From Link Prediction to Forecasting: Addressing Challenges in Batch-based Temporal Graph Learning
This addresses evaluation challenges for researchers in temporal graph learning, though it is incremental as it focuses on improving assessment rather than introducing a new method.
The paper tackles the problem of skewed model performance and unfair comparisons in dynamic link prediction due to traditional batch-based evaluation, and proposes reformulating it as a link forecasting task to better account for temporal information.
Dynamic link prediction is an important problem considered in many recent works that propose approaches for learning temporal edge patterns. To assess their efficacy, models are evaluated on continuous-time and discrete-time temporal graph datasets, typically using a traditional batch-oriented evaluation setup. However, as we show in this work, a batch-oriented evaluation is often unsuitable and can cause several issues. Grouping edges into fixed-sized batches regardless of their occurrence time leads to information loss or leakage, depending on the temporal granularity of the data. Furthermore, fixed-size batches create time windows with different durations, resulting in an inconsistent dynamic link prediction task. In this work, we empirically show how traditional batch-based evaluation 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.