Introducing New Node Prediction in Graph Mining: Predicting All Links from Isolated Nodes with Graph Neural Networks
It addresses a novel problem in graph mining and social network analysis, focusing on zero-shot out-of-graph all-links prediction for isolated nodes.
This paper tackles the problem of predicting all links from a new, isolated node in a graph, a task termed new node prediction, and demonstrates that a Deep Graph Neural Network architecture can effectively solve this challenge in a bibliographic citation network.
This paper introduces a new problem in the field of graph mining and social network analysis called new node prediction. More technically, the task can be categorized as zero-shot out-of-graph all-links prediction. This challenging problem aims to predict all links from a new, isolated, and unobserved node that was previously disconnected from the graph. Unlike classic approaches to link prediction (including few-shot out-of-graph link prediction), this problem presents two key differences: (1) the new node has no existing links from which to extract patterns for new predictions; and (2) the goal is to predict not just one, but all the links of this new node, or at least a significant part of them. Experiments demonstrate that an architecture based on Deep Graph Neural Networks can learn to solve this challenging problem in a bibliographic citation network.