AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning

Yu Feng, Zhen Tian, Haoran Luo, Xie Yu, Diancheng Cheng, Haoyue Zheng, Shuai Lyu, Ping Zong, Lianyuan Li, xin ge, Yifan Zhu

ICML 2026 · Continual learning › Domain and prompt-based · approach: Domain-incremental learning with memory · 0 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 energy factor (with regularization) to distance-only selection (ablation)HEDP · CDDB-Hard unknownaverage accuracy: 75.8 -> 83.74Improved
add distance factor to energy-regularized selection (ablation)HEDP · CDDB-Hard unknownaverage accuracy: 81.52 -> 83.74Improved
add energy regularization loss (boundary + midline) (ablation)energy-only HEDP · CDDB-Hard knownaverage accuracy: 78.83 -> 92.75Improved
add boundary loss only (ablation)energy-only HEDP · CDDB-Hard knownaverage accuracy: 78.83 -> 86.85Improved
add midline loss only (ablation)energy-only HEDP · CDDB-Hard knownaverage accuracy: 78.83 -> 91.63Improved
combine boundary and midline losses (ablation)energy-only HEDP · CDDB-Hard unknownaverage accuracy: 79.22 -> 81.52Improved
add energy regularization to energy-only selection (ablation)energy factor · DomainNet known(all)average accuracy: 66.84 -> 72.54Improved
add hybrid energy+distance factors (ablation)energy-regularized HEDP · CORe50 unknownaverage accuracy: 94.07 -> 94.66Improved
vary number of K-means clusters K (ablation)distance factor · CDDB, DomainNet, CORe50 unknownaverage accuracyNo clear effect
set alpha or beta to extreme 0.1 (ablation)hybrid factor weights · unknown domainsaverage accuracy: decrease of approximately 2-3 percentage pointsHurt
place energy boundary Theta too close to or too far from midline Delta (ablation)energy regularization · unknown domainsaverage accuracyHurt

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