[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84905-en":3,"doc-seo-84905-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84905,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Straight-Path Flow Matching for Incomplete Multi-View Clustering","Incomplete Multi-View Clustering (IMVC) tackles clustering when multi-modal samples have missing views. Recent end-to-end generative methods use diffusion models to recover absent views through stochastic noise-to-data trajectories, but such clustering-unaware dynamics initialize from cluster-agnostic noise and do not explicitly preserve cluster structure. This work redesigns the probability path with a flow-matching framework using linear straight-path interpolation between paired view representations. Formal analysis and experiments show deterministic ODE flows align better with clustering objectives and achieve new state-of-the-art results.","arXiv :2607 .0628 1v 1 [ cs .CV] 7 Jul 2026  \nStraight-Path Flow Matching for Incomplete Multi-View Clustering  \nYiteng Yuan 1 * , Junyan Wang2 *†, Zheyuan Liu2 , Hong Jia3 , Lei Fan4 , Zhulin Tao5†, and Lianbo Guo 1  \n1 School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China  \n2 Australian Institute for Machine Learning, Adelaide University, Adelaide, Australia  \n3 University of Auckland, Auckland, New Zealand  \n4 University of New South Wales, Sydney, Australia  \n5 Communication University of China, Beijing, China [yuanyiteng&lbguo@hust.edu.cn](yuanyiteng&lbguo@hust.edu.cn), [junyan.wang&zheyuan.liu@adelaide.edu.au](junyan.wang&zheyuan.liu@adelaide.edu.au)  \n[hong.jia@auckland.ac.nz](hong.jia@auckland.ac.nz), [lei.fan1@unsw.edu.au](lei.fan1@unsw.edu.au), [taozl@cuc.edu.cn](taozl@cuc.edu.cn)  \nAbstract. Incomplete Multi-View Clustering addresses the problem of clustering multi-modal data when certain views are missing. Recent endto-end generative approaches leverage diffusion models to recover missing views via stochastic noise-to-data trajectories. While expressive, such mechanisms are not explicitly designed for clustering, as they initialize from cluster-agnostic noise and rely on stochastic denoising dynamics.  \nIn this work, we revisit probability path design in end-to-end generative IMVC. We introduce a flow-matching framework with a linear interpolation path between paired view representations, that replaces diffusion with probability flows between observed and missing views. We provide a formal analysis showing that deterministic ODE flows are inherently better aligned with clustering objectives than diffusion-based stochastic trajectories, especially in terms of transport mechanisms that respect class-conditional data distributions and maintain cluster consistency infinite-step regimes. Building upon this insight, we develop an end-toend IMVC architecture that integrates straight-path flow-matching view completion with cluster-level and entropy-based alignment to enforce cross-view clustering consistency. Extensive experiments on standard IMVC benchmarks demonstrate that the proposed framework establishes new state-of-the-art performance.  \nKeywords: Incomplete Multi-View Clustering · Flow Matching · ODE  \n1 Introduction  \nThe task of Incomplete Multi-View Clustering (IMVC) [8] addresses the challenge of multi-view clustering (MVC) [2], with an additional layer of difficulty,  \ni.e., not all views are consistently available for each sample. Compared to the ⋆ Equal contribution. † Corresponding author.  \n2 Y. Yuan & J. Wang et al.  \ntraditional MVC task setup, IMVC more closely reflects real-world use cases involving multi-view data [37,49,50], as such data collection processes may encounter sensor malfunctions, occlusions, disk space limitations, or even storage media corruptions.  \nTraditional IMVC methods [24, 25, 39, 40, 47, 51] focus on latent alignment and reconstruction under missing-view constraints. Recently, generative modeling [6, 10, 29] has emerged as a powerful alternative paradigm. Diffusion-based approaches [37,50], in particular, formulate missing-view recovery as conditional generation: starting from Gaussian noise, a stochastic denoising process conditioned on the observed view progressively reconstructs the missing representation. Earlier works [37] adopt a two-stage pipeline in which clustering is performed after generative recovery. Recent research has shifted toward end-toend IMVC frameworks [50] that optimize missing-view recovery and clustering jointly. In the joint framework, the generative module is trained under clusteringoriented supervision, so the intermediate and final recovered features directly determine the clustering embeddings and assignments during training. Consequently, the properties of the generative trajectory directly influence the structural organization of the learned representations, as cross-view discrepancies are progressively reduced","cbCaipoannnJvncO","https://ap.wps.com/l/cbCaipoannnJvncO","pdf",4088311,2,1,28,"English","en",105,"# Introduction\n## Background and Motivation\n## Related Work\n## Proposed Approach\n# Method\n## Straight-Path Flow Matching\n## Clustering-Level and Entropy Alignment","[{\"question\":\"What problem does the paper address in Incomplete Multi-View Clustering?\",\"answer\":\"It addresses multi-view clustering when not all views are consistently available for each sample. Missing views add difficulty beyond the standard MVC setting.\"},{\"question\":\"Why are diffusion-based generative approaches not ideal for IMVC clustering consistency?\",\"answer\":\"Diffusion relies on stochastic dynamics that start from cluster-agnostic noise and denoise progressively, so cluster-discriminative structure becomes clear mainly in low-noise regimes. This can disrupt representation transport before late-stage refinement.\"},{\"question\":\"How does the proposed straight-path flow matching method recover missing views?\",\"answer\":\"It replaces diffusion with deterministic ODE probability flows using a linear interpolation (straight-path) between observed and missing view representations. A neural vector field is trained to match path velocities, and clustering consistency is enforced with cluster-level and entropy-based alignment.\"}]",1784199271,71,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"straight-path-flow-matching-for-incomplete-multi-view-clustering","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/straight-path-flow-matching-for-incomplete-multi-view-clustering/84905/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-22","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in Incomplete Multi-View Clustering?","Question",{"text":75,"@type":76},"It addresses multi-view clustering when not all views are consistently available for each sample. Missing views add difficulty beyond the standard MVC setting.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why are diffusion-based generative approaches not ideal for IMVC clustering consistency?",{"text":80,"@type":76},"Diffusion relies on stochastic dynamics that start from cluster-agnostic noise and denoise progressively, so cluster-discriminative structure becomes clear mainly in low-noise regimes. This can disrupt representation transport before late-stage refinement.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed straight-path flow matching method recover missing views?",{"text":84,"@type":76},"It replaces diffusion with deterministic ODE probability flows using a linear interpolation (straight-path) between observed and missing view representations. A neural vector field is trained to match path velocities, and clustering consistency is enforced with cluster-level and entropy-based alignment.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]