AI Paper Atlas

Research map / Continual learning / Online and replay-based

Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory

Huiyan Xue, Xuming Ran, Yaxin Li, Qi Xu, Enhui Li, Yi Xu, Qiang Zhang

AAAI 2026 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation · 2 citations (OpenAlex)

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
add Selective Subnetwork DistillationSDMLP · Split CIFAR-10 (10k neurons, K=10)validation accuracy: 0.71 -> 0.81Improved
add Selective Subnetwork DistillationSDMLP · Split CIFAR-10 (1k neurons, K=10)validation accuracy: 0.63 -> 0.73Improved
add Selective Subnetwork DistillationSDMLP · Split CIFAR-100 (10k neurons, K=10)validation accuracy: 0.32 -> 0.43Improved
add Selective Subnetwork DistillationSDMLP · Split MNIST (10k neurons, K=10)validation accuracy: 0.53 -> 0.57Improved
combine SSD with EWCSSD · Split CIFAR-10 (10k neurons)validation accuracy: 0.81 -> 0.87Improved
combine SSD with EWCSSD · Split MNIST (10k neurons, K=10)validation accuracy: 0.57 -> 0.86Improved
add SSD to reduce forgettingSDMLP · Split CIFAR-10 (10k neurons)mean BWT: -0.1828 -> -0.1234Improved
add hierarchical (hidden + output) distillation on top of selective (ablation)SSD · Split CIFAR-10 (10k neurons)validation accuracy: 0.7874 -> 0.8083Improved
add selective Top-n filtering on top of hierarchical (ablation)SSD · Split CIFAR-10 (10k neurons)validation accuracy: 0.8056 -> 0.8083Improved
shift KD weight toward output logits (lambda 0.9 -> 0.1) (ablation)SSD · Split CIFAR-10 (10k neurons)validation accuracy: 0.7902 -> 0.8174Improved
vary Top-n between 200 and 1000 (ablation)SSD · Split CIFAR-10 (10k neurons)validation accuracy: 0.8081 (n=200) vs 0.8083 (n=1000)No clear effect
use higher distillation temperature (T = 6 or 8) (ablation)SSD · Split CIFAR-10 (10k neurons)validation accuracy: best 0.8174 at alpha 0.7, T 8.0Improved

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