GeoMix: Towards Geometry-Aware Data Augmentation

• URL: http://arxiv.org/abs/2407.10681v1
• Date: Mon, 15 Jul 2024 12:58:04 GMT
• Title: GeoMix: Towards Geometry-Aware Data Augmentation
• Authors: Wentao Zhao, Qitian Wu, Chenxiao Yang, Junchi Yan,
• Abstract summary: 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.
• Score: 76.09914619612812
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification. By synthesizing samples through the interpolation of features and labels, Mixup effectively addresses the issue of data scarcity. However, it has rarely been explored in graph learning tasks due to the irregularity and connectivity of graph data. Specifically, in node classification tasks, Mixup presents a challenge in creating connections for synthetic data. In this paper, we propose Geometric Mixup (GeoMix), a simple and interpretable Mixup approach leveraging in-place graph editing. It effectively utilizes geometry information to interpolate features and labels with those from the nearby neighborhood, generating synthetic nodes and establishing connections for them. We conduct theoretical analysis to elucidate the rationale behind employing geometry information for node Mixup, emphasizing the significance of locality enhancement-a critical aspect of our method's design. Extensive experiments demonstrate that our lightweight Geometric Mixup achieves state-of-the-art results on a wide variety of standard datasets with limited labeled data. Furthermore, it significantly improves the generalization capability of underlying GNNs across various challenging out-of-distribution generalization tasks. Our code is available at https://github.com/WtaoZhao/geomix.

Related papers

• DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts [70.21017141742763]
  Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. Existing methods generally use a fixed number of GNN layers to generate representations for all graphs. We propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN.
  arXiv  Detail & Related papers  (2024-11-05T11:46:27Z)
• IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors [15.281223268780694]
  Graph Neural Networks (GNNs) have shown great performance in various tasks. The common challenges in graphs are insufficient accurate (high-quality) labels and limited neighbors for nodes. Existing graph augmentation methods typically address only one of these challenges. We propose an elegant method called IntraMix to simultaneously address both challenges.
  arXiv  Detail & Related papers  (2024-05-02T02:38:32Z)
• Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization [51.913685334368104]
  We propose a novel graph invariant learning method based on invariant and variant patterns co-mixup strategy. Our method significantly outperforms state-of-the-art under various distribution shifts.
  arXiv  Detail & Related papers  (2023-12-18T07:26:56Z)
• S-Mixup: Structural Mixup for Graph Neural Networks [18.681950665186005]
  We propose a novel mixup augmentation for node classification called Structural Mixup (S-Mixup) S-Mixup obtains pseudo-labels for unlabeled nodes in a graph along with their prediction confidence via a Graph Neural Network (GNN) classifier. We demonstrate the effectiveness of S-Mixup evaluated on the node classification task.
  arXiv  Detail & Related papers  (2023-08-16T02:08:46Z)
• Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling [60.0185734837814]
  Graph neural networks (GNNs) have found extensive applications in learning from graph data. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures with techniques like graph augmentations. This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with the aim of augmenting their capacity to adapt to a diverse range of training graph structures.
  arXiv  Detail & Related papers  (2023-04-06T01:09:36Z)
• Deep Graph Clustering via Mutual Information Maximization and Mixture Model [6.488575826304023]
  We introduce a contrastive learning framework for learning clustering-friendly node embedding. Experiments on real-world datasets demonstrate the effectiveness of our method in community detection.
  arXiv  Detail & Related papers  (2022-05-10T21:03:55Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• 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)
• Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation [27.215800308343322]
  We present the first Mixup-like graph augmentation method at the graph-level called Graph Transplant. Our method identifies the sub-structure as a mix unit that can preserve the local information. We extensively validate our method with diverse GNN architectures on multiple graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-10T11:10:13Z)
• 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.