AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets

Meng Liu, Ke Liang, Siwei Wang, Xingchen Hu, Sihang Zhou, Xinwang Liu

TPAMI 2025 · Graph learning › Knowledge and temporal graphs · approach: Continuous-time dynamic graph learning · 37 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
apply BenchTGC framework clustering modulesHTNE · arXivCSACC: 25.57 -> 41.49Improved
apply BenchTGC framework clustering modulesHTNE · arXivAIACC: 65.66 -> 76.06Improved
apply BenchTGC framework clustering modulesTREND · DBLPACC: 46.82 -> 55.10Improved
apply BenchTGC framework clustering modulesS2T · BrainACC: 34.32 -> 48.86Improved
apply BenchTGC framework across 5 temporal methods and 9 datasetstemporal graph methods · all 9 datasetsACC/NMI/ARI/F1: only 2 comparisons showed no improvement out of 180Improved
add BenchTGC modules to JODIE (cross-batch calibration)JODIE · all datasetsclusteringNo clear effect
add cluster-center modules to MNCIMNCI · all datasetsclusteringNo clear effect
use temporal interaction sequence instead of static adjacency matrixIJODIE/ITREND vs static methods · SchoolACC/NMI/ARI/F1: 48.32 -> 100.0Improved
use static adjacency-based clustering on large graphs instead of batched temporal trainingstatic clustering methods · arXivCS and largerGPU memory: 16.19 GB vs 8.93 GBHurt
reduce batch size to 1 (ablation)temporal methods · BrainruntimeHurt
reduce batch size to 1 (ablation)temporal methods · School/Brain/Patent/arXivAIGPU memory: below 0.5 GBImproved
increase batch size from 128 to 10000 (ablation)temporal methods · School/Brain/Patent/arXivAIruntime: less than 5 minutes per epochImproved

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