Fully-inductive Node Classification on Arbitrary Graphs

TL;DR

This paper introduces GraphAny, a fully-inductive graph neural network model capable of generalizing to arbitrary test graphs with new structures, features, and labels, by leveraging an analytical solution and learned attention.

Contribution

GraphAny is the first model to handle fully-inductive node classification on arbitrary graphs with different feature and label spaces.

Findings

Achieves 67.26% accuracy on new graphs with minimal training data.

Outperforms all inductive baselines and transductive methods.

Demonstrates strong generalization to diverse graph structures.

Abstract

One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-inductive setup, where models should perform inference on arbitrary test graphs with new structures, feature and label spaces. We propose GraphAny as the first attempt at this challenging setup. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, which can be naturally applied to graphs with any feature and label spaces. To further build a stronger model with learning capacity, we fuse multiple LinearGNN predictions with learned inductive attention scores. Specifically, the attention module is carefully parameterized as a function of the entropy-normalized distance features between pairs of LinearGNN predictions to ensure generalization to new graphs. Empirically, GraphAny trained on a single Wisconsin dataset with only 120 labeled nodes can generalize to 30 new graphs with an average accuracy of 67.26%, surpassing not only all inductive baselines, but also strong transductive methods trained separately on each of the 30 test graphs.