Analytic Drift Resister for Non-Exemplar Continual Graph Learning

TL;DR

This paper introduces ADR, a novel framework for continual graph learning that resists feature drift and catastrophic forgetting through hierarchical merging and classifier reconstruction, improving performance on node classification tasks.

Contribution

It proposes ADR, combining iterative backpropagation, hierarchical merging, and classifier reconstruction to enhance plasticity and prevent feature drift in NECGL.

Findings

ADR achieves competitive results on four node classification benchmarks.

Hierarchical Analytic Merging effectively prevents feature drift.

ACR enables zero-forgetting class-incremental learning.

Abstract

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.