Error-Aware Curriculum Learning for Biomedical Relation Classification

TL;DR

This paper introduces an error-aware curriculum learning framework utilizing GPT-4o to improve biomedical relation classification by analyzing errors, generating targeted remediations, and training models progressively on difficulty-ordered data.

Contribution

It presents a novel teacher-student curriculum learning approach with error analysis and targeted remediations, enhancing biomedical relation classification performance.

Findings

Achieved state-of-the-art results on 4 out of 5 PPI datasets

Improved DDI dataset performance

Maintained competitive results on ChemProt

Abstract

Relation Classification (RC) in biomedical texts is essential for constructing knowledge graphs and enabling applications such as drug repurposing and clinical decision-making. We propose an error-aware teacher--student framework that improves RC through structured guidance from a large language model (GPT-4o). Prediction failures from a baseline student model are analyzed by the teacher to classify error types, assign difficulty scores, and generate targeted remediations, including sentence rewrites and suggestions for KG-based enrichment. These enriched annotations are used to train a first student model via instruction tuning. This model then annotates a broader dataset with difficulty scores and remediation-enhanced inputs. A second student is subsequently trained via curriculum learning on this dataset, ordered by difficulty, to promote robust and progressive learning. We also construct a heterogeneous biomedical knowledge graph from PubMed abstracts to support context-aware RC. Our approach achieves new state-of-the-art performance on 4 of 5 PPI datasets and the DDI dataset, while remaining competitive on ChemProt.