# Inductive Graph Few-shot Class Incremental Learning

arXiv: https://arxiv.org/abs/2411.06634 · HTML: https://mlsanity.com/paper/2411.06634/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2107.08918/) (2021)
- [Overcoming Catastrophic Forgetting in Graph Neural Networks](https://mlsanity.com/paper/2012.06002/) (2020)
- [Inferring Networks of Substitutable and Complementary Products](https://mlsanity.com/paper/1506.08839/) (2015)
- [Few-Shot Class-Incremental Learning from an Open-Set Perspective](https://mlsanity.com/paper/2208.00147/) (2022)
- [MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2006.15524/) (2020)
- [Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.00426/) (2023)
- [CaT: Balanced Continual Graph Learning with Graph Condensation](https://mlsanity.com/paper/2309.09455/) (2023)
- [Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation](https://mlsanity.com/paper/2210.04524/) (2022)
- [Task-Adaptive Few-shot Node Classification](https://mlsanity.com/paper/2206.11972/) (2022)
- [Graph Few-shot Class-incremental Learning](https://mlsanity.com/paper/2112.12819/) (2021)
- [Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting](https://mlsanity.com/paper/2108.08165/) (2021)
- [Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation](https://mlsanity.com/paper/2205.13954/) (2022)
- [Subspace Distillation for Continual Learning](https://mlsanity.com/paper/2307.16419/) (2023)
- [Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)](https://mlsanity.com/paper/2305.05237/) (2023)
- [Supervised Graph Contrastive Learning for Few-shot Node Classification](https://mlsanity.com/paper/2203.15936/) (2022)
- [Multivariate Prototype Representation for Domain-Generalized Incremental Learning](https://mlsanity.com/paper/2309.13563/) (2023)

## Built on by (most cited first, 3 of 3)

- [Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2502.08181/) (2025)
- [Graph Self-Supervised Learning with Learnable Structural and Positional Encodings](https://mlsanity.com/paper/2502.16233/) (2025)
- [MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2610.04963/) (2026)

## Abstract (arXiv)

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.