IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
- URL: http://arxiv.org/abs/2405.00957v1
- Date: Thu, 2 May 2024 02:38:32 GMT
- Title: IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
- Authors: Shenghe Zheng, Hongzhi Wang, Xianglong Liu,
- Abstract summary: Graph Neural Networks (GNNs) demonstrate excellent performance on graphs, with their core idea about aggregating neighborhood information and learning from labels.
The prevailing challenges in most graph datasets are Insufficient High-Quality Labels and Lack of Neighborhoods, resulting in weak GNNs.
We propose an elegant method called IntraMix to simultaneously address both of these two challenges.
- Score: 15.281223268780694
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Graph Neural Networks (GNNs) demonstrate excellent performance on graphs, with their core idea about aggregating neighborhood information and learning from labels. However, the prevailing challenges in most graph datasets are twofold of Insufficient High-Quality Labels and Lack of Neighborhoods, resulting in weak GNNs. Existing data augmentation methods designed to address these two issues often tackle only one. They may either require extensive training of generators, rely on overly simplistic strategies, or demand substantial prior knowledge, leading to suboptimal generalization abilities. To simultaneously address both of these two challenges, we propose an elegant method called IntraMix. IntraMix innovatively employs Mixup among low-quality labeled data of the same class, generating high-quality labeled data at minimal cost. Additionally, it establishes neighborhoods for the generated data by connecting them with data from the same class with high confidence, thereby enriching the neighborhoods of graphs. IntraMix efficiently tackles both challenges faced by graphs and challenges the prior notion of the limited effectiveness of Mixup in node classification. IntraMix serves as a universal framework that can be readily applied to all GNNs. Extensive experiments demonstrate the effectiveness of IntraMix across various GNNs and datasets.
Related papers
- GeoMix: Towards Geometry-Aware Data Augmentation [76.09914619612812]
Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification.
We propose Geometric Mixup (GeoMix), a simple and interpretable Mixup approach leveraging in-place graph editing.
arXiv Detail & Related papers (2024-07-15T12:58:04Z) - LOSS-GAT: Label Propagation and One-Class Semi-Supervised Graph
Attention Network for Fake News Detection [2.6396287656676725]
Loss-GAT is a semi-supervised and one-class approach for fake news detection.
We employ a two-step label propagation algorithm to categorize news into two groups: interest (fake) and non-interest (real)
arXiv Detail & Related papers (2024-02-13T12:02:37Z) - Efficient Heterogeneous Graph Learning via Random Projection [65.65132884606072]
Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs.
Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors.
We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
arXiv Detail & Related papers (2023-10-23T01:25:44Z) - Learning Strong Graph Neural Networks with Weak Information [64.64996100343602]
We develop a principled approach to the problem of graph learning with weak information (GLWI)
We propose D$2$PT, a dual-channel GNN framework that performs long-range information propagation on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities.
arXiv Detail & Related papers (2023-05-29T04:51:09Z) - Informative Pseudo-Labeling for Graph Neural Networks with Few Labels [12.83841767562179]
Graph Neural Networks (GNNs) have achieved state-of-the-art results for semi-supervised node classification on graphs.
The challenge of how to effectively learn GNNs with very few labels is still under-explored.
We propose a novel informative pseudo-labeling framework, called InfoGNN, to facilitate learning of GNNs with extremely few labels.
arXiv Detail & Related papers (2022-01-20T01:49:30Z) - 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) - Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive
Benchmark Study [100.27567794045045]
Training deep graph neural networks (GNNs) is notoriously hard.
We present the first fair and reproducible benchmark dedicated to assessing the "tricks" of training deep GNNs.
arXiv Detail & Related papers (2021-08-24T05:00:37Z) - Exploiting Heterogeneous Graph Neural Networks with Latent Worker/Task
Correlation Information for Label Aggregation in Crowdsourcing [72.34616482076572]
Crowdsourcing has attracted much attention for its convenience to collect labels from non-expert workers instead of experts.
We propose a novel framework based on graph neural networks for aggregating crowd labels.
arXiv Detail & Related papers (2020-10-25T10:12:37Z) - Contrastive and Generative Graph Convolutional Networks for Graph-based
Semi-Supervised Learning [64.98816284854067]
Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph.
A novel GCN-based SSL algorithm is presented in this paper to enrich the supervision signals by utilizing both data similarities and graph structure.
arXiv Detail & Related papers (2020-09-15T13:59:28Z) - Graphs, Entities, and Step Mixture [11.162937043309478]
We propose a new graph neural network that considers both edge-based neighborhood relationships and node-based entity features.
With intensive experiments, we show that the proposed GESM achieves state-of-the-art or comparable performances on eight benchmark graph datasets.
arXiv Detail & Related papers (2020-05-18T06:57:02Z)
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.