paper-with-me

홈 › Papers

Continual Learning on Dynamic Graphs via Parameter Isolation

2023-05-23 · Peiyan Zhang, Yuchen Yan, Chaozhuo Li, Senzhang Wang, Xing Xie, Guojie Song, Sunghun Kim

Many real-world graph learning tasks require handling dynamic graphs where new nodes and edges emerge. Dynamic graph learning methods commonly suffer from the catastrophic forgetting problem, where knowledge learned for previous graphs is overwritten by updates for new graphs. To alleviate the problem, continual graph learning methods are proposed. However, existing continual graph learning methods aim to learn new patterns and maintain old ones with the same set of parameters of fixed size, and thus face a fundamental tradeoff between both goals. In this paper, we propose Parameter Isolation GNN (PI-GNN) for continual learning on dynamic graphs that circumvents the tradeoff via parameter isolation and expansion. Our motivation lies in that different parameters contribute to learning different graph patterns. Based on the idea, we expand model parameters to continually learn emerging graph patterns. Meanwhile, to effectively preserve knowledge for unaffected patterns, we find parameters that correspond to them via optimization and freeze them to prevent them from being rewritten. Experiments on eight real-world datasets corroborate the effectiveness of PI-GNN compared to state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2305.13825

Code (1)

jerry2398/pi-gnn 공식 구현 pytorch

Tasks

Continual LearningGraph Learning

Similar Papers 제목 키워드 기반

Towards guarantees for parameter isolation in continual learning

2023-10-02 · Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe, Thomas Hofmann

Deep learning has proved to be a successful paradigm for solving many challenges in machine learning. However, deep neural networks fail when trained sequentially on multiple tasks, a shortcoming known as catastrophic fo…

Continual Learning

Efficient Parameter Mining and Freezing for Continual Object Detection

2024-02-20 · Angelo G. Menezes, Augusto J. Peterlevitz, Mateus A. Chinelatto, André C. P. L. F. de Carvalho

Continual Object Detection is essential for enabling intelligent agents to interact proactively with humans in real-world settings. While parameter-isolation strategies have been extensively explored in the context of co…

Continual LearningIncremental LearningObjectobject-detection+1

Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates

2023-08-28 · Murat Onur Yildirim, Elif Ceren Gok Yildirim, Ghada Sokar, Decebal Constantin Mocanu 외

Continual learning (CL) refers to the ability of an intelligent system to sequentially acquire and retain knowledge from a stream of data with as little computational overhead as possible. To this end; regularization, re…

Continual Learning

Is Parameter Isolation Better for Prompt-Based Continual Learning?

2026-01-28 · Jiangyang Li, Chenhao Ding, Songlin Dong, Qiang Wang 외 arxiv

Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolating knowledge across tasks and resulting i…

Continual Learning

ScrollNet: Dynamic Weight Importance for Continual Learning

2023-08-31 · Fei Yang, Kai Wang, Joost Van de Weijer

The principle underlying most existing continual learning (CL) methods is to prioritize stability by penalizing changes in parameters crucial to old tasks, while allowing for plasticity in other parameters. The importanc…

Continual Learning