AI Paper Atlas

Research map / Continual learning / Online and replay-based

Hierarchical Prototype Networks for Continual Graph Representation Learning

Xikun Zhang, Dongjin Song, Dacheng Tao

TPAMI 2022 · Continual learning › Online and replay-based · approach: Dynamic expansion and isolation · 60 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 N-prototypes to A-prototypes (ablation)HPNs · Cora (3 tasks)accuracy mean (AM): 89.2 -> 91.7Improved
add C-prototypes on top of A- and N-prototypes (ablation)HPNs · Cora (3 tasks)accuracy mean (AM): 91.7 -> 93.7Improved
add L_div to L_cls (ablation)HPNs · Cora (3 tasks)accuracy mean (AM): 92.4 -> 92.9Improved
add L_dis to L_cls (ablation)HPNs · Cora (3 tasks)accuracy mean (AM): 92.4 -> 92.8Improved
add both L_div and L_dis to L_cls (ablation)HPNs · Cora (3 tasks)accuracy mean (AM): 92.4 -> 93.7Improved
add L_div and L_dis to L_cls (ablation)HPNs · Cora (3 tasks)forgetting mean (FM): +0.8 -> +0.6No clear effect
replace GAT+TWP/MAS-style continual learning baselines with HPNsGAT backbone · OGB-Arxiv (20 tasks)accuracy mean (AM): 81.8 -> 85.8Improved
use HPNs instead of joint training (GAT)OGB-Products · OGB-Products (23 tasks)accuracy mean (AM): 73.7 -> 80.1Improved
use HPNs instead of joint training (GAT)Cora · Cora (3 tasks)accuracy mean (AM): 93.9 -> 93.7No clear effect
use HPNs instead of GEM (replay) in memory useGAT on OGB-Products · OGB-Products (23 tasks)final parameter count: 2,220,032 -> 4,908Improved
increase number of AFEs and prototype dimension (ablation)HPNs · OGB-Arxiv (20 tasks)AM and FMImproved
vary prototype threshold t_A from 0.01 to 0.4 (ablation)HPNs · Cora (3 tasks)AM and FMNo clear effect

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