EG-RL：基于强化学习的时序图边梯度增强方法
Edge-Gradient Augmentation under Reinforcement Learning for Temporal Graph
AI 导读
研究者提出边缘梯度强化学习框架 EG-RL，通过节点与链接编码模块显式编码边的出现与消失事件，并利用策略驱动的强化学习机制动态选择最有信息量的边快照以增强时序图。该模型包含节点编码、链接编码、token 混合和通道混合等模块，在多个动态图数据集上显著提升了 AUC 与平均精度，消融实验验证了自适应边梯度增强的必要性。
正文 · 原文
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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16678 [cs.LG] |
| (or arXiv:2611.16678v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16678 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiawei Chen [view email]
[v1]
Thu, 12 Nov 2026 11:53:35 UTC (22,161 KB)
来源：arXiv cs.AI · arxiv.org