Inductive Linear Probing for Few-shot Node Classification
- URL: http://arxiv.org/abs/2306.08192v1
- Date: Wed, 14 Jun 2023 01:33:06 GMT
- Title: Inductive Linear Probing for Few-shot Node Classification
- Authors: Hirthik Mathavan, Zhen Tan, Nivedh Mudiam, Huan Liu
- Abstract summary: We conduct an empirical study to highlight the limitations of current frameworks in the inductive few-shot node classification setting.
We propose a simple yet competitive baseline approach specifically tailored for inductive few-shot node classification tasks.
- Score: 23.137926097692844
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Meta-learning has emerged as a powerful training strategy for few-shot node
classification, demonstrating its effectiveness in the transductive setting.
However, the existing literature predominantly focuses on transductive few-shot
node classification, neglecting the widely studied inductive setting in the
broader few-shot learning community. This oversight limits our comprehensive
understanding of the performance of meta-learning based methods on graph data.
In this work, we conduct an empirical study to highlight the limitations of
current frameworks in the inductive few-shot node classification setting.
Additionally, we propose a simple yet competitive baseline approach
specifically tailored for inductive few-shot node classification tasks. We hope
our work can provide a new path forward to better understand how the
meta-learning paradigm works in the graph domain.
Related papers
- Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Models [30.867447814409623]
Graph neural networks (GNNs) have great ability in node classification, a fundamental task on graphs.
We propose a novel approach that integrates Large Language Models (LLMs) and GNNs.
Our model in improving node classification accuracy with considerably limited labeled data, surpassing state-of-the-art baselines by significant margins.
arXiv Detail & Related papers (2024-07-19T02:34:10Z) - Few-Shot Learning on Graphs: from Meta-learning to Pre-training and
Prompting [56.25730255038747]
This survey endeavors to synthesize recent developments, provide comparative insights, and identify future directions.
We systematically categorize existing studies into three major families: meta-learning approaches, pre-training approaches, and hybrid approaches.
We analyze the relationships among these methods and compare their strengths and limitations.
arXiv Detail & Related papers (2024-02-02T14:32:42Z) - Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach [19.237565246362134]
We introduce a novel method, Hyperbolic GRAph Meta Learner (H-GRAM), for the tasks of node classification and link prediction.
H-GRAM learns transferable information from a set of support local subgraphs in the form of hyperbolic meta gradients and label hyperbolic protonets.
Our comparative analysis shows that H-GRAM effectively learns and transfers information in multiple challenging few-shot settings.
arXiv Detail & Related papers (2023-10-29T06:11:49Z) - Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive
Learning [72.3506897990639]
We propose a simple yet effective unsupervised meta-learning framework, coined Pseudo-supervised Contrast (PsCo) for few-shot classification.
PsCo outperforms existing unsupervised meta-learning methods under various in-domain and cross-domain few-shot classification benchmarks.
arXiv Detail & Related papers (2023-03-02T06:10:13Z) - 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) - A Simple Yet Effective Pretraining Strategy for Graph Few-shot Learning [38.66690010054665]
We propose a simple transductive fine-tuning based framework as a new paradigm for graph few-shot learning.
For pretraining, we propose a supervised contrastive learning framework with data augmentation strategies specific for few-shot node classification.
arXiv Detail & Related papers (2022-03-29T22:30:00Z) - Meta Propagation Networks for Graph Few-shot Semi-supervised Learning [39.96930762034581]
We propose a novel network architecture equipped with a novel meta-learning algorithm to solve this problem.
In essence, our framework Meta-PN infers high-quality pseudo labels on unlabeled nodes via a meta-learned label propagation strategy.
Our approach offers easy and substantial performance gains compared to existing techniques on various benchmark datasets.
arXiv Detail & Related papers (2021-12-18T00:11:56Z) - Uniting Heterogeneity, Inductiveness, and Efficiency for Graph
Representation Learning [68.97378785686723]
graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs.
A majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs.
We propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
arXiv Detail & Related papers (2021-04-04T23:31:39Z) - Fast Few-Shot Classification by Few-Iteration Meta-Learning [173.32497326674775]
We introduce a fast optimization-based meta-learning method for few-shot classification.
Our strategy enables important aspects of the base learner objective to be learned during meta-training.
We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach.
arXiv Detail & Related papers (2020-10-01T15:59:31Z) - Graph Prototypical Networks for Few-shot Learning on Attributed Networks [72.31180045017835]
We propose a graph meta-learning framework -- Graph Prototypical Networks (GPN)
GPN is able to perform textitmeta-learning on an attributed network and derive a highly generalizable model for handling the target classification task.
arXiv Detail & Related papers (2020-06-23T04:13:23Z)
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.