AI Paper Atlas

Research map / Continual learning / Online and replay-based

Capacity-Agnostic Parameter Isolation for Continual Graph Learning

Ye Xiao, Ruikun Li, Zhenyu Yang, Andrey Vasnev, Junbin Gao

ICML 2026 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use CAGNN decoupled subnetwork instead of WSN full-network propagationparameter-isolation GNN · OGB-Arxivruntime per epoch (ms): 787 -> 197Improved
use CAGNN instead of WSNparameter-isolation GNN · Synthetic CoraFull (140 tasks)memory (MB) at T140: 8980.4 -> 6296.2Improved
use task-specific context instead of random/all-ones/parameterized scores (ablation)CAGNN · Synthetic CoraFull (sparsity 0.99)parameter usage: 61.30% -> 22.45%Improved
use task-specific context instead of random/all-ones/parameterized scores (ablation)CAGNN · Synthetic CoraFull (sparsity 0.99)AP: 96.51±1.1 -> 97.05±0.3No clear effect
add differentiable proxy for mask learning (ablation)CAGNN · Aromaticity (sparsity 0.90)AP: 45.43±2.1 -> 49.28±1.2Improved
add differentiable proxy for mask learning (ablation)CAGNN · Cora (sparsity 0.90)AP: 93.97±1.2 -> 94.41±1.6No clear effect
add Fisher regularization (ablation)CAGNN · CoraFull (parameter utilization)parameter usageImproved
use both dendritic and low-rank masking instead of one stage (ablation)CAGNN · Computers (5 tasks)parameter usage: 44.50% -> 30.20%Improved
use both dendritic and low-rank masking instead of one stage (ablation)CAGNN · MNIST (5 tasks)AP: 96.89±1.2 -> 96.04±1.7No clear effect
use low-rank masking instead of neuron-wise masking (ablation)CAGNN · synthetic CoraFullconvergenceImproved
use only 10% warm-up epochs instead of longer warm-up (ablation)CAGNN · CoraFullparameter utilizationNo clear effect
increase sparsity / overlap ratio (ablation)CAGNN · CoraFull (35 tasks)accuracy vs zero-interferenceNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy