Dynamic link prediction is an important problem considered by many recent works proposing various approaches for learning temporal edge patterns. To assess their efficacy, models are evaluated on publicly available benchmark datasets involving continuous-time and discrete-time temporal graphs. However, as we show in this work, the suitability of common batch-oriented evaluation depends on the datasets' characteristics, which can cause two issues: First, for continuous-time temporal graphs, fixed-size batches create time windows with different durations, resulting in an inconsistent dynamic link prediction task. Second, for discrete-time temporal graphs, the sequence of batches can additionally introduce temporal dependencies that are not present in the data. In this work, we empirically show that this common evaluation approach leads to skewed model performance and hinders the fair comparison of methods. We mitigate this problem by reformulating dynamic link prediction as a link forecasting task that better accounts for temporal information present in the data. We provide implementations of our new evaluation method for commonly used graph learning frameworks.

翻译：动态链接预测是许多近期工作关注的重要问题，这些工作提出了多种学习时间边模式的方法。为评估其有效性，模型在涉及连续时间和离散时间时序图的公开基准数据集上进行测试。然而，正如本工作所示，常见的基于批次的评估方法适用性取决于数据集特征，这可能导致两个问题：第一，对于连续时间时序图，固定大小的批次会产生不同时长的时间窗口，导致动态链接预测任务不一致；第二，对于离散时间时序图，批次的序列可能额外引入数据中不存在的时间依赖性。本工作通过实验表明，这种常见评估方法会导致模型性能偏差，并阻碍方法的公平比较。我们通过将动态链接预测重新表述为链接预报任务来缓解此问题，该任务能更好地利用数据中的时间信息。我们为常用图学习框架提供了新评估方法的实现。