cs.LGNov 12, 2026

Edge-Gradient Augmentation under Reinforcement Learning for Temporal Graph

Authors: Yongqing Zhou, Jiawei Chen, Wenjun Wang, Xinyu Wang, Wei Yu, Qiyao Peng

Organizations: Tianjin University, Tianjin, China · Zhejiang Yuexiu University, Shaoxing, China

Abstract

Temporal link prediction is critical for understand- ing dynamic interactions in evolving networks, informing appli- cations ranging from social network analysis to recommendation systems. Existing methods typically rely on raw temporal graph data, often neglecting explicit edge-change information that can significantly improve predictive performance. To address this gap, we propose edge-gradient reinforced learning (EG-RL), a framework that explicitly encodes edge-gradient events (edge births and deaths) through dedicated node and link encoding modules. EG-RL uses a policy-driven reinforcement-learning mechanism to dynamically select and augment the most infor- mative edge snapshots, guided by critic-based feedback to opti- mize prediction accuracy. The model comprises distinct modules for node encoding, link encoding, token mixing, and channel mixing, integrated through global pooling and followed by a two-layer multilayer perceptron classifier. Extensive experiments on multiple dynamic graph datasets demonstrate substantial gains in area under the receiver operating characteristic curve and average precision. Ablation studies further confirm the necessity of adaptive edge-gradient augmentation and validate the effectiveness of the proposed encoding and reinforcement- learning mechanisms.

Figures & tables

Explore similar work

CardsList
  1. Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution

    Mar 9, 2026Hua Liu, Yanbin Wei, Fei Xing +3Dynamic Graph LearningTemporal Link Prediction

  2. A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction

    Feb 15, 2026Nafiseh Sadat Sajadi, Behnam Bahrak, Mahdi Jafari SiavoshaniTemporal GNNsLink Prediction

  3. MambaTG: Candidate-Aware State Space Modeling for Future Link Prediction on Temporal Graphs

    Nov 5, 2026Nguyen Hong Quan, Sitao Luan, Yilun Zheng +1Link PredictionTemporal Link Prediction