Graph Neural Network Generalization with Gaussian Mixture Model Based Augmentation
Graph Neural Networks (GNNs) have shown great promise in tasks like node and graph classification, but they often struggle to generalize, particularly to unseen or out-of-distribution (OOD) data. These challenges are exacerbated when training data is limited in size or diversity. To address these issues, we introduce a theoretical framework using Rademacher complexity to compute a regret bound on the generalization error and then characterize the effect of data augmentation. This framework informs the design of GRATIN, an efficient graph data augmentation algorithm leveraging the capability of Gaussian Mixture Models (GMMs) to approximate any distribution. Our approach not only outperforms existing augmentation techniques in terms of generalization but also offers improved time complexity, making it highly suitable for real-world applications.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDiversityGraph ClassificationGraph Neural NetworkSimilar Papers 제목 키워드 기반
Graph Community Augmentation with GMM-based Modeling in Latent Space
This study addresses the issue of graph generation with generative models. In particular, we are concerned with graph community augmentation problem, which refers to the problem of generating unseen or unfamiliar graphs …
Graph GenerationAugmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories
In this paper we improve the zero-shot generalization ability of language models via Mixture-Of-Memory Augmentation (MoMA), a mechanism that retrieves augmentation documents from multiple information corpora ("external m…
RetrievalZero-shot GeneralizationAn augmentation strategy to mimic multi-scanner variability in MRI
Most publicly available brain MRI datasets are very homogeneous in terms of scanner and protocols, and it is difficult for models that learn from such data to generalize to multi-center and multi-scanner data. We propose…
Data AugmentationSC-MAD: Mixtures of Higher-order Networks for Data Augmentation
The myriad complex systems with multiway interactions motivate the extension of graph-based pairwise connections to higher-order relations. In particular, the simplicial complex has inspired generalizations of graph neur…
Data AugmentationUnderstanding Contrastive Learning via Gaussian Mixture Models
Contrastive learning attempts to learn representations from un-labeled data; it does so via a loss function that encourages the embedding of a point to be close to that of its augmentations, and far from the embeddings o…
Contrastive LearningDimensionality Reduction