Task-Aware Adaptive Modulation: A Replay-Free and Resource-Efficient Approach For Continual Graph Learning

• URL: http://arxiv.org/abs/2509.00735v1
• Date: Sun, 31 Aug 2025 08:04:43 GMT
• Title: Task-Aware Adaptive Modulation: A Replay-Free and Resource-Efficient Approach For Continual Graph Learning
• Authors: Jingtao Liu, Xinming Zhang,
• Abstract summary: 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.<n>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.
• Score: 3.780931979011216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• TAAM:Inductive Graph-Class Incremental Learning with Task-Aware Adaptive Modulation [3.780931979011216]
  We propose Task-Aware Adaptive Modulation (TAAM) to guide the reasoning process of a fixed GNN backbone.<n>For each new task, a dedicated NSM is trained and then frozen, acting as an "expert module"<n>These modules perform detailed, node-attentive adaptive modulation on the computational flow of a shared GNN backbone.
  arXiv  Detail & Related papers  (2026-02-08T16:11:55Z)
• Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning [51.07663354001582]
  Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task.<n>We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches.<n>We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods.
  arXiv  Detail & Related papers  (2025-12-01T15:56:00Z)
• Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization [20.603433987118837]
  Drone-view Geo-Localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GPS-tagged satellite images.<n>Existing methods heavily rely on strictly pre-paired drone-satellite images for supervised learning.<n>We propose a novel end-to-end self-supervised learning method with a shallow backbone network.
  arXiv  Detail & Related papers  (2025-02-17T02:53:08Z)
• DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning [23.878495627964146]
  Continual learning aims to equip models with the ability to retain previously learned knowledge like a human.<n>Existing methods usually overlook the issue of information leakage caused by the fact that the experiment data have been used in pre-trained models.<n>In this paper, we propose a new LoRA-based rehearsal-free method named DESIRE.
  arXiv  Detail & Related papers  (2024-11-28T13:54:01Z)
• Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning [22.13331870720021]
  We propose a beyond prompt learning approach to the RFCL task, called Continual Adapter (C-ADA) C-ADA flexibly extends specific weights in CAL to learn new knowledge for each task and freezes old weights to preserve prior knowledge. Our approach achieves significantly improved performance and training speed, outperforming the current state-of-the-art (SOTA) method.
  arXiv  Detail & Related papers  (2024-07-14T17:40:40Z)
• Adaptive Retention & Correction: Test-Time Training for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task.<n>We name our approach Adaptive Retention & Correction (ARC)<n>ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN [20.380620709345898]
  Early-exiting dynamic neural networks (EDNN) allow a model to make some of its predictions from intermediate layers (i.e., early-exit) Training an EDNN architecture is challenging as it consists of two intertwined components: the gating mechanism (GM) that controls early-exiting decisions and the intermediate inference modules (IMs) that perform inference from intermediate representations. We propose a novel architecture that connects these two modules. This leads to significant performance improvements on classification datasets and enables better uncertainty characterization capabilities.
  arXiv  Detail & Related papers  (2023-10-13T14:56:38Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One [60.5818387068983]
  Graph neural networks (GNN) suffer from severe inefficiency. We propose to decouple a multi-layer GNN as multiple simple modules for more efficient training. We show that the proposed framework is highly efficient with reasonable performance.
  arXiv  Detail & Related papers  (2023-04-20T07:21:32Z)
• Learning in Feedback-driven Recurrent Spiking Neural Networks using full-FORCE Training [4.124948554183487]
  We propose a supervised training procedure for RSNNs, where a second network is introduced only during the training. The proposed training procedure consists of generating targets for both recurrent and readout layers. We demonstrate the improved performance and noise robustness of the proposed full-FORCE training procedure to model 8 dynamical systems.
  arXiv  Detail & Related papers  (2022-05-26T19:01:19Z)
• Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement [56.40587594647692]
  We propose a novel transfer learning algorithm, introducing the idea of Target-awareness REpresentation Disentanglement (TRED) TRED disentangles the relevant knowledge with respect to the target task from the original source model and used as a regularizer during fine-tuning the target model. Experiments on various real world datasets show that our method stably improves the standard fine-tuning by more than 2% in average.
  arXiv  Detail & Related papers  (2020-10-16T17:45:08Z)
• Fast Few-Shot Classification by Few-Iteration Meta-Learning [173.32497326674775]
  We introduce a fast optimization-based meta-learning method for few-shot classification. Our strategy enables important aspects of the base learner objective to be learned during meta-training. We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-10-01T15:59:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.