Summary
MDTE is a minority-aware diffusion framework for class-imbalanced node classification on temporal graphs, proposed by Zhou Zelong, Zhang Tianming, Yang Zhengyi, Tang Yifu, Hou Chenyu and colleagues (arXiv:2608.24812). The method addresses the problem where majority-dominated temporal propagation progressively assimilates minority-class representations, leaving conventional node and neighborhood information insufficient for discriminating minority classes. MDTE reconstructs stable and discriminative temporal edge-event representations through conditional diffusion denoising. It introduces a Distribution-Aware Selective Propagation module combining Local Outlier Factor (LOF)-based propagation filtering with cluster-aware low-frequency propagation, which preserves informative neighborhood dependencies while mitigating harmful propagation and majority-class information assimilation. A multi-view discriminative fusion module leverages feature reconstruction and topology prediction to characterize class differences in distribution learning and extracts complementary discriminative signals to guide the denoising process. The paper targets machine learning researchers working on temporal graph learning and imbalanced classification.
Paper Overview
Field: Machine Learning
Authors: Zhou Zelong, Zhang Tianming, Yang Zhengyi, Tang Yifu, Hou Chenyu, et al.
Published: 2026-08-25
arXiv: 2608.24812
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, the authors 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. This module preserves informative neighborhood dependencies while mitigating harmful propagation and majority-class information assimilation.
The framework further develops multi-view discriminative fusion, leveraging feature reconstruction and topology prediction to characterize class differences during distribution learning and to extract complementary discriminative signals that guide the denoising process.
---
*Auto-collected on 2026-08-27*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634098