Inductive Graph Few-shot Class Incremental Learning

• URL: http://arxiv.org/abs/2411.06634v1
• Date: Mon, 11 Nov 2024 00:06:20 GMT
• Title: Inductive Graph Few-shot Class Incremental Learning
• Authors: Yayong Li, Peyman Moghadam, Can Peng, Nan Ye, Piotr Koniusz,
• Abstract summary: We introduce inductive GFSCIL that continually learns novel classes with newly emerging nodes. Compared to the transductive GFSCIL, the inductive setting exacerbates catastrophic forgetting due to inaccessible previous data. We propose a novel method, called Topology-based class Augmentation and Prototype calibration.
• Score: 34.19083477893245
• License:
• 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.

Related papers

• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [75.44877675117749]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph datasets Benchmark.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning [21.901331484173944]
  We analyze the causes of catastrophic forgetting in class incremental learning. We propose a two-stage learning framework with a fixed encoder and an incrementally updated prototype classifier. Our method does not rely on preserved samples of old classes, is thus a non-exemplar based CIL method.
  arXiv  Detail & Related papers  (2023-08-04T14:20:42Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Two-level Graph Network for Few-Shot Class-Incremental Learning [7.815043173207539]
  Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points. Existing FSCIL methods ignore the semantic relationships between sample-level and class-level. In this paper, we designed a two-level graph network for FSCIL named Sample-level and Class-level Graph Neural Network (SCGN)
  arXiv  Detail & Related papers  (2023-03-24T08:58:08Z)
• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [120.53458753007851]
  Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. We deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse. We propose a neural collapse inspired framework for FSCIL. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)
• Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification [56.17097897754628]
  We show that transductive linear probing with self-supervised graph contrastive pretraining can outperform the state-of-the-art fully supervised meta-learning based methods under the same protocol. We hope this work can shed new light on few-shot node classification problems and foster future research on learning from scarcely labeled instances on graphs.
  arXiv  Detail & Related papers  (2022-12-11T21:10:34Z)
• Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation [50.772432242082914]
  Existing graph neural network based methods mainly focus on classifying unlabeled nodes within fixed classes with abundant labeling. In this paper, we focus on this challenging but practical graph few-shot class-incremental learning (GFSCIL) problem and propose a novel method called Geometer. Instead of replacing and retraining the fully connected neural network classifer, Geometer predicts the label of a node by finding the nearest class prototype.
  arXiv  Detail & Related papers  (2022-05-27T13:02:07Z)
• Hierarchical Prototype Networks for Continual Graph Representation Learning [90.78466005753505]
  We present Hierarchical Prototype Networks (HPNs) which extract different levels of abstract knowledge in the form of prototypes to represent the continuously expanded graphs. We show that HPNs not only outperform state-of-the-art baseline techniques but also consume relatively less memory.
  arXiv  Detail & Related papers  (2021-11-30T14:15:14Z)
• Class-incremental Learning with Pre-allocated Fixed Classifiers [20.74548175713497]
  In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. We propose a novel fixed classifier in which a number of pre-allocated output nodes are subject to the classification loss right from the beginning of the learning phase.
  arXiv  Detail & Related papers  (2020-10-16T22:40:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.