PRISM: Iterative Cross-Modal Posterior Refinement for Dynamic Text-Attributed Graphs

• URL: http://arxiv.org/abs/2605.06073v1
• Date: Thu, 07 May 2026 11:58:47 GMT
• Title: PRISM: Iterative Cross-Modal Posterior Refinement for Dynamic Text-Attributed Graphs
• Abstract summary: multimodal learning has emerged as a promising yet underexplored direction for enhancing DyTAG representation learning.<n>We propose textbfPRISM, an iterative cross-modal posterior refinement framework for DyTAG representation learning.<n>PRISM organizes DyTAG information into semantic and behavioral modalities, providing a more intrinsic alternative to carrier-level modality partitions.
• Score: 5.2307029116231165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic text-attributed graphs (DyTAGs) provide a powerful framework for modeling evolving systems in which node semantics and time-dependent interactions are tightly coupled. Recently, multimodal learning has emerged as a promising yet underexplored direction for enhancing DyTAG representation learning. However, existing methods typically rely on rigid modality partitions and one-shot fusion strategies, which limit their ability to capture the intrinsic and evolving dependencies between node semantics and interaction behaviors. To address these limitations, we propose \textbf{PRISM}, an iterative cross-modal posterior refinement framework for DyTAG representation learning. PRISM organizes DyTAG information into semantic and behavioral modalities, providing a more intrinsic alternative to carrier-level modality partitions. Instead of fusing the two modalities in a single step, PRISM learns a refinement trajectory that progressively transforms semantic priors into behavior-conditioned posterior states through cross-modal interaction with behavioral evidence. Extensive experiments on DTGB benchmark datasets show that PRISM achieves strong performance on temporal link prediction and destination node retrieval tasks. Further ablation studies validate the effectiveness of semantic--behavioral modeling and iterative posterior refinement.

Related papers

• Text-guided Feature Disentanglement for Cross-modal Gait Recognition [5.766298616867406]
  Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios.<n>Real-world scenarios often involve sensing modalities such as LiDAR and RGB cameras, making LiDAR-Cross-modal Gait recognition a critical yet challenging task.<n>To address this challenge, we propose TCFDNet, a Text-guided Cross-modal Feature Disentanglement Network.<n>Extensive experiments on SUSTech1K and FreeGait datasets demonstrate that TCFDNet achieves new state-of-the-art results and validate the effectiveness of the proposed modules.
  arXiv  Detail & Related papers  (2026-05-29T03:16:44Z)
• Bidirectional Learning of Facial Action Units and Expressions via Structured Semantic Mapping across Heterogeneous Datasets [85.74213192818668]
  We propose a Structured Semantic Mapping (SSM) framework for bidirectional AU--FE learning under different data domains and heterogeneous supervision.<n>SSM consists of three key components: (1) a shared visual backbone that learns unified facial representations from dynamic AU and FE videos; (2) semantic mediation via a Textual Semantic Prototype (TSP) module; and (3) a Dynamic Prior Mapping (DPM) module that incorporates prior knowledge derived from the Facial Action Coding System.
  arXiv  Detail & Related papers  (2026-04-12T09:08:32Z)
• TAWRMAC: A Novel Dynamic Graph Representation Learning Method [1.7230595437884768]
  We introduce TAWRMAC, a novel framework that integrates Temporal Anonymous Walks with Restart, Memory Augmentation, and Neighbor Co-occurrence embedding.<n>By providing stable, generalizable, and context-aware embeddings, TAWRMAC advances the state of the art in continuous-time dynamic graph learning.
  arXiv  Detail & Related papers  (2025-10-10T21:38:07Z)
• Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation [14.707224594220264]
  We propose a Text-Derived Graph Network (TRG-Net) to enhance both modeling and supervision.<n>For modeling, the Dynamic Spatio-Temporal Fusion Modeling (D) method incorporates Text-Derived Joint Graphs (JGT) with channel adaptation.<n>For supervision, the Absolute-Relative Inter-Class Supervision (ARIS) method employs contrastive learning between action features and text embeddings to regularize the absolute class.
  arXiv  Detail & Related papers  (2025-03-19T11:38:14Z)
• SemanticBoost: Elevating Motion Generation with Augmented Textual Cues [73.83255805408126]
  Our framework comprises a Semantic Enhancement module and a Context-Attuned Motion Denoiser (CAMD) The CAMD approach provides an all-encompassing solution for generating high-quality, semantically consistent motion sequences. Our experimental results demonstrate that SemanticBoost, as a diffusion-based method, outperforms auto-regressive-based techniques.
  arXiv  Detail & Related papers  (2023-10-31T09:58:11Z)
• IDRNet: Intervention-Driven Relation Network for Semantic Segmentation [34.09179171102469]
  Co-occurrent visual patterns suggest that pixel relation modeling facilitates dense prediction tasks. Despite the impressive results, existing paradigms often suffer from inadequate or ineffective contextual information aggregation. We propose a novel textbfIntervention-textbfDriven textbfRelation textbfNetwork.
  arXiv  Detail & Related papers  (2023-10-16T18:37:33Z)
• 3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation [33.20461146674787]
  In 3D Referring Expression (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions. We introduce an innovative end-to-end Superpoint-Text Matching Network (3D-STMN) that is enriched by dependency-driven insights. Our model not only set new performance standards, registering an mIoU gain of 11.7 points but also achieve a staggering enhancement in inference speed, surpassing traditional methods by 95.7 times.
  arXiv  Detail & Related papers  (2023-08-31T11:00:03Z)
• Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification [68.06496970320595]
  Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. We present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs.
  arXiv  Detail & Related papers  (2022-05-18T07:47:01Z)
• ConTIG: Continuous Representation Learning on Temporal Interaction Graphs [32.25218861788686]
  ConTIG is a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories. Our model exploit three-fold factors in dynamic networks which include latest interaction, neighbor features and inherent characteristics. Experiments results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation and dynamic node classification tasks.
  arXiv  Detail & Related papers  (2021-09-27T12:11:24Z)
• Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks [61.950353376870154]
  Joint-event-extraction is a sequence-to-sequence labeling task with a tag set composed of tags of triggers and entities. We propose a Cross-Supervised Mechanism (CSM) to alternately supervise the extraction of triggers or entities. Our approach outperforms the state-of-the-art methods in both entity and trigger extraction.
  arXiv  Detail & Related papers  (2020-10-13T11:51:17Z)
• A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis [73.74885246830611]
  We propose a novel dependency syntactic knowledge augmented interactive architecture with multi-task learning for end-to-end ABSA. This model is capable of fully exploiting the syntactic knowledge (dependency relations and types) by leveraging a well-designed Dependency Relation Embedded Graph Convolutional Network (DreGcn) Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-04T14:59:32Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.