to construct meta-tasks, aiming to acquire prior knowledge for cold-start adaptation. However, these methods often fail to account for preference discrepancies between regular and cold-start users, leading to biased preference modeling and suboptimal recommendations. To address this issue, we propose a novel counterfactual task-augmented meta-learning method for cold-start sequential recommendations. Our approach intervenes in user interaction histories to create counterfactual sequences that simulate potential but unrealized user behaviors, establishing counterfactual tasks within a meta-learning framework. Additionally, we aggregate meta-path neighbors to uncover latent relationships between items, enabling more detailed and accurate modeling of user preferences. Moreover, by integrating real and counterfactual task losses, we jointly optimize the model through a combination of global and local updates, enhancing its adaptability to cold-start scenarios. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art techniques, achieving superior results in cold-start sequential recommendation tasks.

Graph Neural Networks are powerful tools for modeling graph-structured data but their interpretability remains a significant challenge. Existing model-agnostic GNN explainers aim to identify critical subgraphs or node features relevant to task predictions but often rely on GNN predictions for supervision, lacking ground-truth explanations. This limitation can introduce biases, causing explanations to fail in accurately reflecting the GNN's decision-making processes. To address this, we propose a novel explainer for GNNs with graph segmentation and contrastive learning. Our model introduces a graph segmentation learning module to divide the input graph into explanatory and redundant subgraphs. Next, we implement edge perturbation to augment these subgraphs, generating multiple positive and negative pairs for contrastive learning between explanatory and redundant subgraphs. Finally, we develop a contrastive learning module to guide the learning of explanatory and redundant subgraphs by pulling positive pairs with the same explanatory subgraphs closer while pushing negative pairs with different explanatory subgraphs far away. This approach allows for a clearer distinction of critical subgraphs, enhancing the fidelity of the explanations. We conducted extensive experiments on graph classification and node classification tasks, demonstrating the effectiveness of the proposed method.

Graph contrastive learning (GCL) has become a hot topic in the field of graph representaion learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation techniques to generate multiple views and positive/negative pairs, both of which greatly influence the performance. Unfortunately, commonly used random augmentations may disturb the underlying semantics of graphs. Moreover, traditional GNNs, a type of widely employed encoders in GCL, are inevitably confronted with over-smoothing and over-squashing problems. To address these issues, we propose GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning (GTCA), which inherits the advantages of both GNN and Transformer, incorporating graph topology to obtain comprehensive graph representations. Theoretical analysis verifies the trustworthiness of the proposed method. Extensive experiments on benchmark datasets demonstrate state-of-the-art empirical performance.

Deep learning has achieved remarkable success in supervised image classification tasks, which relies on a large number of labeled samples for each class. Recently, zero-shot learning has garnered significant attention, which aims to recognize unseen classes using only training samples from seen classes. To bridge the gap between images and classes, class semantic attributes are introduced, making the alignment between image and class semantic attributes critical to zero-shot learning. However, existing methods often struggle to accurately focus on the image regions corresponding to individual class semantic attributes and tend to overlook the relations between different regions of an image, leading to poor alignment. To address these challenges, we propose a class semantic attribute perception guided zero-shot learning method. Specifically, we achieve coarse-grained perception of class semantic attributes across the entire image through contrastive semantic learning. Additionally, we attain fine-grained perception of individual class semantic attributes within image regions via region partitioning-based attribute alignment, which fully considers the relations between different regions of an image. By integrating these two processes into a unified network, we achieve multi-grained class semantic attribute perception, thereby enhancing the alignment between images and class semantic attributes. We validate the effectiveness of the proposed method on zero-shot learning benchmark data sets.

Classification is a cornerstone of machine learning research. Most of the existing classifiers assume that the concepts corresponding to classes can be precisely defined. This notion diverges from the widely accepted understanding in cognitive science, which posits that real-world concepts are often inherently ambiguous. To bridge this big gap, we propose a Human Cognition-Inspired Hierarchical Fuzzy Learning Machine (HC-HFLM), which leverages a novel hierarchical alignment loss to integrate rich class knowledge from human knowledge system into learning process. We further theoretically prove that minimizing this loss can align the hierarchical structure derived from data with those contained in class knowledge, resulting in clear semantics and high interpretability. Systematic experiments verify that the proposed method can achieve significant gains in interpretability and generalization performance.

Graph contrastive learning has attracted great interest as a dominant and promising self-supervised representation learning approach in recent years. While existing works follow the basic principle of pulling positive pairs closer and pushing negative pairs far away, they still suffer from several critical problems, such as the underlying semantic disturbance brought by augmentation strategies, the failure of GCN in capturing long-range dependence, rigidness and inefficiency of node sampling techniques. To address these issues, we propose Manifold Learning Inspired Lightweight Graph Contrastive Learning (ML$^2$-GCL), which inherits the merits of both manifold learning and GCN. ML$^2$-GCL avoids the potential risks of semantic disturbance with only one single view. It achieves global nonlinear structure recovery from locally linear fits, which can make up for the defects of GCN. The most amazing advantage is about the lightweight due to its closed-form solution of positive pairs weights and removal of pairwise distances calculation. Theoretical analysis proves the existence of the optimal closed-form solution. Extensive empirical results on various benchmarks and evaluation protocols demonstrate effectiveness and lightweight of ML$^2$-GCL. We release the code at https://github.com/a-hou/ML2-GCL.

Dynamic graph representation learning using Spiking Neural Networks (SNNs) exploits the temporal spiking behavior of neurons, offering advantages in capturing the temporal evolution and sparsity of dynamic graphs. However, existing SNN-based methods often fail to effectively capture the impact of latency in information propagation on node representations. To address this, we propose Delay-DSGN, a dynamic spiking graph neural network incorporating a learnable delay mechanism. By leveraging synaptic plasticity, the model dynamically adjusts connection weights and propagation speeds, enhancing temporal correlations and enabling historical data to influence future representations. Specifically, we introduce a Gaussian delay kernel into the neighborhood aggregation process at each time step, adaptively delaying historical information to future time steps and mitigating information forgetting. Experiments on three large-scale dynamic graph datasets demonstrate that Delay-DSGN outperforms eight state-of-the-art methods, achieving the best results in node classification tasks. We also theoretically derive the constraint conditions between the Gaussian kernel’s standard deviation and size, ensuring stable training and preventing gradient explosion and vanishing issues.

Graph Neural Ordinary Differential Equations (GODE) integrate the Variational Autoencoder (VAE) framework with differential equations, effectively modeling latent space uncertainty and continuous dynamics, excelling in graph data evolution and incompleteness. However, existing GODE face challenges in capturing time-varying relationships and nonlinear node state evolution, which limits their ability to model complex dynamic graphs. To address these issues, we propose the ControlSynth Graph ODE (CSG-ODE). In the VAE encoding phase, CSG-ODE introduces an information transmission-based inter-node importance weighting mechanism, integrating it with latent correlations to guide adaptive graph convolutional recurrent networks for temporal node embedding. During decoding, CSG-ODE employs ODE to model node dynamics, capturing nonlinear evolution through sub-networks with nonlinear activations. For scenarios or prediction tasks that require stability, we extend CSG-ODE to stable CSG-ODE (SCSG-ODE) by constraining weight matrices to learnable anti-symmetric forms, theoretically ensuring enhanced stability. Experiments on traffic, motion capture, and simulated physical systems datasets demonstrate that CSG-ODE outperforms state-of-the-art GODE, while SCSG-ODE achieves both superior performance and optimal stability.

Open-world semi-supervised learning (OWSSL) aims to recognize both known and unknown classes, but the labeled samples only cover the known classes. Existing OWSSL methods primarily represent classes as symbolic variables, which ignore the rich internal semantic information associated with the classes and thus hampers their ability to recognize unknown classes. Recent studies incorporate textual descriptions of classes to facilitate training, but these methods overlook the class semantic correlations, which constrains their effectiveness in recognizing unknown classes. To address these issues, we propose a novel OWSSL method. Our method fine-tunes only the image encoder during training while keeping the text encoder frozen, thereby preserving the rich semantic correlations learned during the pre-training phase. Furthermore, we employ a semantic margin to extract class semantic correlations from textual descriptions, which are then utilized in enhancing image representation discriminability. Experimental results across multiple datasets demonstrate that our method significantly outperforms representative OWSSL methods in the recognition of both known and unknown classes.

Multi-modal point cloud completion, which utilizes a complete image and a partial point cloud as input, is a crucial task in 3D computer vision. Previous methods commonly employ a cross-attention mechanism to fuse point clouds and images. However, these approaches often fail to fully leverage image information and overlook the intrinsic geometric details of point clouds that could complement the image modality. To address these challenges, we propose an interleaved attention enhanced Transformer (IAET) with three main components, i.e., token embedding, bidirectional token supplement, and coarse-to-fine decoding. IAET incorporates a novel interleaved attention mechanism to enable bidirectional information supplementation between the point cloud and image modalities. Additionally, to maximize the use of the supplemented image information, we introduce a view-guided upsampling module that leverages image tokens as queries to guide the generation of detailed point cloud structures. Extensive experiments demonstrate the effectiveness of IAET, highlighting its state-of-the-art performance on multi-modal point cloud completion benchmarks in various scenarios. The source code is freely accessible at https://github.com/doldolOuO/IAET.

The success of current graph contrastive learning methods largely relies on the choice of data augmentation and contrastive objectives. However, most existing methods tend to optimize these two components independently, neglecting their potential interplay, which leads to suboptimal quality of the learned embeddings. To address this issue, we propose Uncertainty-guided Graph Contrastive Learning (UGCL) from a unified perspective. The core of our method is the introduction of sample uncertainty, a critical metric that quantifies the degree of class ambiguity within individual samples. On this basis, we design a novel multi-scale data augmentation strategy and a weighted graph contrastive loss function, both of which significantly enhance the quality of embeddings. Theoretically, we demonstrate that UGCL can coordinate overall optimization objectives through uncertainty, and through experiments, we show that it improves the performance of tasks such as node classification, node clustering, and link prediction, thereby verifying the effectiveness of our method.

Hypergraphs offer a natural paradigm for modeling complex systems with multi-way interactions. Hypergraph neural networks (HGNNs) have demonstrated remarkable success in learning from such higher-order relational data. While such higher-order modeling enhances relational reasoning, the effectiveness of hypergraph learning remains bottlenecked by two persistent challenges: the scarcity of labeled data inherent to complex systems, and the vulnerability to structural noise in real-world interaction patterns. Traditional data augmentation methods, though successful in Euclidean and graph-structured domains, struggle to preserve the intricate balance between node features and hyperedge semantics, often disrupting the very group-wise interactions that define hypergraph value. To bridge this gap, we present HyperMixup, a hypergraph-aware augmentation framework that preserves higher-order interaction patterns through structure-guided feature mixing. Specifically, HyperMixup contains three critical components: 1) Structure-aware node pairing guided by joint feature-hyperedge similarity metrics, 2) Context-enhanced hierarchical mixing that preserves hyperedge semantics through dual-level feature fusion, and 3) Adaptive topology reconstruction mechanisms that maintain hypergraph consistency while enabling controlled diversity expansion. Theoretically, we establish that our method induces hypergraph-specific regularization effects through gradient alignment with hyperedge covariance structures, while providing robustness guarantees against combined node-hyperedge perturbations. Comprehensive experiments across diverse hypergraph learning tasks demonstrate consistent performance improvements over state-of-the-art baselines, with particular effectiveness in low-label regimes. The proposed framework advances hypergraph representation learning by unifying data augmentation with higher-order topological constraints, offering both practical utility and theoretical insights for relational machine learning.

The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or positional and structural encodings. Despite making some progress, existing works tend to overlook external information of graphs, specifically the correlation between graphs. Intuitively, graphs with similar structures should have similar representations. Therefore, we propose Graph External Attention (GEA) --- a novel attention mechanism that leverages multiple external node/edge key-value units to capture inter-graph correlations implicitly. On this basis, we design an effective architecture called Graph External Attention Enhanced Transformer (GEAET), which integrates local structure and global interaction information for more comprehensive graph representations. Extensive experiments on benchmark datasets demonstrate that GEAET achieves state-of-the-art empirical performance. The source code is available for reproducibility at: https://github.com/icm1018/GEAET.

In point cloud, some regions typically exist nodes from multiple categories, i.e., these regions have both homophilic and heterophilic nodes. However, most existing methods ignore the heterophily of edges during the aggregation of the neighborhood node features, which inevitably mixes unnecessary information of heterophilic nodes and leads to blurred boundaries of segmentation. To address this problem, we model the point cloud as a homophilic-heterophilic graph and propose a graph regulation network (GRN) to produce finer segmentation boundaries. The proposed method can adaptively adjust the propagation mechanism with the degree of neighborhood homophily. Moreover, we build a prototype feature extraction module, which is utilised to mine the homophily features of nodes from the global prototype space. Theoretically, we prove that our convolution operation can constrain the similarity of representations between nodes based on their degree of homophily. Extensive experiments on fully and weakly supervised point cloud semantic segmentation tasks demonstrate that our method achieves satisfactory performance. Especially in the case of weak supervision, that is, each sample has only 1%-10% labeled points, the proposed method has a significant improvement in segmentation performance.

Graph neural networks (GNNs) have made great progress in graph-based semi-supervised learning (GSSL). However, most existing GNNs are confronted with the oversmoothing issue that limits their expressive ability. A key factor that leads to this problem is the excessive aggregation of information from other classes when updating the node representation. To alleviate this limitation, we propose an effective method called GUIded Dropout over Edges (GUIDE) for training deep GNNs. The core of the method is to reduce the influence of nodes from other classes by removing a certain number of inter-class edges. In GUIDE, we drop edges according to the edge strength, which is defined as the time an edge acts as a bridge along the shortest path between node pairs. We find that the stronger the edge strength, the more likely it is to be an inter-class edge. In this way, GUIDE can drop more inter-class edges and keep more intra-class edges. Therefore, nodes in the same community or class are more similar, whereas different classes are more separated in the embedded space. In addition, we perform some theoretical analysis of the proposed method, which explains why it is effective in alleviating the oversmoothing problem. To validate its rationality and effectiveness, we conduct experiments on six public benchmarks with different GNNs backbones. Experimental results demonstrate that GUIDE consistently outperforms state-of-the-art methods in both shallow and deep GNNs.

The generalization performance of machine learning methods depends heavily on the quality of data representation. However, existing researches rarely consider representation learning from the perspective of generalization error. In this paper, we prove that generalization error of representation learning function can be estimated effectively by solving two convex optimization problems. Based on it, we propose a general representation learning framework. And then, we apply the proposed framework to two most commonly used nonlinear mapping methods, i.e., kernel based method and deep neural network (DNN), and thus design a kernel selection method and a DNN boosting framework, correspondingly. Finally, extensive experiments verify the effectiveness of the proposed methods.

Although deep learning has been extensively studied and achieved remarkable performance on single image super-resolution (SISR), existing convolutional neural networks (CNN) mainly focus on broader and deeper architecture design, ignoring the detailed information of the image itself and the potential relationship between the features. Recently, several attempts have been made to address the SISR with graph representation learning. However, existing GNN-based methods learning to deal with the SISR problem are limited to the information processing of the entire image or the relationship processing between different feature images of the same layer, ignoring the interdependence between the extracted features of different layers, which is not conducive to extracting deeper hierarchical features. In this paper, we propose an interlayer feature representation based graph neural network for image super-resolution (LSGNN), which consists of a layer feature graph representation learning module and a channel spatial attention module. The layer feature graph representation learning module mainly captures the interdependence between the features of different layers, which can learn more fine-grained image detail features. In addition, we also unified a channel attention module and a spatial attention module into our model, which takes into account the channel dimension information and spatial scale information, to improve the expressive ability, and achieve high quality image details. Extensive experiments and ablation studies demonstrate the superiority of the proposed model.

Graph convolutional neural networks can effectively process geometric data and thus have been successfully used in point cloud data representation. However, existing graph-based methods usually adopt the K-nearest neighbor (KNN) algorithm to construct graphs, which may not be optimal for point cloud analysis tasks, owning to the solution of KNN is independent of network training. In this paper, we propose a novel graph structure learning convolutional neural network (GSLCN) for multiple point cloud analysis tasks. The fundamental concept is to propose a general graph structure learning architecture (GSL) that builds long-range and short-range dependency graphs. To learn optimal graphs that best serve to extract local features and investigate global contextual information, respectively, we integrated the GSL with the designed graph convolution operator under a unified framework. Furthermore, we design the graph structure losses with some prior knowledge to guide graph learning during network training. The main benefit is that given labels and prior knowledge are taken into account in GSLCN, providing useful supervised information to build graphs and thus facilitating the graph convolution operation for the point cloud. Experimental results on challenging benchmarks demonstrate that the proposed framework achieves excellent performance for point cloud classification, part segmentation, and semantic segmentation.

Distance metric learning, which aims at learning an appropriate metric from data automatically, plays a crucial role in the fields of pattern recognition and information retrieval. A tremendous amount of work has been devoted to metric learning in recent years, but much of the work is basically designed for training a linear and global metric with labeled samples. When data are represented with multimodal and high-dimensional features and only limited supervision information is available, these approaches are inevitably confronted with a series of critical problems: 1) naive concatenation of feature vectors can cause the curse of dimensionality in learning metrics and 2) ignorance of utilizing massive unlabeled data may lead to overfitting. To mitigate this deficiency, we develop a semisupervised Laplace-regularized multimodal metric-learning method in this work, which explores a joint formulation of multiple metrics as well as weights for learning appropriate distances: 1) it learns a global optimal distance metric on each feature space and 2) it searches the optimal combination weights of multiple features. Experimental results demonstrate both the effectiveness and efficiency of our method on retrieval and classification tasks.

Given a group photograph, it is interesting and useful to judge whether the characters in it share specific kinship relation, such as father-daughter, father-son, mother-daughter, or mother-son. Recently, facial image-based kinship verification has attracted wide attention in computer vision. Some metric learning algorithms have been developed for improving kinship verification. However, most of the existing algorithms ignore fusing multiple feature representations and utilizing kernel techniques. In this paper, we develop a novel weighted graph embedding-based metric learning (WGEML) framework for kinship verification. Inspired by the fact that family members usually show high similarity in facial features like eyes, noses, and mouths, despite their diversity, we jointly learn multiple metrics by constructing an intrinsic graph and two penalty graphs to characterize the intraclass compactness and interclass separability for each feature representation, respectively, so that both the consistency and complementarity among multiple features can be fully exploited. Meanwhile, combination weights are determined through a weighted graph embedding framework. Furthermore, we present a kernelized version of WGEML to tackle nonlinear problems. Experimental results demonstrate both the effectiveness and efficiency of our proposed methods.

Metric learning plays a fundamental role in the fields of multimedia retrieval and pattern recognition. Recently, an online multikernel similarity (OMKS) learning method has been presented for content-based image retrieval (CBIR), which was shown to be promising for capturing the intrinsic nonlinear relations within multimodal features from large-scale data. However, the similarity function in this method is learned only from labeled images. In this paper, we present a new framework to exploit unlabeled images and develop a semisupervised OMKS algorithm. The proposed method is a multistage algorithm consisting of feature selection, selective ensemble learning, active sample selection, and triplet generation. The novel aspects of our work are the introduction of classification confidence to evaluate the labeling process and select the reliably labeled images to train the metric function, and a method for reliable triplet generation, where a new criterion for sample selection is used to improve the accuracy of label prediction for unlabeled images. Our proposed method offers advantages in challenging scenarios, in particular, for a small set of labeled images with high-dimensional features. Experimental results demonstrate the effectiveness of the proposed method as compared with several baseline methods.