RCTEA: Richness-guided Co-training for Temporal Entity Alignment

• URL: http://arxiv.org/abs/2605.18255v1
• Date: Mon, 18 May 2026 11:55:03 GMT
• Title: RCTEA: Richness-guided Co-training for Temporal Entity Alignment
• Abstract summary: Temporal Entity Alignment (TEA) aims to identify equivalent entities across Temporal Knowledge Graphs (TKGs)<n>We propose the RCTEA framework, which jointly models both structural and temporal aspects of TKGs for entity alignment.<n>We introduce a dual-view neighborhood consensus algorithm that jointly refines the feature encoders to enforce local structural consistency of the predicted alignments.
• Score: 12.221149374732272
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal Entity Alignment (TEA), which aims to identify equivalent entities across Temporal Knowledge Graphs (TKGs), is crucial for integrating knowledge facts from multiple sources. However, existing TEA models often fail to capture the orthogonal yet complementary effects between structural and temporal features, and typically overlook the importance of information richness, a key factor for effective message passing in neural feature encoders. To address these limitations, we propose the RCTEA framework, which jointly models both structural and temporal aspects of TKGs for entity alignment. Specifically, we design a richness-guided attention mechanism along with an adaptive weighting strategy to facilitate effective feature fusion. To ensure robust alignment despite noisy entity contexts, we introduce a dual-view neighborhood consensus algorithm that jointly refines the feature encoders to enforce local structural consistency of the predicted alignments. Extensive experiments demonstrate the superiority of RCTEA, achieving state-of-the-art performance on public TEA benchmarks.

Related papers

• Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy [57.058369251551795]
  Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks.<n>We propose SCISE, a framework that preserves structural Integrity by synergizing community-aware sampling with constrained Structural Entropy.<n>We show that SCISE significantly outperforms state-of-the-art algorithms, with ablation studies and robustness analyses further validating its effectiveness and reliability for real-world large-scale graphs.
  arXiv  Detail & Related papers  (2026-07-06T07:55:53Z)
• Jointly Learning Structured Representations and Stabilized Affinity for Human Motion Segmentation [7.350724521347576]
  Human Motion Clustering (HMS) aims to partition a video into non-overlapping segments corresponding to different human motions.<n>For videos in the real world, raw frame-level features often violate the Unionof-Subspaces assumption and yield unsatisfactory segmentation performance.<n>We propose Temporal Deep Self-expressive subspace Clustering ( TDSC) which jointly learns temporally consistent structured representations and affinity for accurate and robust HMS.
  arXiv  Detail & Related papers  (2026-05-07T06:48:53Z)
• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering [75.50670592447219]
  Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes.<n>This survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives.
  arXiv  Detail & Related papers  (2026-03-21T14:15:34Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• SynergyKGC: Reconciling Topological Heterogeneity in Knowledge Graph Completion via Topology-Aware Synergy [5.188469894836893]
  We present SynergyKGC, an adaptive framework that advances traditional neighbor aggregation to an active Cross-Modal Synergy Expert.<n>By coupling a density-dependent Identity Anchoring strategy with a Double-tower Coherent Consistency architecture, SynergyKGC effectively reconciles topological heterogeneity while ensuring representational stability across training and inference phases.
  arXiv  Detail & Related papers  (2026-02-11T13:31:58Z)
• ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification [51.07970070817353]
  An ideal time series classification (TSC) should be able to capture invariant representations.<n>Current methods are largely unguided, lacking the semantic direction required to isolate truly universal features.<n>We propose an end-to-end Energy-Regularized Information for Shift-Robustness framework to enable guided and reliable feature disentanglement.
  arXiv  Detail & Related papers  (2025-08-19T12:13:41Z)
• Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation [66.40525136929398]
  Test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain, without re-accessing the source domain.<n>We propose Matcha, an innovative framework designed for effective and efficient adaptation to structure shifts in graphs.<n>We validate the effectiveness of Matcha on both synthetic and real-world datasets, demonstrating its robustness across various combinations of structure and attribute shifts.
  arXiv  Detail & Related papers  (2024-10-09T15:15:40Z)
• Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph Learning [26.57090339778029]
  We propose to model tasks in a unified probabilistic perspective, viewing them as predictions based on conditional information with shared dependencies. Based on this proposal, we introduce Unified Spatio-temporal Diffusion Models (USTD) to address the tasks uniformly. USTD is holistically designed, comprising a shared-temporal encoder and attention-based denoising decoders are task-specific.
  arXiv  Detail & Related papers  (2023-10-26T12:48:43Z)
• A Simple Temporal Information Matching Mechanism for Entity Alignment Between Temporal Knowledge Graphs [18.451872649228196]
  We propose a simple graph neural network (GNN) model combined with a temporal information matching mechanism. We also propose a method to generate unsupervised alignment seeds via the temporal information of TKG.
  arXiv  Detail & Related papers  (2022-09-20T12:27:34Z)
• Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization [74.34699679568818]
  Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. We propose a cross-modal consensus network (CO2-Net) to tackle this problem.
  arXiv  Detail & Related papers  (2021-07-27T04:21:01Z)

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.