Inductive Graph Few-shot Class Incremental Learning

TL;DR

This paper introduces an inductive approach for graph few-shot class incremental learning that continually learns new classes without accessing previous data, using topology-based augmentation and prototype calibration to mitigate forgetting and overfitting.

Contribution

It proposes TAP, a novel method combining multi-topology class augmentation and prototype calibration for inductive GFSCIL, addressing catastrophic forgetting and overfitting in a practical setting.

Findings

TAP improves generalization in inductive GFSCIL.

The method effectively mitigates catastrophic forgetting.

Experimental results on four datasets demonstrate superior performance.

Abstract

Node classification with Graph Neural Networks (GNN) under a fixed set of labels is well known in contrast to Graph Few-Shot Class Incremental Learning (GFSCIL), which involves learning a GNN classifier as graph nodes and classes growing over time sporadically. We introduce inductive GFSCIL that continually learns novel classes with newly emerging nodes while maintaining performance on old classes without accessing previous data. This addresses the practical concern of transductive GFSCIL, which requires storing the entire graph with historical data. Compared to the transductive GFSCIL, the inductive setting exacerbates catastrophic forgetting due to inaccessible previous data during incremental training, in addition to overfitting issue caused by label sparsity. Thus, we propose a novel method, called Topology-based class Augmentation and Prototype calibration (TAP). To be specific, it first creates a triple-branch multi-topology class augmentation method to enhance model generalization ability. As each incremental session receives a disjoint subgraph with nodes of novel classes, the multi-topology class augmentation method helps replicate such a setting in the base session to boost backbone versatility. In incremental learning, given the limited number of novel class samples, we propose an iterative prototype calibration to improve the separation of class prototypes. Furthermore, as backbone fine-tuning poses the feature distribution drift, prototypes of old classes start failing over time, we propose the prototype shift method for old classes to compensate for the drift. We showcase the proposed method on four datasets.