AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction

Tao Zou, Chengfeng Wu, Tianxi Liao, Junchen Ye, Bowen Du

AAAI 2026 · Graph learning › Knowledge and temporal graphs · approach: Continuous-time dynamic graph learning · 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
replace self-attention with the adaptive token mixer (GLFormer)DyGFormer · MOOC, transductive APAP: 87.52 -> 87.87Improved
replace self-attention with the adaptive token mixer (GLFormer)TGN · LastFM, transductive APAP: 77.07 -> 84.96Improved
replace self-attention with the adaptive token mixer (GLFormer)TGAT · Enron, transductive APAP: 71.12 -> 75.48Improved
replace self-attention with the adaptive token mixer (GLFormer)CAWN · Wikipedia, transductive APAP: 98.76 -> 98.67No clear effect
replace self-attention with MLP token mixerCAWN · MOOC, transductive APAP: 80.15 -> 82.86Improved
replace self-attention with average pooling over recent neighborsDyGFormer · MOOC, transductive APAP: 87.52 -> 84.91Hurt
replace self-attention with pooling or MLP (attention-free)five Transformer baselines · Wikipedia, MOOC, LastFM, EnronAPNo clear effect
remove learnable order parameters (w/o LP) (ablation)GLFormer · Wikipedia, MOOC, LastFM, EnronAPImproved
add relative-time weights (versus w/o RT) (ablation)GLFormer · Wikipedia, MOOC, LastFM, EnronAPImproved
use GELU instead of ReLU (ablation)GLFormer · Wikipedia, MOOC, LastFM, EnronAPImproved
add residual connections (versus w/o ResNet) (ablation)GLFormer · Wikipedia, MOOC, LastFM, EnronAPImproved
add channel mixers (versus w/o CM) (ablation)GLFormer · Wikipedia, MOOC, LastFM, EnronAPImproved

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