Online Continual Graph Learning
Continual Learning (CL) aims to incrementally acquire new knowledge while mitigating catastrophic forgetting. Within this setting, Online Continual Learning (OCL) focuses on updating models promptly and incrementally from single or small batches of observations from a data stream. Extending OCL to graph-structured data is crucial, as many real-world networks evolve over time and require timely, online predictions. However, existing continual or streaming graph learning methods typically assume access to entire graph snapshots or multiple passes over tasks, violating the efficiency constraints of the online setting. To address this gap, we introduce the Online Continual Graph Learning (OCGL) setting, which formalizes node-level continual learning on evolving graphs under strict memory and computational budgets. OCGL defines how a model incrementally processes a stream of node-level information while maintaining anytime inference and respecting resource constraints. We further establish a comprehensive benchmark comprising seven datasets and nine CL strategies, suitably adapted to the OCGL setting, enabling a standardized evaluation setup. Finally, we present a minimalistic yet competitive baseline for OCGL, inspired by our benchmarking results, that achieves strong empirical performance with high efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningGraph LearningSimilar Papers 제목 키워드 기반
Feature-based Graph Attention Networks Improve Online Continual Learning
Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving…
Continual LearningGraph Attentionimage-classificationImage ClassificationContinual Spatio-Temporal Graph Convolutional Networks
Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as the…
Action RecognitionSkeleton Based Action RecognitionTemporal Action LocalizationTemporal SequencesReshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation
Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environ…
Test-time AdaptationSafe Continual Reinforcement Learning Methods for Nonstationary Environments. Towards a Survey of the State of the Art
This work provides a state-of-the-art survey of continual safe online reinforcement learning (COSRL) methods. We discuss theoretical aspects, challenges, and open questions in building continual online safe reinforcement…
Reinforcement LearningContinual LearningThe Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offline training on task-specific subgraphs is…
Graph Learning