Guardado en:
Detalles Bibliográficos
Autores principales: Ali, Adnan, Li, Jinlong, Chen, Huanhuan, Bashir, Ali Kashif
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.15044
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917944211013632
author Ali, Adnan
Li, Jinlong
Chen, Huanhuan
Bashir, Ali Kashif
author_facet Ali, Adnan
Li, Jinlong
Chen, Huanhuan
Bashir, Ali Kashif
contents Graph contrastive learning (GCL) aims to contrast positive-negative counterparts to learn the node embeddings, whereas graph data augmentation methods are employed to generate these positive-negative samples. The variation, quantity, and quality of negative samples compared to positive samples play crucial roles in learning meaningful embeddings for node classification downstream tasks. Less variation, excessive quantity, and low-quality negative samples cause the model to be overfitted for particular nodes, resulting in less robust models. To solve the overfitting problem in the GCL paradigm, this study proposes a novel Cumulative Sample Selection (CSS) algorithm by comprehensively considering negative samples' quality, variations, and quantity. Initially, three negative sample pools are constructed: easy, medium, and hard negative samples, which contain 25%, 50%, and 25% of the total available negative samples, respectively. Then, 10% negative samples are selected from each of these three negative sample pools for training the model. After that, a decision agent module evaluates model training results and decides whether to explore more negative samples from three negative sample pools by increasing the ratio or keep exploiting the current sampling ratio. The proposed algorithm is integrated into a proposed graph contrastive learning framework named NegAmplify. NegAmplify is compared with the SOTA methods on nine graph node classification datasets, with seven achieving better node classification accuracy with up to 2.86% improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15044
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning
Ali, Adnan
Li, Jinlong
Chen, Huanhuan
Bashir, Ali Kashif
Machine Learning
Artificial Intelligence
Graph contrastive learning (GCL) aims to contrast positive-negative counterparts to learn the node embeddings, whereas graph data augmentation methods are employed to generate these positive-negative samples. The variation, quantity, and quality of negative samples compared to positive samples play crucial roles in learning meaningful embeddings for node classification downstream tasks. Less variation, excessive quantity, and low-quality negative samples cause the model to be overfitted for particular nodes, resulting in less robust models. To solve the overfitting problem in the GCL paradigm, this study proposes a novel Cumulative Sample Selection (CSS) algorithm by comprehensively considering negative samples' quality, variations, and quantity. Initially, three negative sample pools are constructed: easy, medium, and hard negative samples, which contain 25%, 50%, and 25% of the total available negative samples, respectively. Then, 10% negative samples are selected from each of these three negative sample pools for training the model. After that, a decision agent module evaluates model training results and decides whether to explore more negative samples from three negative sample pools by increasing the ratio or keep exploiting the current sampling ratio. The proposed algorithm is integrated into a proposed graph contrastive learning framework named NegAmplify. NegAmplify is compared with the SOTA methods on nine graph node classification datasets, with seven achieving better node classification accuracy with up to 2.86% improvement.
title From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.15044