EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs

02/15/2022
by   Namyong Park, et al.
17

How can we perform knowledge reasoning over temporal knowledge graphs (TKGs)? TKGs represent facts about entities and their relations, where each fact is associated with a timestamp. Reasoning over TKGs, i.e., inferring new facts from time-evolving KGs, is crucial for many applications to provide intelligent services. However, despite the prevalence of real-world data that can be represented as TKGs, most methods focus on reasoning over static knowledge graphs, or cannot predict future events. In this paper, we present a problem formulation that unifies the two major problems that need to be addressed for an effective reasoning over TKGs, namely, modeling the event time and the evolving network structure. Our proposed method EvoKG jointly models both tasks in an effective framework, which captures the ever-changing structural and temporal dynamics in TKGs via recurrent event modeling, and models the interactions between entities based on the temporal neighborhood aggregation framework. Further, EvoKG achieves an accurate modeling of event time, using flexible and efficient mechanisms based on neural density estimation. Experiments show that EvoKG outperforms existing methods in terms of effectiveness (up to 77 efficiency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/16/2022

Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs

In this paper, we investigate a realistic but underexplored problem, cal...
research
12/15/2020

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

Large knowledge graphs often grow to store temporal facts that model the...
research
06/27/2022

Geo-Situation for Modeling Causality of Geo-Events in Knowledge Graphs

This paper proposes a framework for representing and reasoning causality...
research
03/30/2020

Graph Hawkes Network for Reasoning on Temporal Knowledge Graphs

The Hawkes process has become a standard method for modeling self-exciti...
research
05/16/2017

Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs

The availability of large scale event data with time stamps has given ri...
research
05/08/2022

It's the Same Old Story! Enriching Event-Centric Knowledge Graphs by Narrative Aspects

Our lives are ruled by events of varying importance ranging from simple ...
research
10/10/2022

Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs

Answering factual questions with temporal intent over knowledge graphs (...

Please sign up or login with your details

Forgot password? Click here to reset