Efficient and Robust Continual Graph Learning for Graph Classification in Biology

2024-11-18 · Ding Zhang, Jane Downer, Can Chen, Ren Wang

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.

📄 PDF Abstract BibTeX arXiv:2411.11668

Code (0)

등록된 구현이 없습니다.

Tasks

Classification Graph Classification Graph Learning

Universal Graph Continual Learning

2023-08-27 · Thanh Duc Hoang, Do Viet Tung, Duy-Hung Nguyen, Bao-Sinh Nguyen 외

We address catastrophic forgetting issues in graph learning as incoming data transits from one to another graph distribution. Whereas prior studies primarily tackle one setting of graph continual learning such as increme…

Continual Learning Graph Classification Graph Learning Node Classification

Hybrid Approach of Relation Network and Localized Graph Convolutional Filtering for Breast Cancer Subtype Classification

2017-11-16 · Sungmin Rhee, Seokjun Seo, Sun Kim

Network biology has been successfully used to help reveal complex mechanisms of disease, especially cancer. On the other hand, network biology requires in-depth knowledge to construct disease-specific networks, but our c…

Classification Deep Learning General Classification Relation+2

PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation

2023-12-22 · Yilun Liu, Ruihong Qiu, Yanran Tang, Hongzhi Yin 외

When handling streaming graphs, existing graph representation learning models encounter a catastrophic forgetting problem, where previously learned knowledge of these models is easily overwritten when learning with newly…

Continual Learning Graph Learning Graph Representation Learning Node Classification+1

AGALE: A Graph-Aware Continual Learning Evaluation Framework

2024-06-03 · Tianqi Zhao, Alan Hanjalic, Megha Khosla

In recent years, continual learning (CL) techniques have made significant progress in learning from streaming data while preserving knowledge across sequential tasks, particularly in the realm of euclidean data. To foste…

Continual Learning Graph Learning Multi-Label Classification MUlTI-LABEL-ClASSIFICATION+1

Reinforced Continual Learning for Graphs

2022-09-04 · Appan Rakaraddi, Siew Kei Lam, Mahardhika Pratama, Marcus de Carvalho

Graph Neural Networks (GNNs) have become the backbone for a myriad of tasks pertaining to graphs and similar topological data structures. While many works have been established in domains related to node and graph classi…

class-incremental learning Class Incremental Learning Continual Learning Graph Classification+1