Logic and Commonsense-Guided Temporal Knowledge Graph Completion

  title={Logic and Commonsense-Guided Temporal Knowledge Graph Completion},
  author={Guanglin Niu and Bo Li},
  • Guanglin NiuBo Li
  • Published 30 November 2022
  • Computer Science
  • ArXiv
A temporal knowledge graph (TKG) stores the events de- rived from the data involving time. Predicting events is ex-tremely challenging due to the time-sensitive property of events. Besides, the previous TKG completion (TKGC) approaches cannot represent both the timeliness and the causal- ity properties of events, simultaneously. To address these challenges, we propose a L ogic and C ommonsense- G uided E mbedding model (LCGE) to jointly learn the time-sensitive representation involving… 

Figures and Tables from this paper



TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation

A new approach of TKG embedding, TeRo, which defines the temporal evolution of entity embedding as a rotation from the initial time to the current time in the complex vector space, and analyzes the effect of time granularity on link prediction over TKGs.

Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks

A new representation learning model for temporal knowledge graphs, namely CyGNet, based on a novel time-aware copy-generation mechanism that is not only able to predict future facts from the whole entity vocabulary, but also capable of identifying facts with repetition and accordingly predicting such future facts with reference to the known facts in the past.

Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings

A novel time-aware knowledge graph embebdding approach, TeLM, which performs 4th-order tensor factorization of a Temporal knowledge graph using a Linear temporal regularizer and Multivector embeddings and investigates the effect of the temporal dataset’s time granularity on temporal knowledge graph completion.

Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs

Know-Evolve is presented, a novel deep evolutionary knowledge network that learns non-linearly evolving entity representations over time that effectively predicts occurrence or recurrence time of a fact which is novel compared to prior reasoning approaches in multi-relational setting.

Diachronic Embedding for Temporal Knowledge Graph Completion

Novel models for temporal KG completion are built through equipping static models with a diachronic entity embedding function which provides the characteristics of entities at any point in time where only static entity features are provided.

Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs

This paper proposes Recurrent Event Network (RE-NET), a novel autoregressive architecture for predicting future interactions that employs a recurrent event encoder to encode past facts and uses a neighborhood aggregator to model the connection of facts at the same timestamp.

Learning Sequence Encoders for Temporal Knowledge Graph Completion

This work utilizes recurrent neural networks to learn time-aware representations of relation types which can be used in conjunction with existing latent factorization methods to incorporate temporal information.

HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

HyTE is a temporally aware KG embedding method which explicitly incorporates time in the entity-relation space by associating each timestamp with a corresponding hyperplane and not only performs KG inference using temporal guidance, but also predicts temporal scopes for relational facts with missing time annotations.

Temporal Knowledge Graph Completion Based on Time Series Gaussian Embedding

ATiSE, a temporal KG embedding model which incorporates time information into entity/relation representations by using Additive Time Series decomposition, is proposed and Experimental results show that ATiSE chieves the state-of-the-art on link prediction over four temporal KGs.

Deriving Validity Time in Knowledge Graph

This paper introduces the task of predicting time validity for unannotated edges as a variation of relational embedding, and adapt existing approaches, and explores the importance example selection and the incorporation of side information in the learning process.