Author name cluster

Xinwang Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

88 papers

1 author row

AAAI Conference 2026 Conference Paper

Enhancing Kernel Power $K$-means: Scalable and Robust Clustering with Random Fourier Features and Possibilistic Method

Yixi Chen
Weixuan Liang
Tianrui Liu
Jun-Jie Huang
Ao Li
Xueling Zhu
Xinwang Liu

Kernel power k-means (KPKM) leverages a family of means to mitigate local minima issues in kernel k-means. However, KPKM faces two key limitations: (1) the computational burden of the full kernel matrix restricts its use on extensive data, and (2) the lack of authentic centroid-sample assignment learning reduces its noise robustness. To overcome these challenges, we propose RFF-KPKM, introducing the first approximation theory for applying random Fourier features (RFF) to KPKM. RFF-KPKM employs RFF to generate efficient, low dimensional feature maps, bypassing the need for the whole kernel matrix. Crucially, we are the first to establish strong theoretical guarantees for this combination: (1) an excess risk bound of O( k^3/n), (2) strong consistency with membership values, and (3) a (1 + ε) relative error bound achievable using the RFF of dimension poly(ε^{−1} logk). Furthermore, to improve robustness and the ability to learn multiple kernels, we propose IP-RFF-MKPKM, an improved possibilistic RFF-based multiple kernel power k-means. IP-RFF-MKPKM ensures the scalability of MKPKM via RFF and refines cluster assignments by combining the merits of the possibilistic and fuzzy membership. Experiments on large-scale datasets demonstrate the superior efficiency and clustering accuracy of the proposed methods compared to the state-of-the-art alternatives.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Graph Masked Autoencoder for Multi-view Remote Sensing Data Clustering

Renxiang Guan
Junhong Li
Siwei Wang
Tianrui Liu
Dayu Hu
Miaomiao Li
Xinwang Liu

Multi-view graph clustering (MVGC) for remote sensing data has gained increasing attention due to its ability to integrate complementary information across modalities while capturing spatial dependencies in heterogeneous data. Although current methods based on graph contrastive learning achieve strong performance, they often misidentify intra-cluster samples as negatives, leading to class conflicts and reduced clustering accuracy. Graph masked autoencoders have recently shown promising potential in learning robust representations through masked reconstruction, but their application to remote sensing data remains underexplored. This challenge is especially notable in the multi-view remote sensing setting, where high heterogeneity and complex spatial structures increase the difficulty of effective representation learning. To address these issues, we propose Clustering-Guided graph Mask AutoEncoder (CG-MAE), the first framework to extend graph masked autoencoders to multi-view remote sensing clustering. We introduce a clustering-guided masking strategy that selectively masks nodes near cluster centers and intra-cluster edges, which are crucial for capturing key structural information. By reconstructing these masked components, the model is encouraged to focus on learning features that are highly relevant to clustering. To further improve training stability and efficiency, we design an easy-to-hard node masking strategy that enables the model to gradually learn from increasingly challenging patterns. Additionally, we propose a dual self-adaptive learning mechanism that encourages the model to align more closely with the underlying semantic distributions. Extensive experiments on four widely used multi-view remote sensing datasets demonstrate that CG-MAE consistently outperforms state-of-the-art methods in both clustering accuracy and representation quality.

PDF Details DOI

JBHI Journal 2026 Journal Article

HCA-Net: Hierarchical Contextual Attention Network for Lightweight and Accurate Polyp Segmentation

Chengcheng Li
Huiying Xu
Xinzhong Zhu
Huiling Chen
Xinwang Liu
Yun Liu
Chang Tang
Zhendong Chen

Early detection of colorectal polyps is crucial for clinical screening and cancer prevention, where accurate and efficient automatic segmentation plays a pivotal role. However, colonoscopy images often suffer from low contrast, blurred boundaries, and scale variations, making segmentation challenging. Existing encoder-decoder networks (e. g. , U-Net) suffer from asymmetric supervision and feature redundancy, which in turn lead to semantic inconsistency and loss of fine details. While deeper or hybrid designs alleviate these issues, their high complexity and computational burden limit feasibility in real-time clinical practice. To address these challenges, we propose a lightweight segmentation framework, Hierarchical Contextual Attention Network (HCA-Net), consisting of the Redundancy-Suppressed Dual-Path Downsampling (RS-DPD) module and the Boundary-Aware Semantic Alignment Upsampling (BA-SAU) module, applied to the encoder and decoder, respectively. RS-DPD suppresses redundancy while preserving fine-grained details through a dual-path design, whereas BA-SAU leverages cross-layer contextual attention to enforce semantic consistency and enhance boundary sensitivity. Both modules are built upon our proposed Hierarchical Contextual Attention (HCA) mechanism, which combines convolutional projection with pooling-based compression to achieve efficient global modeling and accurate local boundary restoration. In addition, a composite boundary-aware loss function is designed to improve pixel-level accuracy, structural consistency, and robustness in low-contrast and boundary-ambiguous regions. Extensive experiments on public colorectal polyp datasets demonstrate that HCA-Net achieves state-of-the-art (SOTA) segmentation accuracy with significantly improved efficiency, while maintaining robustness under low-contrast and blurred-boundary conditions.

Details DOI

AAAI Conference 2026 Conference Paper

Hierarchical Cross-View Alignment for Multi-View Clustering via Decoupled Information Distillation

Taichun Zhou
Siwei Wang
Zhibin Dong
Jiaqi Jin
Ke Liang
Baili Xiao
Miaomiao Li
Xinwang Liu

Multi-view clustering aims to uncover shared semantics and complementary information across different views. However, the inherent heterogeneity among views poses significant challenges to effective collaborative modeling and information integration. While recent studies have introduced distillation-based mechanisms to enhance cross-view consistency and alleviate heterogeneity, these approaches often rely on manually defined knowledge transfer paths or fixed fusion weights, which are inflexible in handling complex and dynamic view relationships in practice. To address this issue, we propose HOARD: a novel framework for Hierarchical crOss-view Alignment for multi-view clusteRing via Decoupled information distillation. HOARD structurally decouples multi-view representations into shared and specific components, and performs hierarchical alignment. Specifically, we introduce a granular-ball contrastive alignment to enhance the semantic consistency of shared features, and a prototype collaborative transmission alignment strategy to align specific features while preserving view-specific structural characteristics. Moreover, we design an information distillation unit to adaptively model cross-view knowledge transfer in both feature spaces. An attention mechanism is further employed to integrate shared and specific information. Extensive experiments on benchmark datasets demonstrate that HOARD significantly improves alignment quality and clustering performance, achieving state-of-the-art results.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Make Model Transparent: Brain Network Analysis via Causal and Knowledge Graph Learning

Lingyuan Meng
Ke Liang
Hao Yu
Haotian Wang
Miaomiao Li
Xinwang Liu

Brain network analysis technology reveals the organizational mechanism and information processing mode by constructing the structural connection network between brain regions. It has achieved satisfactory results in brain disease prediction tasks, promoting the progress of neuroscience. In recent years, graph transformer has become the most mainstream method for brain analysis with its powerful feature extraction ability and attention mechanism. However, these methods face two challenges, i.e., lack of interpretability, and neglect of semantic associations among brain regions. To solve these problems, we proposed a large language model (LLM)-driven causal knowledge brain network transformer framework, termed BrainCKT, which is plug-and-play, and can adapt to most of the existing mainstream graph transformer-based methods. Specifically, we constructed a brain region causal graph and used its adjacency matrix to guide the learning process of the self-attention mechanism. In addition, we constructed a brain science knowledge graph and encoded it through a pre-trained model to enhance the original brain region features. Finally, we integrated BrainCKT into four mainstream graph transformer baselines for verification. Experimental results on two brain imaging datasets proved the effectiveness of BrainCKT.

PDF Details DOI

AIJ Journal 2026 Journal Article

On the convergence of SignSGD under weak first- and second-order gradient Lipschitz

Tao Sun
Xinwang Liu

Sign-based stochastic methods have attracted increasing attention for their ability to perform well with only a few sign bits of information for updating specific fields. Nonetheless, convergence analyses for such methods always rely on strong assumptions that the function is globally first- or second-order gradient Lipschitz; such assumptions are very restrictive and generally not satisfied in real-world instances such as training deep neural networks. This paper reconsiders sign-based methods and studies the convergence of such schemes under more realistic assumptions on first- and second-order gradient Lipschitz. We prove that these weak assumptions hold for a class of two-layer neural networks training with weight decay. We then prove the convergence of a class of sign-based methods in the weak first-order gradient Lipschitz framework and then introduce a modified second-order condition that still allows for nonconvex acceleration within the corresponding sign-based frameworks. Unlike other methods, our findings are based on less restrictive assumptions, thereby broadening their applicability.

Details DOI

AAAI Conference 2026 Conference Paper

Parameter-Free Clustering via Self-Supervised Consensus Maximization

Lijun Zhang
Suyuan Liu
Siwei Wang
Shengju Yu
Xueling Zhu
Miaomiao Li
Xinwang Liu

Clustering is a fundamental task in unsupervised learning, but most existing methods heavily rely on hyperparameters such as the number of clusters or other sensitive settings, limiting their applicability in real-world scenarios. To address this long-standing challenge, we propose a novel and fully parameter-free clustering framework via Self-supervised Consensus Maximization, named SCMax. Our framework performs hierarchical agglomerative clustering and cluster evaluation in a single, integrated process. At each step of agglomeration, it creates a new, structure-aware data representation through a self-supervised learning task guided by the current clustering structure. We then introduce a nearest neighbor consensus score, which measures the agreement between the nearest neighbor-based merge decisions suggested by the original representation and the self-supervised one. The moment at which consensus maximization occurs can serve as a criterion for determining the optimal number of clusters. Extensive experiments on multiple datasets demonstrate that the proposed framework outperforms existing clustering approaches designed for scenarios with an unknown number of clusters.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Sample-specific Modality Diagnosis and Cross-modal Enhancement for Incomplete Multimodal Representations

Junsong Chen
Jiyuan Liu
Suyuan Liu
Wei Zhang
Ao Li
En Zhu
Xinwang Liu

In multimodal sentiment analysis, modality missingness and quality degradation are common. Existing methods often rely on batch-level modality generation, generation but neglect sample-level missingness, hence their flexibility is limited severely in real-world scenarios. To address this, Sample-specific Modality Diagnosis and Cross-modal Enhancement for Incomplete Multimodal Representations (SMCIR) is proposed. Specifically, The Dynamic Multi-feature Fusion Detector (DMFD) is presented, which detects missingness and severity at the sample-level using indicators such as information entropy, modality similarity, and mutual information. Unlike batch-based methods, the DMFD provides fine-grained detection and adaptive responses, improving sensitivity to modality disturbances. Meanwhile, the Context-aware Modality Completion Generator (CMCG) is developed to restore missing modalities through context-guided reconstruction using multiscale feature fusion and cross-modal attention. In this way, the proposed CMCG method can avoid redundancy and inconsistency, enhancing the consistency and discriminativity of the fused representation. In CMCG, the text modality serves as a stable guide to improve context consistency. Experiments on the CMU-MOSI and CMU-MOSEI datasets show that SMCIR outperforms existing full-modal and non-recovery-based methods, well validating its efficacy and superiority in multimodal learning.

PDF Details DOI

AAAI Conference 2026 Conference Paper

TVChain: Leveraging Textual-Visual Prompt Chains for Jailbreaking Large Vision-Language Models

Hao Yu
Ke Liang
Junxian Duan
Jun Wang
Siwei Wang
Chuan Ma
Xinwang Liu

Large Vision-Language Models (LVLMs) enhance the capabilities of Large Language Models by integrating visual inputs, thereby enabling advanced multimodal reasoning across diverse applications. However, these enhanced reasoning capabilities introduce new security risks, particularly to jailbreaking attacks that bypass built-in safety mechanisms to elicit harmful or unauthorized outputs. While recent efforts have explored adversarial and typographic prompts, most existing attacks suffer from three key limitations: reliance on auxiliary models, limited effectiveness in black-box scenarios, and inadequate exploitation of the LVLMs' intrinsic reasoning abilities. In this work, we propose TVChain, a novel black-box jailbreaking framework that explicitly intervenes in both the visual and textual reasoning processes of LVLMs. TVChain decomposes malicious prompts into a sequence of semantically meaningful sub-images that represent relevant objects and behaviors, thereby circumventing direct exposure of illicit content. In parallel, a carefully designed chain-of-thought (CoT) textual prompt is employed to steer the model's reasoning toward reconstructing the intended activity in a covert yet effective manner. We demonstrate that this compositional prompting strategy reduces the likelihood of triggering safety mechanisms while preserving attack efficacy. Extensive evaluations on eleven LVLMs (seven open-source and four commercial) across two benchmark datasets and three state-of-the-art defenses validate the effectiveness and robustness of TVChain.

PDF Details DOI

EAAI Journal 2025 Journal Article

Analysis of interrelationships of human errors using linguistic decision-making trial and evaluation laboratory with consensus reaching process

Qiaohong Zheng
Xinwang Liu

Analyzing human errors' interrelationships is one of the most important assignments for human reliability improvement in sociotechnical systems. Human factor analysis and classification system (HFACS) is effective in human error analysis due to its taxonomy and systematical perspective. It reveals interrelationships among human errors emerging in a multi-hierarchy of systems. However, the conventional HFACS method is incapable of quantifying their interrelationship. Especially, due to the nature of human errors, their objective data is limited. Experts' opinions are important resources to facilitate human error analysis. However, limited improved HFACS considers experts' consensus on interrelationships analysis results, especially in linguistic environments. Accordingly, this paper aims to address HFACS-based interrelationships analysis problems utilizing linguistic decision-making trial and evaluation laboratory (DEMATEL) with consensus reaching process (CRP). First, probabilistic linguistic terms are utilized to represent experts' opinions on human errors' interrelationships. Second, CRP is introduced to derive consensual opinions on human errors' interrelationships, shifting the focus to identifying human errors with low consensus levels rather than experts. Then, a hybrid weighting method is introduced to determine the weight of experts' opinions in the information fusion phase, which reflects inherent uncertainty and inter-recognition of experts’ opinions. Furthermore, DEMATEL is introduced to model direct and indirect interrelationships among human errors. Finally, a case study of a drug administration process is conducted to validate the efficiency of the proposed method. The case study indicates that neglect of safety culture development and limited financial and human resources are the top two human errors, with importance degree 0. 148 and 0. 107.

Details DOI

NeurIPS Conference 2025 Conference Paper

Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete Scenarios

Shengju Yu
Pei Zhang
Siwei Wang
Suyuan Liu
Xinhang Wan
Zhibin Dong
Tiejun Li
Xinwang Liu

Although receiving notable improvements, current multi-view clustering (MVC) techniques generally rely on feature library mechanisms to propagate accumulated knowledge from historical views to newly-arrived data, which overlooks the information pertaining to basis embedding within each view. Moreover, the mapping paradigm inevitably alters the values of learned landmarks and built affinities due to the uninterruption nature, accordingly disarraying the hierarchical cluster structures. To mitigate these two issues, we in the paper provide a named BSTM algorithm. Concretely, we firstly synchronize with the distinct dimensions by introducing a group of specialized projectors, and then establish unified anchors for all views collected so far to capture intrinsic patterns. Afterwards, departing from per-view architectures, we devise a shared bipartite graph construction via indicators to quantify similarity, which not only avoids redundant data-recalculations but alleviates the representation distortion caused by fusion. Crucially, there two components are optimized within an integrated framework, and collectively facilitate knowledge transfer upon encountering incoming views. Subsequently, to flexibly do transformation on anchors and meanwhile maintain numerical consistency, we develop a bit-swapping scheme operating exclusively on 0 and 1. It harmonizes anchors on current view and that on previous views through one-hot encoded row and column attributes, and the graph structures are correspondingly reordered to reach a matched configuration. Furthermore, a computationally efficient four-step updating strategy with linear complexity is designed to minimize the associated loss. Extensive experiments organized on publicly-available benchmark datasets with varying missing percentages confirm the superior effectiveness of our BSTM.