AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Recurrent Temporal Revision Graph Networks

YIZHOU CHEN, Anxiang Zeng, Qingtao Yu, Kerui Zhang, Cao Yuanpeng, Kangle Wu, Guangda Huzhang, Han Yu, Zhiming Zhou

NeurIPS 2023 · Graph learning › Knowledge and temporal graphs · approach: Temporal graph neural architectures · 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
replace standard temporal neighbor aggregation with recurrent temporal revisionRTRGN · MovieLens, Wikipedia, UCI-FSN, and Ecommerce (2-layer link prediction)AP (%): 94.90\pm0.4 vs 85.33\pm0.5; 98.79\pm0.2 vs 98.38\pm0.2; 98.04\pm0.1 vs 93.48\pm0.4; 95.28\pm0.1 vs 85.59\pm0.2Improved
replace standard temporal neighbor aggregation with recurrent temporal revisionRTRGN · MovieLens, Wikipedia, UCI-FSN, and Ecommerce (2-layer link prediction)AP (%): 93.37\pm0.3 vs 83.43\pm0.5; 98.28\pm0.2 vs 97.85\pm0.2; 95.62\pm0.1 vs 83.58\pm0.3; 92.87\pm0.1 vs 84.31\pm0.2Improved
add heterogeneous revision (HR) (ablation)RTRGN · Oscillating CSLAccuracy: 16.67 -> 100.0Improved
add heterogeneous revision (HR) (ablation)RTRGN · Cuneiform WritingAccuracy: 96.43 -> 100.0Improved
remove the retained hidden state h_u^k(t^-) (ablation)RTRGN · MovieLens, Wikipedia, and UCIAUCHurt
remove neighbor revision r_u^k(t), leaving a pure RNN (ablation)RTRGN · MovieLens, Wikipedia, and UCIAUCHurt
remove neighbor state h_v^{k-1}(t) from temporal revision (ablation)RTRGN · MovieLens, Wikipedia, and UCIAUCNo clear effect
remove neighbor state change Δh_v^{k-1}(t) from temporal revision (ablation)RTRGN · MovieLens, Wikipedia, and UCIAUCHurt
remove lower-level neighbor revisions r_v^{k-1}(t) from temporal revision (ablation)RTRGN · MovieLens, Wikipedia, and UCIAUCHurt
replace GRU for FUNC_4 with a 2-layer MLP (ablation)RTRGN · 7 of 8 tested link prediction benchmarksAPHurt
replace the GRU state transition with weighted averaging (ablation)RTRGN · link prediction benchmarksperformanceHurt
use an RNN cell instead of a GRU for the state transition (ablation)RTRGN · link prediction benchmarksperformanceNo 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