Graph condensation reduces the size of large graphs while preserving performance, addressing the scalability challenges of Graph Neural Networks caused by computational inefficiencies on large datasets. Existing methods often rely on bi-level optimization, requiring extensive GNN training and limiting their scalability. To tackle these issues, we propose Graph Condensation via Gaussian Process (GCGP), a novel and efficient framework that optimizes a compact, high-fidelity condensed graph, enabling effective training of various GNNs with reduced computational cost. GCGP utilizes a Gaussian Process (GP), with the condensed graph serving as observations, to estimate the posterior distribution of predictions. This approach eliminates the need for the iterative and resource-intensive training typically required by GNNs. To enhance the capability of the GCGP in capturing dependencies between function values, we derive a specialized covariance function that incorporates structural information. This covariance function broadens the receptive field of input nodes by local neighborhood aggregation, thereby facilitating the representation of intricate dependencies within the nodes. To address the challenge of optimizing binary structural information in condensed graphs, Concrete random variables are utilized to approximate the binary adjacency matrix in a continuous counterpart. This relaxation process allows the adjacency matrix to be represented in a differentiable form, enabling the application of gradient-based optimization techniques to discrete graph structures. Experimental results show that the proposed GCGP method efficiently condenses large-scale graph data while preserving predictive performance, addressing the scalability and efficiency challenges.

Recommender systems are essential for modern content platforms, yet traditional behavior-based models often struggle with cold users who have limited interaction data. Engaging these users is crucial for platform growth. To bridge this gap, we propose leveraging the social-relation graph to enrich interest representations from behavior-based models. However, extracting value from social graphs is challenging due to relation noise and cross-domain inconsistency. To address the noise propagation and obtain accurate social interest, we employ a dual-view denoising strategy, employing low-rank SVD to the user-item interaction matrix for a denoised social graph and contrastive learning to align the original and reconstructed social graphs. Addressing the interest inconsistency between social and behavioral interests, we adopt a ''mutual distillation'' technique to isolate the original interests into aligned social/behavior interests and social/behavior specific interests, maximizing the utility of both. Experimental results on widely adopted industry datasets verify the method's effectiveness, particularly for cold users, offering a fresh perspective for future research. The implementation can be accessed at https://github.com/WANGLin0126/CLSRec.

360 video captures the complete surrounding scenes with the ultra-large field of view of 360x180. This makes 360 scene understanding tasks, e.g., segmentation and tracking, crucial for appications, such as autonomous driving, robotics. With the recent emergence of foundation models, the community is, however, impeded by the lack of large-scale, labelled real-world datasets. This is caused by the inherent spherical properties, e.g., severe distortion in polar regions, and content discontinuities, rendering the annotation costly yet complex. This paper introduces Leader360V, the first large-scale (10K+), labeled real-world 360 video datasets for instance segmentation and tracking. Our datasets enjoy high scene diversity, ranging from indoor and urban settings to natural and dynamic outdoor scenes. To automate annotation, we design an automatic labeling pipeline, which subtly coordinates pre-trained 2D segmentors and large language models (LLMs) to facilitate the labeling. The pipeline operates in three novel stages. Specifically, in the Initial Annotation Phase, we introduce a Semantic- and Distortion-aware Refinement (SDR) module, which combines object mask proposals from multiple 2D segmentors with LLM-verified semantic labels. These are then converted into mask prompts to guide SAM2 in generating distortion-aware masks for subsequent frames. In the Auto-Refine Annotation Phase, missing or incomplete regions are corrected either by applying the SDR again or resolving the discontinuities near the horizontal borders. The Manual Revision Phase finally incorporates LLMs and human annotators to further refine and validate the annotations. Extensive user studies and evaluations demonstrate the effectiveness of our labeling pipeline. Meanwhile, experiments confirm that Leader360V significantly enhances model performance for 360 video segmentation and tracking, paving the way for more scalable 360 scene understanding. We release our dataset and code at {https://leader360v.github.io/Leader360V_HomePage/} for better understanding.

The rapid development of Internet technology has given rise to a vast amount of graph-structured data. Graph Neural Networks (GNNs), as an effective method for various graph mining tasks, incurs substantial computational resource costs when dealing with large-scale graph data. A data-centric manner solution is proposed to condense the large graph dataset into a smaller one without sacrificing the predictive performance of GNNs. However, existing efforts condense graph-structured data through a computational intensive bi-level optimization architecture also suffer from massive computation costs. In this paper, we propose reforming the graph condensation problem as a Kernel Ridge Regression (KRR) task instead of iteratively training GNNs in the inner loop of bi-level optimization. More specifically, We propose a novel dataset condensation framework (GC-SNTK) for graph-structured data, where a Structure-based Neural Tangent Kernel (SNTK) is developed to capture the topology of graph and serves as the kernel function in KRR paradigm. Comprehensive experiments demonstrate the effectiveness of our proposed model in accelerating graph condensation while maintaining high prediction performance. The source code is available on \hrefhttps://github.com/WANGLin0126/GCSNTK https://github.com/WANGLin0126/GCSNTK.

Recommender systems aim to provide personalized suggestions to users, helping them make effective decisions. However, recent evidence has revealed the untrustworthy aspects of advanced recommender systems, leading to harmful effects in safety-critical areas like finance and healthcare. This tutorial will offer a comprehensive overview of achieving trustworthy recommender systems. It will cover six important aspects: Safety & Robustness, Non-discrimination & Fairness, Explainability, Privacy, Environmental Well-being, and Accountability & Auditability. Each aspect will be defined and categorized, followed by a discussion of the latest research progress and notable works. Additionally, potential interactions among these aspects and future research directions for trustworthy recommender systems will be explored.

Feature selection and feature extraction, in the field of data dimensionality reduction, are the two main strategies. Nevertheless, each of these two strategies has its own advantages and disadvantages. The features chosen by feature selection method have complete physical meaning. However, feature selection cannot reveal the implicit structural information of the samples. In this article, the methods proposed by us combine both feature selection and feature extraction, called joint feature selection and extraction with sparse unsupervised projection (SUP) and graph optimization SUP (GOSUP). A constraint on the number of nonzero rows of the projection matrix is added, which ensures the sparsity of the projection matrix, and only the features corresponding to the nonzero rows of the projection matrix are selected for the feature extraction procedure. We invoke a newly proposed algorithm to tackle this constrained optimization problem. A new concept of "purification matrix" is invented, the use of which could better eliminate meaningless information of samples in subspace. The performance on several datasets verifies the effectiveness of the proposed method for data dimensionality reduction.

Hyperspectral images can provide spectral characteristics related to the physical properties of different materials, which arouses great interest in many fields. Band selection (BS) could effectively solve the problem of high dimensions and redundant information of HSI data. However, most BS methods utilize a single measurement criterion to evaluate band importance so that the assessment of bands is not comprehensive. To dispose of these issues, we propose the hypergraph spectral clustering band selection (HSCBS) method in this letter. First, a novel hypergraph construction method is proposed to combine bands selected by different priority criteria. Second, based on the hypergraph Laplacian matrix, an unsupervised band selection model named HSCBS is presented to cluster the bands into compact clusters with high within-class similarity and low between-class similarity. The results of comprehensive experimental on two public real datasets demonstrate the effectiveness of HSCBS.

Dimensionality reduction (DR) technique has been frequently used to alleviate information redundancy and reduce computational complexity. Traditional DR methods generally are inability to deal with nonlinear data and have high computational complexity. To cope with the problems, we propose a fast unsupervised projection (FUP) method. The simplified graph of FUP is constructed by samples and representative points, where the number of the representative points selected through iterative optimization is less than that of samples. By generating the presented graph, it is proved that large-scale data can be projected faster in numerous scenarios. Thereafter, the orthogonality FUP (OFUP) method is proposed to ensure the orthogonality of projection matrix. Specifically, the OFUP method is proved to be equivalent to PCA upon certain parameter setting. Experimental results on benchmark data sets show the effectiveness in retaining the essential information.

The linear discriminant analysis (LDA) method needs to be transformed into another form to acquire an approximate closed-form solution, which could lead to the error between the approximate solution and the true value. Furthermore, the sensitivity of dimensionality reduction (DR) methods to subspace dimensionality cannot be eliminated. In this article, a new formulation of trace ratio LDA (TRLDA) is proposed, which has an optimal solution of LDA. When solving the projection matrix, the TRLDA method given by us is transformed into a quadratic problem with regard to the Stiefel manifold. In addition, we propose a new trace difference problem named optimal dimensionality linear discriminant analysis (ODLDA) to determine the optimal subspace dimension. The nonmonotonicity of ODLDA guarantees the existence of optimal subspace dimensionality. Both the two approaches have achieved efficient DR on several data sets.