paper-with-me

Papers

Analytic Drift Resister for Non-Exemplar Continual Graph Learning

2026-04-03 · Lei Song, Shihan Guan, Youyong Kong arxiv

Non-Exemplar Continual Graph Learning (NECGL) seeks to eliminate the privacy risks intrinsic to rehearsal-based paradigms by retaining solely class-level prototype representations rather than raw graph examples for mitigating catastrophic forgetting. However, this design choice inevitably precipitates feature drift. As a nascent alternative, Analytic Continual Learning (ACL) capitalizes on the intrinsic generalization properties of frozen pre-trained models to bolster continual learning performance. Nonetheless, a key drawback resides in the pronounced attenuation of model plasticity. To surmount these challenges, we propose Analytic Drift Resister (ADR), a novel and theoretically grounded NECGL framework. ADR exploits iterative backpropagation to break free from the frozen pre-trained constraint, adapting to evolving task graph distributions and fortifying model plasticity. Since parameter updates trigger feature drift, we further propose Hierarchical Analytic Merging (HAM), performing layer-wise merging of linear transformations in Graph Neural Networks (GNNs) via ridge regression, thereby ensuring absolute resistance to feature drift. On this basis, Analytic Classifier Reconstruction (ACR) enables theoretically zero-forgetting class-incremental learning. Empirical evaluation on four node classification benchmarks demonstrates that ADR maintains strong competitiveness against existing state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2604.02633

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningNode ClassificationContinual LearningGraph Learning

Similar Papers 제목 키워드 기반

Exemplar-free Continual Representation Learning via Learnable Drift Compensation

2024-07-11 · Alex Gomez-Villa, Dipam Goswami, Kai Wang, Andrew D. Bagdanov 외

Exemplar-free class-incremental learning using a backbone trained from scratch and starting from a small first task presents a significant challenge for continual representation learning. Prototype-based approaches, when…

class-incremental learningClass Incremental LearningContinual LearningExemplar-Free+2

Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation

2022-11-22 · Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov 외

We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of pre…

Continual LearningExemplar-Free

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

2024-05-29 · CVPR 2024 1 · Dipam Goswami, Albin Soutif--Cormerais, Yuyang Liu, Sandesh Kamath 외

Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential dri…

Continual LearningExemplar-Free

Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task

2024-05-28 · Huiping Zhuang, Di Fang, Kai Tong, Yuchen Liu 외

In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come…

Autonomous DrivingContinual LearningExemplar-Free

Instance-Prototype Affinity Learning for Non-Exemplar Continual Graph Learning

2025-05-15 · Lei Song, Jiaxing Li, Shihan Guan, Youyong Kong

Graph Neural Networks (GNN) endure catastrophic forgetting, undermining their capacity to preserve previously acquired knowledge amid the assimilation of novel information. Rehearsal-based techniques revisit historical e…

Contrastive LearningGraph LearningNode Classification