The prevalence of real-world multi-view data makes incomplete multi-view clustering (IMVC) a crucial research. The rapid development of Graph Neural Networks (GNNs) has established them as one of the mainstream approaches for multi-view clustering. Despite significant progress in GNNs-based IMVC, some challenges remain: (1) Most methods rely on the K-Nearest Neighbors (KNN) algorithm to construct static graphs from raw data, which introduces noise and diminishes the robustness of the graph topology. (2) Existing methods typically utilize the Mean Squared Error (MSE) loss between the reconstructed graph and the sparse adjacency graph directly as the graph reconstruction loss, leading to substantial gradient noise during optimization. To address these issues, we propose a novel Dynamic Deep Graph Learning for Incomplete Multi-View Clustering with Masked Graph Reconstruction Loss (DGIMVCM). Firstly, we construct a missing-robust global graph from the raw data. A graph convolutional embedding layer is then designed to extract primary features and refined dynamic view-specific graph structures, leveraging the global graph for imputation of missing views. This process is complemented by graph structure contrastive learning, which identifies consistency among view-specific graph structures. Secondly, a graph self-attention encoder is introduced to extract high-level representations based on the imputed primary features and view-specific graphs, and is optimized with a masked graph reconstruction loss to mitigate gradient noise during optimization. Finally, a clustering module is constructed and optimized through a pseudo-label self-supervised training mechanism. Extensive experiments on multiple datasets validate the effectiveness and superiority of DGIMVCM.

Bingkang Shi, Jen-tse Huang, Luo Long, Tianyu Zong, Hongzhu Yi, Yuanxiang Wang, Songlin Hu, Xiaodan Zhang, Zhongjiang Yao. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Tianyu Zong, Rui Dai, Hongzhu Yi, Yuanxiang Wang, Zhenghao Zhang, Zhenyu Guan, Yujia Yang, Bingkang Shi, Yueyang Ding, Xiangxiang Chu, Kaikui Liu, Jungang Xu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

In additive manufacturing (AM), final product geometries are often deformed or distorted. The deviations of three-dimensional (3D) shapes from their intended designs can be represented as 2D surfaces in a$\mathbb {R}^{3}$space, which constitutes a complicated set of data for learning and predicting geometric quality. Patterns of deviation surfaces vary with shape geometries, sizes/volumes, materials, and AM processes. Our previous work has established an engineering-informed convolution framework to learn shape deviation from a small set of training products built with the same material and process. It incorporates the characteristics of the layer-wise shape forming process through a convolution formulation and the size factor for a category of smooth 3D shapes such as domes or cylinders. This study extends this fabrication-aware learning framework to a larger class of products including both smooth and non-smooth surfaces (polyhedral shapes). The key idea of learning heterogeneous deviation surface data under a unified model is to establish the association between the deviation profiles of smooth base shapes and those of non-smooth polyhedral shapes. The association, which is characterized by a novel 3D cookie-cutter function, views polyhedral shapes as being carved out from smooth base shapes. In essence, the AM process of building non-smooth shapes is mathematically decomposed into two steps: additively fabricate smooth base shapes using a convolution learning framework, and then subtract extra materials using a cookie-cutter function. The proposed joint learning framework of shape deviation data reflects this decomposition by adopting a sequential model estimation procedure. The model learning procedure first establishes the convolution model to capture the effects of layer-wise fabrication and sizes, and then estimates the 3D cookie-cutter function to realize geometric differences between smooth and non-smooth shapes. A new Gaussian process model is proposed to consider the spatial correlation among neighboring regions within a 3D shape and across different shapes. The case study demonstrates the feasibility and prospects of prescriptive learning of complex 3D shape deviations in AM and extension to broader engineering surface data.Note to Practitioners—Engineering processes such as 3D printing generate complex shape data in the form of 3D point clouds. Qualification and verification of 3D shapes involves modeling and learning of heterogeneous shape deviation data that are affected by both product geometries and process physics. This study develops an engineering-informed, small-sample machine learning methodology to learn and predict deviations of smooth and non-smooth 3D shapes in a unified modeling framework. The fabrication of a non-smooth 3D shape is mathematically decomposed into the smooth base shape formation and shape difference realization. Both process knowledge and shape geometries are captured in the learning framework. It provides a new data analytical tool for shape engineering in additive manufacturing and beyond.

The 3-D shape accuracy is a critical performance measure for products built via additive manufacturing (AM). With advances in computing and increased accessibility of AM product data, machine learning for AM (ML4AM) has become a viable strategy for enhancing 3-D printing performance. A proper description of the 3-D shape formation through the layer-by-layer fabrication process is critical to ML4AM, such as feature selection and AM process modeling. The physics-based modeling and simulation approaches present voxel-level description of an object formation from points to lines, lines to surfaces, and surfaces to 3-D shapes. However, this computationally intensive modeling framework does not provide a clear structure for machine learning of AM data. Significant progress has been made to model and predict the shape accuracy of planar objects under data analytical frameworks. In order to predict, learn, and compensate for 3-D shape deviations using shape measurement data, we propose a shape deviation generator (SDG) under a novel convolution formulation to facilitate the learning and prediction of 3-D printing accuracy. The shape deviation representation, individual layer input function, and layer-to-layer transfer function for the convolution modeling framework are proposed and derived. A deconvolution problem for identifying the transfer function is formulated to capture the interlayer interaction and error accumulation effects in the layer-by-layer fabrication processes. Physics-informed sequential model estimation is developed to fully establish the SDG models. The Gaussian process regression is adopted to capture spatial correlations. The printed 2-D and 3-D shapes via a stereolithography (SLA) process are used to demonstrate the proposed modeling framework and derive new process insights for AM processes. Note to Practitioners-With advances in computing and increased availability of product data, machine learning for additive manufacturing (ML4AM) has become a viable strategy for enhancing 3-D printing accuracy. This work establishes the shape deviation generator (SDG) as a novel data analytical framework through a convolution formulation to model the 3-D shape formation in the AM process. This new engineering-informed machine-learning framework will facilitate the learning of AM data to establish models for geometric shape accuracy prediction and control.

Tractography refers to the process of tracing out the nerve fiber bundles from diffusion Magnetic Resonance Images (dMRI) data acquired either in vivo or ex-vivo. Tractography is a mature research topic within the field of diffusion MRI analysis, nevertheless, several new methods are being proposed on a regular basis thereby justifying the need, as the problem is not fully solved. Tractography is usually applied to the model (used to represent the diffusion MR signal or a derived quantity) reconstructed from the acquired data. Separating shape and orientation of these models was previously shown to approximately preserve diffusion anisotropy (a useful bio-marker) in the ubiquitous problem of interpolation. However, no further intrinsic geometric properties of this framework were exploited to date in literature. In this paper, we propose a new intrinsic recursive filter on the product manifold of shape and orientation. The recursive filter, dubbed IUKFPro, is a generalization of the unscented Kalman filter (UKF) to this product manifold. The salient contributions of this work are: (1) A new intrinsic UKF for the product manifold of shape and orientation. (2) Derivation of the Riemannian geometry of the product manifold. (3) IUKFPro is tested on synthetic and real data sets from various tractography challenge competitions. From the experimental results, it is evident that IUKFPro performs better than several competing schemes in literature with regards to some of the error measures used in the competitions and is competitive with respect to others.