Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs

By Woojeong Jin, Meng Qu, Xisen Jin, Xiang Ren. Conference on Empirical Methods in Natural Language Processing, 2019

493 citations recorded by the source corpus.

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 this https URL

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/77dbd2b3d28541f35efb505fd95a9a0830af4585

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xueqi Cheng
2. Jiafeng Guo
3. Yue Liu
4. Siwei Wang
5. Lingyuan Meng
6. Wenxuan Tu
7. Joakim Skarding
8. Bogdan Gabrys

Citations in the corpus

• Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey (2020, background): “RE-Net [95] encodes a dynamic knowledge graph by inte-”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, methodology): “RE-NET [151] applies the GCN and RNN models to capture the evolutional dynamics in temporal knowledge graphs to the query over time.”
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning (2021, methodology): “The former [4, 9, 21] attempts to infer missing facts from t0 to tT [16].”