MDTE: Minority-Aware Diffusion over Temporal Edge Events for Imbalanced Node Classification
2026-08-25 • Machine Learning
Machine Learning
AI summaryⓘ
The authors address the problem of class imbalance in node classification on temporal graphs, where minority class nodes get overshadowed by majority ones over time. They propose MDTE, a method that carefully controls how information spreads between nodes to keep minority class characteristics clear and distinct. MDTE uses techniques to filter out misleading information and combines different perspectives to better identify minority classes. Experiments show that their method improves detection and classification of minority classes across multiple datasets.
class imbalancenode classificationtemporal graphsdiffusion denoisingLocal Outlier Factorpropagation filteringfeature reconstructiontopology predictionminority class detection
Authors
Zhou Zelong, Zhang Tianming, Yang Zhengyi, Tang Yifu, Hou Chenyu, Cao Bin, Fan Jing
Abstract
Class-imbalanced node classification on temporal graphs is challenging because majority-dominated temporal propagation progressively assimilates minority representations, while conventional node and neighborhood information provides insufficient discriminative evidence for minority classes. To address these issues, we propose MDTE, a minority-aware diffusion framework that reconstructs stable and discriminative temporal edge-event representations through conditional diffusion denoising. Specifically, MDTE introduces Distribution-Aware Selective Propagation, which combines Local Outlier Factor (LOF)-based propagation filtering with cluster-aware low-frequency propagation. The module preserves informative neighborhood dependencies while mitigating harmful propagation and majority-class information assimilation. It further develops Multi-View Discriminative Fusion, which exploits feature reconstruction and topology prediction to characterize class-wise differences in distribution learning and extracts complementary discriminability signals to guide denoising. Experiments on five real-world datasets demonstrate that MDTE consistently achieves the best performance on minority-class-oriented metrics, improving minority-class recall by up to 23.53 percentage points, minority-class F1 by 8.68 percentage points, and AUPRC by 2.67 percentage points over the strongest baselines.