Learning Adaptive Propagation for Knowledge Graph Reasoning

05/30/2022
by   Yongqi Zhang, et al.
0

Due to the success of Graph Neural Networks (GNNs) in learning from graph-structured data, various GNN-based methods have been introduced to learn from knowledge graphs (KGs). In this paper, to reveal the key factors underneath existing GNN-based methods, we revisit exemplar works from the lens of the propagation path. We find that the answer entity can be close to queried one, but the information dependency can be long. Thus, better reasoning performance can be obtained by exploring longer propagation paths. However, identifying such a long-range dependency in KG is hard since the number of involved entities grows exponentially. This motivates us to learn an adaptive propagation path that filters out irrelevant entities while preserving promising targets during the propagation. First, we design an incremental sampling mechanism where the close and promising target can be preserved. Second, we design a learning-based sampling distribution to identify the targets with fewer involved entities. In this way, GNN can go deeper to capture long-range information. Extensive experiments show that our method is efficient and achieves state-of-the-art performances in both transductive and inductive reasoning settings, benefiting from the deeper propagation.

READ FULL TEXT
research
06/07/2022

Learning to Efficiently Propagate for Reasoning on Knowledge Graphs

Path-based methods are more appealing solutions than embedding methods f...
research
02/03/2023

LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation

Recent works have demonstrated the benefits of capturing long-distance d...
research
03/22/2023

Logical Expressiveness of Graph Neural Network for Knowledge Graph Reasoning

Graph Neural Networks (GNNs) have been recently introduced to learn from...
research
06/29/2023

Exploring Exploiting High-Order Graph Structure for Sparse Knowledge Graph Completion

Sparse knowledge graph (KG) scenarios pose a challenge for previous Know...
research
04/07/2023

Rethinking GNN-based Entity Alignment on Heterogeneous Knowledge Graphs: New Datasets and A New Method

The development of knowledge graph (KG) applications has led to a rising...
research
09/24/2021

How Does Knowledge Graph Embedding Extrapolate to Unseen Data: a Semantic Evidence View

Knowledge Graph Embedding (KGE) aims to learn representations for entiti...
research
08/14/2023

Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis

The task of inductive knowledge graph completion requires models to lear...

Please sign up or login with your details

Forgot password? Click here to reset