Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs

TL;DR

Recurrent Event Network (RE-NET) introduces an autoregressive model for predicting future events in temporal knowledge graphs, effectively capturing sequential dependencies and outperforming existing methods on multiple datasets.

Contribution

The paper presents RE-NET, a novel autoregressive architecture that models future facts in temporal knowledge graphs using recurrent encoding and neighborhood aggregation.

Findings

Achieves state-of-the-art results on five datasets.

Excels in multi-step inference over future timestamps.

Effectively models sequential dependencies in temporal data.

Abstract

Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This paper proposes Recurrent Event Network (RE-NET), a novel autoregressive architecture for predicting future interactions. The occurrence of a fact (event) is modeled as a probability distribution conditioned on temporal sequences of past knowledge graphs. Specifically, our RE-NET employs a recurrent event encoder to encode past facts and uses a neighborhood aggregator to model the connection of facts at the same timestamp. Future facts can then be inferred in a sequential manner based on the two modules. We evaluate our proposed method via link prediction at future times on five public datasets. Through extensive experiments, we demonstrate the strength of RENET, especially on multi-step inference over future timestamps, and achieve state-of-the-art performance on all five datasets. Code and data can be found at https://github.com/INK-USC/RE-Net.