Representation learning methods have revolutionized machine learning on networks by converting discrete network structures into continuous domains. However, dynamic networks that evolve over time pose new challenges. To address this, dynamic representation learning methods have gained attention, offering benefits like reduced learning time and improved accuracy by utilizing temporal information. T-batching is a valuable technique for training dynamic network models that reduces training time while preserving vital conditions for accurate modeling. However, we have identified a limitation in the training loss function used with t-batching. Through mathematical analysis, we propose two alternative loss functions that overcome these issues, resulting in enhanced training performance. We extensively evaluate the proposed loss functions on synthetic and real-world dynamic networks. The results consistently demonstrate superior performance compared to the original loss function. Notably, in a real-world network characterized by diverse user interaction histories, the proposed loss functions achieved more than 26.9% enhancement in Mean Reciprocal Rank (MRR) and more than 11.8% improvement in Recall@10. These findings underscore the efficacy of the proposed loss functions in dynamic network modeling.

翻译：表示学习方法通过将离散网络结构转化为连续域，革新了网络上的机器学习。然而，随时间演化的动态网络带来了新的挑战。为此，动态表示学习方法通过利用时序信息，在减少学习时间与提升准确率方面展现出优势，受到了广泛关注。T-batching作为训练动态网络模型的重要技术，既能降低训练时间，又能维持精确建模所需的关键条件。然而，我们发现当前与T-batching结合使用的训练损失函数存在局限性。通过数学分析，我们提出两种替代损失函数以克服这些问题，从而提升训练性能。我们在合成动态网络和真实动态网络上对所提损失函数进行了全面评估。结果表明，相较于原始损失函数，新方法始终表现出更优性能。值得注意的是，在一个用户交互历史多样化的真实网络中，所提损失函数在平均倒数排名（MRR）上实现了超过26.9%的提升，在Recall@10指标上提升了超过11.8%。这些发现充分证明了所提损失函数在动态网络建模中的有效性。