AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Global-Recent Semantic Reasoning on Dynamic Text-Attributed Graphs with Large Language Models

Yunan Wang, Jianxin Li, Ziwei Zhang

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 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
use node-centric implicit reasoning with sliding window for recent semantics (ablation)DyGRASP recent semantic reasoning · GDELTtoken consumption: 1.68B -> 0.10BImproved
use node-centric implicit reasoning with sliding window for recent semantics (ablation)DyGRASP recent semantic reasoning · Enrontoken consumption: 3.62B -> 0.86BImproved
use node-centric implicit reasoning with sliding window for recent semantics (ablation)DyGRASP recent semantic reasoning · Googlemaptoken consumption: 2.42B -> 0.35BImproved
use node-centric implicit reasoning with sliding window for recent semantics (ablation)DyGRASP recent semantic reasoning · Stack_electoken consumption: 7.00B -> 0.96BImproved
add DyGRASP recent-global semantic reasoning to TGATTGAT · GDELT destination retrieval (transductive)Hit@10 (%): 89.97 -> 91.96Improved
add DyGRASP recent-global semantic reasoning to TGATTGAT · Enron destination retrieval (transductive)Hit@10 (%): 89.12 -> 96.25Improved
add DyGRASP recent-global semantic reasoning to TGATTGAT · Googlemap destination retrieval (transductive)Hit@10 (%): 63.53 -> 82.79Improved
add DyGRASP recent-global semantic reasoning to TGATTGAT · Stack_elec destination retrieval (transductive)Hit@10 (%): 93.74 -> 99.74Improved
add DyGRASP recent-global semantic reasoning to DyGFormerDyGFormer · GDELT destination retrieval (transductive)Hit@10 (%): 91.64 -> 93.24Improved
add DyGRASP recent-global semantic reasoning to DyGFormerDyGFormer · Enron destination retrieval (transductive)Hit@10 (%): 92.04 -> 99.40Improved
add DyGRASP recent-global semantic reasoning to DyGFormerDyGFormer · Googlemap destination retrieval (transductive)Hit@10 (%): 51.32 -> 85.88Improved
add DyGRASP to DyGFormer on Googlemap (inductive)DyGFormer · Googlemap destination retrieval (inductive)Hit@10 (%): 43.84 -> 81.14Improved

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