任务感知自适应调制：一种面向持续图学习的无回放且资源高效的方法
Task-Aware Adaptive Modulation: A Replay-Free and Resource-Efficient Approach For Continual Graph Learning
AI总结：
针对持续图学习中稳定性-可塑性失衡与预训练资源负担问题，提出无回放的任务感知自适应调制方法TAAM，通过原型引导的神经突触调制器动态调制冻结GNN骨干的计算流，在6个GCIL基准上全面超越SOTA。
摘要：
持续图学习（Continual Graph Learning, CGL）专注于在获取新知识的同时保留先前学习的信息，这对现实世界的图应用至关重要。当前方法面临两个主要问题：1）稳定性-可塑性困境：基于回放的方法往往会在该困境下产生失衡，同时带来高昂的存储成本。2）资源密集型预训练：主流的无回放方法严重依赖经过大规模预训练的骨干网络，这种依赖造成了巨大的资源负担。\n在本文中，我们认为克服这些挑战的关键不在于回放数据或微调整个网络，而在于动态调制冻结骨干网络的内部计算流。我们提出，轻量级的任务特定模块可以有效引导图神经网络（GNN）的推理过程。受这一洞见启发，我们提出了任务感知自适应调制（Task-Aware Adaptive Modulation, TAAM），这是一种无回放、资源高效的方法，为应对稳定性-可塑性困境开辟了新路径。\nTAAM的核心是其神经突触调制器（Neural Synapse Modulators, NSM），针对每个任务训练后会被冻结以存储专家知识。一种关键的原型引导策略管控这些调制器：1）在训练阶段，它通过从相似的过往调制器深度拷贝来初始化新的NSM，以促进知识迁移。2）在推理阶段，它为每个任务选择最相关的冻结NSM。这些NSM被插入到冻结的GNN骨干网络中，对其内部流执行细粒度的、节点注意力式的调制——这与先前方法的静态扰动不同。\n大量实验表明，在六个GCIL基准数据集上，TAAM全面优于当前最优方法。代码将在论文录用后发布。
英文摘要：
Continual Graph Learning(CGL)focuses on acquiring new knowledge while retaining previously learned information, essential for real-world graph applications. Current methods grapple with two main issues:1) The Stability-Plasticity Dilemma: Replay-based methods often create an imbalance between the Dilemma, while incurring significant storage costs.2) The Resource-Heavy Pre-training: Leading replay-free methods critically depend on extensively pre-trained backbones, this reliance imposes a substantial resource burden.In this paper, we argue that the key to overcoming these challenges lies not in replaying data or fine-tuning the entire network, but in dynamically modulating the internal computational flow of a frozen backbone. We posit that lightweight, task-specific modules can effectively steer a GNN's reasoning process. Motivated by this insight, we propose Task-Aware Adaptive Modulation(TAAM), a replay-free, resource-efficient approach that charts a new path for navigating the stability-plasticity dilemma. TAAM's core is its Neural Synapse Modulators(NSM), which are trained and then frozen for each task to store expert knowledge. A pivotal prototype-guided strategy governs these modulators: 1) For training, it initializes a new NSM by deep-copying from a similar past modulator to boost knowledge transfer. 2) For inference, it selects the most relevant frozen NSM for each task. These NSMs insert into a frozen GNN backbone to perform fine-grained, node-attentive modulation of its internal flow-different from the static perturbations of prior methods. Extensive experiments show that TAAM comprehensively outperforms state-of-the-art methods across six GCIL benchmark datasets. The code will be released upon acceptance of the paper.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
