Guardado en:
Detalles Bibliográficos
Autores principales: Tavakkol, Sasan, Chen, Lin, Springer, Max, Schantz, Abigail, Bratanič, Blaž, Cohen-Addad, Vincent, Bateni, MohammadHossein
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.09544
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911103583256576
author Tavakkol, Sasan
Chen, Lin
Springer, Max
Schantz, Abigail
Bratanič, Blaž
Cohen-Addad, Vincent
Bateni, MohammadHossein
author_facet Tavakkol, Sasan
Chen, Lin
Springer, Max
Schantz, Abigail
Bratanič, Blaž
Cohen-Addad, Vincent
Bateni, MohammadHossein
contents Scarcity of labeled data, especially for rare events, hinders training effective machine learning models. This paper proposes SYNAPSE-G (Synthetic Augmentation for Positive Sampling via Expansion on Graphs), a novel pipeline leveraging Large Language Models (LLMs) to generate synthetic training data for rare event classification, addressing the cold-start problem. This synthetic data serve as seeds for semi-supervised label propagation on a similarity graph constructed between the seeds and a large unlabeled dataset. This identifies candidate positive examples, subsequently labeled by an oracle (human or LLM). The expanded dataset then trains/fine-tunes a classifier. We theoretically analyze how the quality (validity and diversity) of the synthetic data impacts the precision and recall of our method. Experiments on the imbalanced SST2 and MHS datasets demonstrate SYNAPSE-G's effectiveness in finding positive labels, outperforming baselines including nearest neighbor search.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification
Tavakkol, Sasan
Chen, Lin
Springer, Max
Schantz, Abigail
Bratanič, Blaž
Cohen-Addad, Vincent
Bateni, MohammadHossein
Machine Learning
Scarcity of labeled data, especially for rare events, hinders training effective machine learning models. This paper proposes SYNAPSE-G (Synthetic Augmentation for Positive Sampling via Expansion on Graphs), a novel pipeline leveraging Large Language Models (LLMs) to generate synthetic training data for rare event classification, addressing the cold-start problem. This synthetic data serve as seeds for semi-supervised label propagation on a similarity graph constructed between the seeds and a large unlabeled dataset. This identifies candidate positive examples, subsequently labeled by an oracle (human or LLM). The expanded dataset then trains/fine-tunes a classifier. We theoretically analyze how the quality (validity and diversity) of the synthetic data impacts the precision and recall of our method. Experiments on the imbalanced SST2 and MHS datasets demonstrate SYNAPSE-G's effectiveness in finding positive labels, outperforming baselines including nearest neighbor search.
title SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification
topic Machine Learning
url https://arxiv.org/abs/2508.09544