Along the Time

Zhang, Fuwei; Zhang, Zhao; Ao, Xiang; Zhuang, Fuzhen; Xu, Yongjun; He, Qing

doi:10.1145/3511808.3557233

Cited by 9 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multiplication of two Complex numbers q 1 = a + bi, q 2 = c + di is defined by q 1 * q 2 = (ac − bd) + (ad + bc)i. It has been proved by previous works (Zhang et al 2022;Lacroix, Obozinski, and Usunier 2020;Xu et al 2020) to represent temporal knowledge graphs effectively. Following their work, we represent s, p, o, τ in complex space as:…”

Section: Embeddings In Geometric Subspacesmentioning

confidence: 94%

“…To capture heterogeneous structural and logical patterns in a temporal KG, we propose the HGE model which extends the complex space adopted by existing models (Zhang et al 2022;Lacroix, Obozinski, and Usunier 2020) to an attention-based product space. We introduce the key components of our temporal knowledge graph embedding method, HGE, in the following order: a) embedding space, b) temporal-relational attention, c) temporal-geometric attention.…”

Section: Embedding Model In Heterogeneous Geometric Subspacesmentioning

confidence: 99%

“…Existing embedding approaches such as TeRO, Rotate-QVS, and TLT-KGE (Xu et al 2020;Chen et al 2022;Zhang et al 2022) resorted to single underlying embedding spaces, such as Complex space or Quaternion space to model symmetric patterns by the rotations on a unit hypersphere. Other works (Chami et al 2020;Balazevic, Allen, and Hospedales 2019;Montella, Barahona, and Heinecke 2021;Han et al 2020) use hyperbolic space to preserve hierarchical patterns in temporal KGs.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, to deal with the evolution of patterns between entities, we propose the temporal-relational attention mechanism to balance static embedding and time-evolving embedding. We compare our TKGE model, heterogeneous geometric embedding (HGE), to TKGE methods in Complex space such as TComplEx (Lacroix, Obozinski, and Usunier 2020), TeRo (Xu et al 2020), TLT-KGE (Zhang et al 2022) and find that our model obtains better results for link prediction tasks in TKGs. In summary, the key contributions of this paper are as follows:…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Pan,

Nayyeri,

et al. 2024

AAAI

View full text Add to dashboard Cite

Temporal knowledge graphs represent temporal facts (s,p,o,?) relating a subject s and an object o via a relation label p at time ?, where ? 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.

show abstract

Section: Embeddings In Geometric Subspacesmentioning

confidence: 94%

Section: Embedding Model In Heterogeneous Geometric Subspacesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Pan,

Nayyeri,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Moreover, considering the temporal uncertainty during the evolution of entity/relationship representations over time, ATiSE maps the representations of temporal knowledge graphs into the space of multi-dimensional Gaussian distributions. EvoKG [27] captures the ever-changing structural and temporal dynamics in TKGs via recurrent event modeling and models the interactions between entities based on the temporal neighbourhood aggregation framework. Further, EvoKG achieves accurate modeling of event time using flexible and efficient mechanisms based on neural density estimation.…”

Section: Temporal Knowledge Graph Representationmentioning

confidence: 99%

A Temporal Knowledge Graph Embedding Model Based on Variable Translation

Han,

Lu,

Zhang

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Knowledge representation learning (KRL) aims to encode entities and relationships in various knowledge graphs into low-dimensional continuous vectors. It is popularly used in knowledge graph completion (or link prediction) tasks. Translation-based knowledge representation learning methods perform well in knowledge graph completion (KGC). However, the translation principles adopted by these methods are too strict and cannot model complex entities and relationships (i.e., N-1, 1-N, and N-N) well. Besides, these traditional translation principles are primarily used in static knowledge graphs and overlook the temporal properties of triplet facts. Therefore, we propose a temporal knowledge graph embedding model based on variable translation (TKGE-VT). The model proposes a new variable translation principle, which enables flexible transformation between entities and relationship embedding. Meanwhile, this paper considers the temporal properties of both entities and relationships and applies the proposed principle of variable translation to temporal knowledge graphs. We conduct link prediction and triplet classification experiments on four benchmark datasets: WN11, WN18, FB13, and FB15K. Our model outperforms baseline models on multiple evaluation metrics according to the experimental results.

show abstract

Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs Using Confidence-Augmented Reinforcement Learning

Ding,

Wu,

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Along the Time

Cited by 9 publications

References 26 publications

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

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

A Temporal Knowledge Graph Embedding Model Based on Variable Translation

Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs Using Confidence-Augmented Reinforcement Learning

Contact Info

Product

Resources

About