解决生物图数据分类中的持续学习难题，防止遗忘且抗攻击。
Efficient and Robust Continual Graph Learning for Graph Classification in Biology
- 通过扰动采样和基序稀疏化，高效识别关键数据并压缩存储。
- 在多个生物图数据集上实现知识保留，分类性能稳定提升。
- 适合需要长期学习与安全性的生物医学图分析场景。
图分类对理解复杂的生物系统至关重要，分子结构与相互作用天然可表示为图。传统图神经网络（GNNs）在静态任务中表现良好，但在动态环境中易受灾难性遗忘影响。本文提出扰动与稀疏化持续图学习（PSCGL），一种针对生物数据集的高效且鲁棒的持续图学习框架。引入扰动采样策略以识别对模型学习有贡献的关键数据点，并采用基于基序的图稀疏化技术，在保持性能的同时降低存储需求。此外，该框架具备天然防御图后门攻击的能力，这对敏感的生物应用场景极为重要。在多个生物数据集上的大量实验表明，PSCGL不仅能够跨任务保留知识，还显著提升了图分类模型在生物学中的效率与鲁棒性。
原文摘要 · Abstract (English)
Graph classification is essential for understanding complex biological systems, where molecular structures and interactions are naturally represented as graphs. Traditional graph neural networks (GNNs) perform well on static tasks but struggle in dynamic settings due to catastrophic forgetting. We present Perturbed and Sparsified Continual Graph Learning (PSCGL), a robust and efficient continual graph learning framework for graph data classification, specifically targeting biological datasets. We introduce a perturbed sampling strategy to identify critical data points that contribute to model learning and a motif-based graph sparsification technique to reduce storage needs while maintaining performance. Additionally, our PSCGL framework inherently defends against graph backdoor attacks, which is crucial for applications in sensitive biological contexts. Extensive experiments on biological datasets demonstrate that PSCGL not only retains knowledge across tasks but also enhances the efficiency and robustness of graph classification models in biology.
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。