Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

by   Zhaocheng Zhu, et al.

Link prediction is a very fundamental task on graphs. Inspired by traditional path-based methods, in this paper we propose a general and flexible representation learning framework based on paths for link prediction. Specifically, we define the representation of a pair of nodes as the generalized sum of all path representations, with each path representation as the generalized product of the edge representations in the path. Motivated by the Bellman-Ford algorithm for solving the shortest path problem, we show that the proposed path formulation can be efficiently solved by the generalized Bellman-Ford algorithm. To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm. The NBFNet parameterizes the generalized Bellman-Ford algorithm with 3 neural components, namely INDICATOR, MESSAGE and AGGREGATE functions, which corresponds to the boundary condition, multiplication operator, and summation operator respectively. The NBFNet is very general, covers many traditional path-based methods, and can be applied to both homogeneous graphs and multi-relational graphs (e.g., knowledge graphs) in both transductive and inductive settings. Experiments on both homogeneous graphs and knowledge graphs show that the proposed NBFNet outperforms existing methods by a large margin in both transductive and inductive settings, achieving new state-of-the-art results.


page 1

page 2

page 3

page 4


Path-aware Siamese Graph Neural Network for Link Prediction

In this paper, we propose an algorithm of Path-aware Siamese Graph neura...

A Theory of Link Prediction via Relational Weisfeiler-Leman

Graph neural networks are prominent models for representation learning o...

A Joint Framework for Inductive Representation Learning and Explainable Reasoning in Knowledge Graphs

Despite their large-scale coverage, existing cross-domain knowledge grap...

Learning to Efficiently Propagate for Reasoning on Knowledge Graphs

Path-based methods are more appealing solutions than embedding methods f...

TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs

Conventional static knowledge graphs model entities in relational data a...

Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting

We study the knowledge extrapolation problem to embed new components (i....

Discriminative Predicate Path Mining for Fact Checking in Knowledge Graphs

Traditional fact checking by experts and analysts cannot keep pace with ...

Please sign up or login with your details

Forgot password? Click here to reset