Related papers: Graph Mixup with Soft Alignments

Graph Mixup with Soft Alignments

URL: http://arxiv.org/abs/2306.06788v1
Date: Sun, 11 Jun 2023 22:04:28 GMT
Title: Graph Mixup with Soft Alignments
Authors: Hongyi Ling, Zhimeng Jiang, Meng Liu, Shuiwang Ji, Na Zou
Abstract summary: 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.
Score: 49.61520432554505
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: We study graph data augmentation by mixup, which has been used successfully on images. A key operation of mixup is to compute a convex combination of a pair of inputs. This operation is straightforward for grid-like data, such as images, but challenging for graph data. The key difficulty lies in the fact that different graphs typically have different numbers of nodes, and thus there lacks a node-level correspondence between graphs. In this work, we propose S-Mixup, a simple yet effective mixup method for graph classification by soft alignments. Specifically, given a pair of graphs, we explicitly obtain node-level correspondence via computing a soft assignment matrix to match the nodes between two graphs. Based on the soft assignments, we transform the adjacency and node feature matrices of one graph, so that the transformed graph is aligned with the other graph. In this way, any pair of graphs can be mixed directly to generate an augmented graph. We conduct systematic experiments to show that S-Mixup can improve the performance and generalization of graph neural networks (GNNs) on various graph classification tasks. In addition, we show that S-Mixup can increase the robustness of GNNs against noisy labels.

Related papers

Learning on Large Graphs using Intersecting Communities [13.053266613831447]
MPNNs iteratively update each node's representation in an input graph by aggregating messages from the node's neighbors. MPNNs might quickly become prohibitive for large graphs provided they are not very sparse. We propose approximating the input graph as an intersecting community graph (ICG) -- a combination of intersecting cliques.
arXiv Detail & Related papers (2024-05-31T09:26:26Z)
CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning [65.1042892570989]
We propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning. We employ two strategies, namely cross-view interaction and cross-graph interaction, for effective node representation learning. We transform node representations into graph-level representations via pooling operations for graph similarity computation.
arXiv Detail & Related papers (2022-05-30T13:20:26Z)
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)
Intrusion-Free Graph Mixup [33.07540841212878]
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.
arXiv Detail & Related papers (2021-10-18T14:16:00Z)
Scalable Graph Neural Networks for Heterogeneous Graphs [12.44278942365518]
Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities.
arXiv Detail & Related papers (2020-11-19T06:03:35Z)
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)
Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
arXiv Detail & Related papers (2020-06-19T13:09:44Z)
Wasserstein-based Graph Alignment [56.84964475441094]
We cast a new formulation for the one-to-many graph alignment problem, which aims at matching a node in the smaller graph with one or more nodes in the larger graph. We show that our method leads to significant improvements with respect to the state-of-the-art algorithms for each of these tasks.
arXiv Detail & Related papers (2020-03-12T22:31:59Z)

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