用提示词动态学习图数据，不遗忘旧知识且内存恒定
Prompt-Driven Continual Graph Learning
- 为每个任务学独立提示词，模型本身不变
- 在4个基准上优于现有方法，内存不随图规模增长
- 适合持续学习新图数据且关注隐私与效率的场景
持续图学习（CGL）旨在不断适应随时间演化的图数据，同时避免遗忘先前知识，当前主流方法依赖缓存历史数据重训模型，但面临可扩展性差和隐私风险。本文提出提示驱动的持续图学习框架（PROMPTCGL），为每个新任务学习独立提示词，保持图神经网络模型固定，自然避免灾难性遗忘。通过分层提示机制，从特征与拓扑双层面指导模型应对动态任务的多样性；设计个性化提示生成器，为每个节点生成定制提示，显著减少所需提示数量，实现与图规模无关的恒定内存消耗。在四个基准数据集上的实验表明，PROMPTCGL在性能上超越现有CGL方法，同时大幅降低内存开销。
原文摘要 · Abstract (English)
Continual Graph Learning (CGL), which aims to accommodate new tasks over evolving graph data without forgetting prior knowledge, is garnering significant research interest. Mainstream solutions adopt the memory replay-based idea, ie, caching representative data from earlier tasks for retraining the graph model. However, this strategy struggles with scalability issues for constantly evolving graphs and raises concerns regarding data privacy. Inspired by recent advancements in the prompt-based learning paradigm, this paper introduces a novel prompt-driven continual graph learning (PROMPTCGL) framework, which learns a separate prompt for each incoming task and maintains the underlying graph neural network model fixed. In this way, PROMPTCGL naturally avoids catastrophic forgetting of knowledge from previous tasks. More specifically, we propose hierarchical prompting to instruct the model from both feature- and topology-level to fully address the variability of task graphs in dynamic continual learning. Additionally, we develop a personalized prompt generator to generate tailored prompts for each graph node while minimizing the number of prompts needed, leading to constant memory consumption regardless of the graph scale. Extensive experiments on four benchmarks show that PROMPTCGL achieves superior performance against existing CGL approaches while significantly reducing memory consumption. Our code is available at https://github.com/QiWang98/PromptCGL.
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。