paper-with-me

홈 › Papers

Graph Neural Network Generalization with Gaussian Mixture Model Based Augmentation

2024-11-13 · Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Amine Mohamed Aboussalah, Michalis Vazirgiannis

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.

📄 PDF Abstract BibTeX arXiv:2411.08638

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDiversityGraph ClassificationGraph Neural Network

Similar Papers 제목 키워드 기반

Graph Community Augmentation with GMM-based Modeling in Latent Space

2024-12-02 · Shintaro Fukushima, Kenji Yamanishi

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 Generation

Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories

2023-02-07 · Suyu Ge, Chenyan Xiong, Corby Rosset, Arnold Overwijk 외

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 Generalization

An augmentation strategy to mimic multi-scanner variability in MRI

2021-03-23 · Maria Ines Meyer, Ezequiel de la Rosa, Nuno Barros, Roberto Paolella 외

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 Augmentation

SC-MAD: Mixtures of Higher-order Networks for Data Augmentation

2023-09-14 · Madeline Navarro, Santiago Segarra

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 Augmentation

Understanding Contrastive Learning via Gaussian Mixture Models

2024-11-05 · Parikshit Bansal, Ali Kavis, Sujay Sanghavi

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