CID-TKG: Collaborative Historical Invariance and Evolutionary Dynamics Learning for Temporal Knowledge Graph Reasoning

• URL: http://arxiv.org/abs/2604.09600v1
• Date: Mon, 09 Mar 2026 03:28:57 GMT
• Title: CID-TKG: Collaborative Historical Invariance and Evolutionary Dynamics Learning for Temporal Knowledge Graph Reasoning
• Abstract summary: Temporal knowledge graph (TKG) reasoning aims to infer future facts at unseen timestamps from temporally evolving entities and relations.<n>We propose a novel collaborative learning framework for TKGR (dubbed CID-TKG) that integrates evolutionary dynamics and historical invariance semantics as an effective inductive bias for reasoning.
• Score: 30.500753683144378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal knowledge graph (TKG) reasoning aims to infer future facts at unseen timestamps from temporally evolving entities and relations. Despite recent progress, existing approaches still suffer from inherent limitations due to their inductive biases, as they predominantly rely on time-invariant or weakly time-dependent structures and overlook the evolutionary dynamics. To overcome this limitation, we propose a novel collaborative learning framework for TKGR (dubbed CID-TKG) that integrates evolutionary dynamics and historical invariance semantics as an effective inductive bias for reasoning. Specifically, CID-TKG constructs a historical invariance graph to capture long-term structural regularities and an evolutionary dynamics graph to model short-term temporal transitions. Dedicated encoders are then employed to learn representations from each structure. To alleviate semantic discrepancies across the two structures, we decompose relations into view-specific representations and align view-specific query representations via a contrastive objective, which promotes cross-view consistency while suppressing view-specific noise. Extensive experiments verify that our CID-TKG achieves state-of-the-art performance under extrapolation settings.

Related papers

• CHE-TKG: Collaborative Historical Evidence and Evolutionary Dynamics Learning for Temporal Knowledge Graph Reasoning [30.500753683144378]
  Temporal knowledge graph (TKG) reasoning aims to predict future events from historical facts.<n> CHE-TKG is a novel collaborative dual-view learning framework for TKG reasoning.
  arXiv  Detail & Related papers  (2026-05-06T08:58:17Z)
• Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains [50.66049136093248]
  We develop a time-aware structural causal model (SCM) that incorporates dynamic causal factors and the causal mechanism drifts.<n>We show that our method can yield the optimal causal predictor for each time domain.<n>Results on both synthetic and real-world datasets exhibit that SYNC can achieve superior temporal generalization performance.
  arXiv  Detail & Related papers  (2025-06-21T14:05:37Z)
• Towards Foundation Model on Temporal Knowledge Graph Reasoning [17.165969719351125]
  Temporal Knowledge Graphs (TKGs) store temporal facts with quadruple formats (s, p, o, t)<n>New model employs sinusoidal positional encodings to capture fine-grained temporal patterns.<n>PostRA demonstrates strong zero-shot performance on unseen temporal knowledge graphs.
  arXiv  Detail & Related papers  (2025-06-04T09:19:49Z)
• 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)
• Learning Multi-graph Structure for Temporal Knowledge Graph Reasoning [3.3571415078869955]
  This paper proposes an innovative reasoning approach that focuses on Learning Multi-graph Structure (LMS) LMS incorporates an adaptive gate for merging entity representations both along and across timestamps effectively. It also integrates timestamp semantics into graph attention calculations and time-aware decoders.
  arXiv  Detail & Related papers  (2023-12-04T08:23:09Z)
• 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)
• DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph [59.583555454424]
  We propose a novel disenTangled representation learning framework for discrete-time Dynamic graphs, namely DyTed. We specially design a temporal-clips contrastive learning task together with a structure contrastive learning to effectively identify the time-invariant and time-varying representations respectively.
  arXiv  Detail & Related papers  (2022-10-19T14:34:12Z)
• Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs [13.230166885504202]
  We investigate a realistic but underexplored problem, called few-shot temporal knowledge graph reasoning. It aims to predict future facts for newly emerging entities based on extremely limited observations in evolving graphs. We propose a novel Meta Temporal Knowledge Graph Reasoning framework.
  arXiv  Detail & Related papers  (2022-10-16T22:40:33Z)
• An Empirical Study: Extensive Deep Temporal Point Process [61.14164208094238]
  We first review recent research emphasis and difficulties in modeling asynchronous event sequences with deep temporal point process.<n>We propose a Granger causality discovery framework for exploiting the relations among multi-types of events.
  arXiv  Detail & Related papers  (2021-10-19T10:15:00Z)
• Interpretable Time-series Representation Learning With Multi-Level Disentanglement [56.38489708031278]
  Disentangle Time Series (DTS) is a novel disentanglement enhancement framework for sequential data. DTS generates hierarchical semantic concepts as the interpretable and disentangled representation of time-series. DTS achieves superior performance in downstream applications, with high interpretability of semantic concepts.
  arXiv  Detail & Related papers  (2021-05-17T22:02:24Z)
• 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.