EG-RL：基于强化学习的时序图边梯度增强框架
Edge-Gradient Augmentation under Reinforcement Learning for Temporal Graph
搞图神经网络的可以看看这篇，把边的增删事件单独编码，再用 RL 挑有用的边快照来增强训练。比直接喂原始时序图的常见做法多了显式信号，AUROC 和 AP 都涨了，还附消融实验。做社交网络分析或推荐系统时序建模的团队值得跑一下代码对比基线。
arXiv 论文 2611.16678 提出 edge-gradient reinforced learning（EG-RL），针对时序链接预测任务显式编码边梯度事件，即边的诞生与消亡，而现有方法通常直接使用原始时序图数据，忽略了这类边变化信息。框架通过专门的节点编码和链接编码模块捕获边梯度事件，并用策略驱动的强化学习机制动态筛选和增强信息量最大的边快照，由 critic 反馈优化预测精度。
模型结构包含节点编码、链接编码、token mixing 和 channel mixing 四个模块，经全局池化后接入两层 MLP 分类器。在多个动态图数据集上的实验显示 AUROC 和 AP 均有明显提升，消融实验验证了自适应边梯度增强的必要性，以及编码模块和强化学习机制各自的有效性。
Edge-Gradient Augmentation under Reinforcement Learning for Temporal Graph
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.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：时序链接预测、强化学习、图神经网络、EG-RL，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Yongqing Zhou, Jiawei Chen, Wenjun Wang, Xinyu Wang, Wei Yu, Qiyao Peng），经 AITOP 多维评分管线结构化提炼。