Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition

Xu, Chengjin; Nayyeri, Mojtaba; Alkhoury, Fouad; Lehmann, Jens; Yazdi, Hamed Shariat

doi:10.48550/arxiv.1911.07893

Cited by 19 publications

(12 citation statements)

References 22 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The insight behind this branch is that knowledge in KBs evolves over time and historical statements/events drive the occurrence of new events. Therefore, their focus is more on extrapolation -predicting unseen entity relationships over time by modeling temporal dependencies of statements/events in KBs [6,10,21,25]. The most well-known model is Know-Evolve [21], which assumes that the occurrence of facts/events can be modeled as a multivariate temporal point process.…”

Section: Related Workmentioning

confidence: 99%

Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes

Cai,

Janowic,

Yan

et al. 2021

Preprint

View full text Add to dashboard Cite

Almost all statements in knowledge bases have a temporal scope during which they are valid. Hence, knowledge base completion (KBC) on temporal knowledge bases (TKB), where each statement may be associated with a temporal scope, has attracted growing attention. Prior works assume that each statement in a TKB must be associated with a temporal scope. This ignores the fact that the scoping information is commonly missing in a KB. Thus prior work is typically incapable of handling generic use cases where a TKB is composed of temporal statements with/without a known temporal scope. In order to address this issue, we establish a new knowledge base embedding framework, called TIME2BOX, that can deal with atemporal and temporal statements of different types simultaneously. Our main insight is that answers to a temporal query always belong to a subset of answers to a time-agnostic counterpart. Put differently, time is a filter that helps pick out answers to be correct during certain periods. We introduce boxes to represent a set of answer entities to a time-agnostic query. The filtering functionality of time is modeled by intersections over these boxes. In addition, we generalize current evaluation protocols on time interval prediction. We describe experiments on two datasets and show that the proposed method outperforms state-of-the-art (SOTA) methods on both link prediction and time prediction. CCS CONCEPTS• Computing methodologies → Knowledge representation and reasoning; Temporal reasoning.

show abstract

Section: Related Workmentioning

confidence: 99%

Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes

Cai,

Janowic,

Yan

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Existing TKGC methods can be broadly categorized into two lines of work. The first line uses shallow encoders with time-sensitive decoding functions to extend static KGC methods [7,11,17,35]. For example, [7] constrains entity and relation embeddings.…”

Section: Related Work 21 Temporal Kg Completionmentioning

confidence: 99%

TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challenging when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient training and inference while preserving its performance on historical knowledge. Recent work approaches TKG completion (TKGC) by augmenting the encoder-decoder framework with a time-aware encoding function. However, naively fine-tuning the model at every time step using these methods does not address the problems of 1) catastrophic forgetting, 2) the model's inability to identify the change of facts (e.g., the change of the political affiliation and end of a marriage), and 3) the lack of training efficiency. To address these challenges, we present the Time-aware Incremental Embedding (TIE) framework, which combines TKG representation learning, experience replay, and temporal regularization. We introduce a set of metrics that characterizes the intransigence of the model and propose a constraint that associates the deleted facts with negative labels.Experimental 1 results on Wikidata12k and YAGO11k datasets demonstrate that the proposed TIE framework reduces training time by about ten times and improves on the proposed metrics compared to vanilla full-batch training. It comes without a significant loss in performance for any traditional measures. Extensive ablation studies reveal performance trade-offs among different evaluation metrics, which is essential for decision-making around real-world TKG applications.

show abstract

“…DE-SIMPLE (Goel et al, 2020) provides diachronic entity embeddings inspired from diachronic word embeddings (Hamilton et al, 2016). Recently, ATISE (Xu et al, 2019) embeds entities and relations as a multi-dimensional Gaussian distributions which are time-sensitive. An advantage of ATISE is its ability to represent time uncertainty as the covariance of the Gaussian distributions.…”

Section: Time-aware Graph Embeddingsmentioning

confidence: 99%

“…The final models for evaluation were selected upon the MRR metric on the validation set. We re-train ATISE and TERO using the same parameters as mentionned in Xu et al (2019) and Xu et al (2020b) but varying dimensions. 5…”

Section: Implementation Detailsmentioning

confidence: 99%

Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures

Montella¹,

Rojas-Barahona²,

Heinecke³

2021

Preprint

View full text Add to dashboard Cite

Knowledge Graph (KG) completion has been excessively studied with a massive number of models proposed for the Link Prediction (LP) task. The main limitation of such models is their insensitivity to time. Indeed, the temporal aspect of stored facts is often ignored. To this end, more and more works consider time as a parameter to complete KGs. In this paper, we first demonstrate that, by simply increasing the number of negative samples, the recent ATTH model can achieve competitive or even better performance than the state-of-the-art on Temporal KGs (TKGs), albeit its nontemporality. We further propose HERCULES, a time-aware extension of ATTH model, which defines the curvature of a Riemannian manifold as the product of both relation and time. Our experiments show that both HERCULES and ATTH achieve competitive or new state-of-the-art performances on ICEWS04 and ICEWS05-15 datasets. Therefore, one should raise awareness when learning TKGs representations to identify whether time truly boosts performances.

show abstract

Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition

Cited by 19 publications

References 22 publications

Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes

Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes

TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion

Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures

Contact Info

Product

Resources

About