Base3: a simple interpolation-based ensemble method for robust dynamic link prediction

Emma Kondrup

Keywords: Dynamic Link Prediction, Baselines, Temporal Graph Learning, Graph Machine Learning, Evaluation

TL;DR: Base3 is a simple, training-free ensemble method for dynamic link prediction that combines edge recurrence, node popularity, and temporal co-occurrence to achieve state-of-the-art performance on temporal graphs.

Abstract: Dynamic link prediction remains a central challenge in temporal graph learning, particularly in designing models that are both effective and practical for real-world deployment. Existing approaches often rely on complex neural architectures, which are computationally intensive and difficult to interpret. In this work, we build on the strong recurrence-based foundation of the EdgeBank baseline, by supplementing it with inductive capabilities. We do so by leveraging the predictive power of non-learnable signals from two complementary perspectives: historical edge recurrence, as captured by EdgeBank, and global node popularity, as introduced in the PopTrack model. We propose t-CoMem, a lightweight memory module that tracks temporal co-occurrence patterns and neighborhood activity. Building on this, we introduce Base3, an interpolation-based model that fuses EdgeBank, PopTrack, and t-CoMem into a unified scoring framework. This combination effectively bridges local and global temporal dynamics – repetition, popularity, and context – without relying on training. Evaluated on the Temporal Graph Benchmark, Base3 achieves performance competitive with state-of-the-art deep models and even outperforms them on several datasets. Notably, it considerably improves on existing baselines’ performance under more realistic and challenging negative sampling strategies –offering a simple yet robust alternative for temporal graph learning.

Format: Long paper, up to 8 pages.

Submission Number: 11