HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces

• URL: http://arxiv.org/abs/2312.13680v2
• Date: Mon, 25 Dec 2023 09:20:07 GMT
• Title: HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
• Authors: Jiaxin Pan, Mojtaba Nayyeri, Yinan Li, Steffen Staab
• Abstract summary: Temporal knowledge graphs represent temporal facts $(s,p,o,tau)$ relating a subject $s$ and an object $o$ at time $tau$, where $tau$ could be a time point or time interval. We propose an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties.
• Score: 31.808046956138757
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Temporal knowledge graphs represent temporal facts $(s,p,o,\tau)$ relating a subject $s$ and an object $o$ via a relation label $p$ at time $\tau$, where $\tau$ could be a time point or time interval. Temporal knowledge graphs may exhibit static temporal patterns at distinct points in time and dynamic temporal patterns between different timestamps. In order to learn a rich set of static and dynamic temporal patterns and apply them for inference, several embedding approaches have been suggested in the literature. However, as most of them resort to single underlying embedding spaces, their capability to model all kinds of temporal patterns was severely limited by having to adhere to the geometric property of their one embedding space. We lift this limitation by an embedding approach that maps temporal facts into a product space of several heterogeneous geometric subspaces with distinct geometric properties, i.e.\ Complex, Dual, and Split-complex spaces. In addition, we propose a temporal-geometric attention mechanism to integrate information from different geometric subspaces conveniently according to the captured relational and temporal information. Experimental results on standard temporal benchmark datasets favorably evaluate our approach against state-of-the-art models.

Related papers

• Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding [23.39851202825318]
  temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately. Existing TKG approaches face two main challenges, i.e., the limited capability to model arbitrary timestamps continuously and the lack of rich inference patterns under temporal constraints. We propose an innovative TKGE method (PTBox) via decomposition-based temporal representation and embedding-based entity representation.
  arXiv  Detail & Related papers  (2024-05-01T07:27:04Z)
• IME: Integrating Multi-curvature Shared and Specific Embedding for Temporal Knowledge Graph Completion [97.58125811599383]
  Temporal Knowledge Graphs (TKGs) incorporate a temporal dimension, allowing for a precise capture of the evolution of knowledge. We propose a novel Multi-curvature shared and specific Embedding (IME) model for TKGC tasks. IME incorporates two key properties, namely space-shared property and space-specific property.
  arXiv  Detail & Related papers  (2024-03-28T23:31:25Z)
• Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space [20.235189945656927]
  Temporal knowledge graph completion (TKGC) aims to fill in missing facts within a given temporal knowledge graph at a specific time. This paper advances beyond conventional approaches by introducing more expressive quaternion representations for TKGC within hypercomplex space.
  arXiv  Detail & Related papers  (2024-03-02T16:50:48Z)
• A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation [89.86345494602642]
  Existing methods are limited in weak-temporal modeling capability. We propose a Decoupled Scoupled Framework (DeST) to address the issues. DeST significantly outperforms current state-of-the-art methods with less computational complexity.
  arXiv  Detail & Related papers  (2023-12-10T09:11:39Z)
• Improving embedding of graphs with missing data by soft manifolds [51.425411400683565]
  The reliability of graph embeddings depends on how much the geometry of the continuous space matches the graph structure. We introduce a new class of manifold, named soft manifold, that can solve this situation. Using soft manifold for graph embedding, we can provide continuous spaces to pursue any task in data analysis over complex datasets.
  arXiv  Detail & Related papers  (2023-11-29T12:48:33Z)
• $\text{H}^2\text{TNE}$: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces [16.31067633778912]
  We propose a hyperbolic heterogeneous temporal network embedding model for temporal HINs. Specifically, we leverage a temporally and heterogeneously double-constrained random walk strategy to capture the structural and semantic information. Experimental results show that our method has superior performance on temporal link prediction and node classification compared with SOTA models.
  arXiv  Detail & Related papers  (2023-04-14T07:39:52Z)
• Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting [75.10017445699532]
  Recent have shifted their focus towards formulating traffic forecasting as atemporal graph modeling problem. We propose a novel approach for accurate traffic forecasting on road networks over multiple future time steps.
  arXiv  Detail & Related papers  (2021-11-25T08:45:14Z)
• Geometric Models for (Temporally) Attributed Description Logics [21.027712454317047]
  Attributed description logics (DLs) have been defined to bridge the gap between DL languages and knowledge graphs. This paper investigates their compatibility, focusing on the attributed version of a Horn dialect of the DL-Lite family. We show that a temporally attributed DL may not have a convex geometric model in general but we can recover geometric satisfiability by imposing some restrictions on the use of the temporal attributes.
  arXiv  Detail & Related papers  (2021-08-27T12:40:14Z)
• Quadric hypersurface intersection for manifold learning in feature space [52.83976795260532]
  manifold learning technique suitable for moderately high dimension and large datasets. The technique is learned from the training data in the form of an intersection of quadric hypersurfaces. At test time, this manifold can be used to introduce an outlier score for arbitrary new points.
  arXiv  Detail & Related papers  (2021-02-11T18:52:08Z)
• CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations [72.4716073597902]
  We propose a method to learn object Canonical Point Cloud Representations of dynamically or moving objects. We demonstrate the effectiveness of our method on several applications including shape reconstruction, camera pose estimation, continuoustemporal sequence reconstruction, and correspondence estimation.
  arXiv  Detail & Related papers  (2020-08-06T17:58:48Z)

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.