Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities

• URL: http://arxiv.org/abs/2604.10164v1
• Date: Sat, 11 Apr 2026 11:23:05 GMT
• Title: Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
• Abstract summary: Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts.<n>We propose TransFIR, a novel framework that leverages historical interaction sequences from semantically similar known entities to support inductive reasoning.
• Score: 54.48612448535698
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts. While existing methods are effective at capturing relational dynamics, their performance is limited by a closed-world assumption, which fails to account for emerging entities not present in the training. Notably, these entities continuously join the network without historical interactions. Empirical study reveals that emerging entities are widespread in TKGs, comprising roughly 25\% of all entities. The absence of historical interactions of these entities leads to significant performance degradation in reasoning tasks. Whereas, we observe that entities with semantic similarities often exhibit comparable interaction histories, suggesting the presence of transferable temporal patterns. Inspired by this insight, we propose TransFIR (Transferable Inductive Reasoning), a novel framework that leverages historical interaction sequences from semantically similar known entities to support inductive reasoning. Specifically, we propose a codebook-based classifier that categorizes emerging entities into latent semantic clusters, allowing them to adopt reasoning patterns from similar entities. Experimental results demonstrate that TransFIR outperforms all baselines in reasoning on emerging entities, achieving an average improvement of 28.6% in Mean Reciprocal Rank (MRR) across multiple datasets. The implementations are available at https://github.com/zhaodazhuang2333/TransFIR.

Related papers

• ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability [61.52935734819602]
  Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks.<n>TGNNs fail to identify which historical interactions most influence a given prediction.<n>We propose ST-TGExplainer, a self-explainable TGNN that disentangles Stability and Transition patterns in temporal graphs.
  arXiv  Detail & Related papers  (2026-05-19T13:16:22Z)
• GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series [5.364986293275663]
  We present textbfGenFacts, a novel generative framework for producing plausible and actionable counterfactual explanations.<n>We evaluate GenFacts on radar gesture recognition as an industrial use case and handwritten letter trajectories as an intuitive benchmark.
  arXiv  Detail & Related papers  (2025-09-25T09:22:19Z)
• Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning [20.195713621340403]
  Temporal Knowledge Graphs (TKGs) incorporate the temporal feature to express the transience of knowledge by describing when facts occur.<n>We propose a novel Disentangled Multi-span Evolutionary Network (DiMNet) for TKG reasoning.
  arXiv  Detail & Related papers  (2025-05-20T07:22:03Z)
• Learning Granularity Representation for Temporal Knowledge Graph Completion [2.689675451882683]
  Temporal Knowledge Graphs (TKGs) incorporate temporal information to reflect the dynamic structural knowledge and evolutionary patterns of real-world facts. This paper proposes textbfLearning textbfGranularity textbfRepresentation (termed $mathsfLGRe$) for TKG completion. It comprises two main components: Granularity Learning (GRL) and Adaptive Granularity Balancing (AGB)
  arXiv  Detail & Related papers  (2024-08-27T08:19:34Z)
• Beyond Transduction: A Survey on Inductive, Few Shot, and Zero Shot Link Prediction in Knowledge Graphs [2.1485350418225244]
  Knowledge graphs (KGs) comprise entities interconnected by relations of different semantic meanings. They inherently suffer from incompleteness, i.e. entities or facts about entities are missing. A larger body of works focuses on the completion of missing information in KGs, which is commonly referred to as link prediction (LP)
  arXiv  Detail & Related papers  (2023-12-08T12:13:40Z)
• Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation [59.417443739208146]
  We propose a new event forecasting model based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities. We evaluate our proposed model on five benchmark graphs.
  arXiv  Detail & Related papers  (2023-08-29T03:26:38Z)
• Generic Temporal Reasoning with Differential Analysis and Explanation [61.96034987217583]
  We introduce a novel task named TODAY that bridges the gap with temporal differential analysis. TODAY evaluates whether systems can correctly understand the effect of incremental changes. We show that TODAY's supervision style and explanation annotations can be used in joint learning.
  arXiv  Detail & Related papers  (2022-12-20T17:40:03Z)
• Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities [22.88552158340435]
  Existing inductive work assumes that new entities all emerge once in a batch. This study dives into a more realistic and challenging setting where new entities emerge in multiple batches. We propose a walk-based inductive reasoning model to tackle the new setting.
  arXiv  Detail & Related papers  (2022-08-22T14:59:19Z)
• Dynamic Relation Discovery and Utilization in Multi-Entity Time Series Forecasting [92.32415130188046]
  In many real-world scenarios, there could exist crucial yet implicit relation between entities. We propose an attentional multi-graph neural network with automatic graph learning (A2GNN) in this work.
  arXiv  Detail & Related papers  (2022-02-18T11:37:04Z)
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning [59.004025528223025]
  Key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps. We propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN)
  arXiv  Detail & Related papers  (2021-04-21T05:12:21Z)

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.