Intrusion-Free Graph Mixup
- URL: http://arxiv.org/abs/2110.09344v1
- Date: Mon, 18 Oct 2021 14:16:00 GMT
- Title: Intrusion-Free Graph Mixup
- Authors: Hongyu Guo and Yongyi Mao
- Abstract summary: We present a simple and yet effective regularization technique to improve the generalization of Graph Neural Networks (GNNs)
We leverage the recent advances in Mixup regularizer for vision and text, where random sample pairs and their labels are interpolated to create synthetic samples for training.
Our method can effectively regularize the graph classification learning, resulting in superior predictive accuracy over popular graph augmentation baselines.
- Score: 33.07540841212878
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a simple and yet effective interpolation-based regularization
technique to improve the generalization of Graph Neural Networks (GNNs). We
leverage the recent advances in Mixup regularizer for vision and text, where
random sample pairs and their labels are interpolated to create synthetic
samples for training. Unlike images or natural sentences, which embrace a grid
or linear sequence format, graphs have arbitrary structure and topology, which
play a vital role on the semantic information of a graph. Consequently, even
simply deleting or adding one edge from a graph can dramatically change its
semantic meanings. This makes interpolating graph inputs very challenging
because mixing random graph pairs may naturally create graphs with identical
structure but with different labels, causing the manifold intrusion issue. To
cope with this obstacle, we propose the first input mixing schema for Mixup on
graph. We theoretically prove that our mixing strategy can recover the source
graphs from the mixed graph, and guarantees that the mixed graphs are manifold
intrusion free. We also empirically show that our method can effectively
regularize the graph classification learning, resulting in superior predictive
accuracy over popular graph augmentation baselines.
Related papers
- GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation [13.317620250521124]
Source-free domain adaptation is a crucial machine learning topic, as it contains numerous applications in the real world.
Recent graph neural network (GNN) approaches can suffer from serious performance decline due to domain shift and label scarcity.
We propose a novel method named Graph Diffusion-based Alignment with Jigsaw (GALA), tailored for source-free graph domain adaptation.
arXiv Detail & Related papers (2024-10-22T01:32:46Z) - Robust Graph Structure Learning under Heterophily [12.557639223778722]
We propose a novel robust graph structure learning method to achieve a high-quality graph from heterophilic data for downstream tasks.
We first apply a high-pass filter to make each node more distinctive from its neighbors by encoding structure information into the node features.
Then, we learn a robust graph with an adaptive norm characterizing different levels of noise.
arXiv Detail & Related papers (2024-03-06T12:29:13Z) - Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph
Clustering [29.17784041837907]
We propose Adaptive Hybrid Graph Filter for Multi-View Graph Clustering (AHGFC)
AHGFC learns the node embedding based on the graph joint aggregation matrix.
Experimental results show that our proposed model performs well on six datasets containing homophilous and heterophilous graphs.
arXiv Detail & Related papers (2024-01-05T07:27:29Z) - Graph Mixup with Soft Alignments [49.61520432554505]
We study graph data augmentation by mixup, which has been used successfully on images.
We propose S-Mixup, a simple yet effective mixup method for graph classification by soft alignments.
arXiv Detail & Related papers (2023-06-11T22:04:28Z) - Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
Contrastive learning has emerged as a premier method for learning representations with or without supervision.
Recent studies have shown its utility in graph representation learning for pre-training.
We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
arXiv Detail & Related papers (2023-02-06T16:26:29Z) - Similarity-aware Positive Instance Sampling for Graph Contrastive
Pre-training [82.68805025636165]
We propose to select positive graph instances directly from existing graphs in the training set.
Our selection is based on certain domain-specific pair-wise similarity measurements.
Besides, we develop an adaptive node-level pre-training method to dynamically mask nodes to distribute them evenly in the graph.
arXiv Detail & Related papers (2022-06-23T20:12:51Z) - G-Mixup: Graph Data Augmentation for Graph Classification [55.63157775049443]
Mixup has shown superiority in improving the generalization and robustness of neural networks by interpolating features and labels between two random samples.
We propose $mathcalG$-Mixup to augment graphs for graph classification by interpolating the generator (i.e., graphon) of different classes of graphs.
Experiments show that $mathcalG$-Mixup substantially improves the generalization and robustness of GNNs.
arXiv Detail & Related papers (2022-02-15T04:09:44Z) - Line Graph Neural Networks for Link Prediction [71.00689542259052]
We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications.
In this formalism, a link prediction problem is converted to a graph classification task.
We propose to seek a radically different and novel path by making use of the line graphs in graph theory.
In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
arXiv Detail & Related papers (2020-10-20T05:54:31Z) - Multilevel Graph Matching Networks for Deep Graph Similarity Learning [79.3213351477689]
We propose a multi-level graph matching network (MGMN) framework for computing the graph similarity between any pair of graph-structured objects.
To compensate for the lack of standard benchmark datasets, we have created and collected a set of datasets for both the graph-graph classification and graph-graph regression tasks.
Comprehensive experiments demonstrate that MGMN consistently outperforms state-of-the-art baseline models on both the graph-graph classification and graph-graph regression tasks.
arXiv Detail & Related papers (2020-07-08T19:48:19Z)
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.