通过图稀疏化提升图神经网络置信预测效率
Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks
- 训练阶段引入参数化图稀疏模块，剔除无关边
- 平均降低预测集合大小32%，提升预测精度
- 适合需要高可靠性的图学习场景
置信预测是一种可靠的机器学习框架，能保证预测覆盖的可靠性。尽管近期研究已将置信预测应用于图神经网络，但大多集中在事后生成预测集。训练阶段的置信预测改进仍属空白。本文从去噪视角提出SparGCP，将图稀疏化与专用于置信预测的目标函数融入GNN训练。SparGCP采用参数化图稀疏模块，过滤掉与任务无关的边，从而提升置信预测效率。在多个真实图数据集上的实验表明，SparGCP优于现有方法，平均减少32%的预测集合大小，并可在消费级GPU上无缝扩展至大规模网络。
原文摘要 · Abstract (English)
Conformal Prediction is a robust framework that ensures reliable coverage across machine learning tasks. Although recent studies have applied conformal prediction to graph neural networks, they have largely emphasized post-hoc prediction set generation. Improving conformal prediction during the training stage remains unaddressed. In this work, we tackle this challenge from a denoising perspective by introducing SparGCP, which incorporates graph sparsification and a conformal prediction-specific objective into GNN training. SparGCP employs a parameterized graph sparsification module to filter out task-irrelevant edges, thereby improving conformal prediction efficiency. Extensive experiments on real-world graph datasets demonstrate that SparGCP outperforms existing methods, reducing prediction set sizes by an average of 32\% and scaling seamlessly to large networks on commodity GPUs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。