# Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms

arXiv: https://arxiv.org/abs/2405.17182 · HTML: https://mlsanity.com/paper/2405.17182/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 53 references that are in the map.
- First posted on arXiv 27 May 2024.

## Builds on (most cited first, 21 of 21)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning](https://mlsanity.com/paper/2105.07944/) (2021)
- [Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities](https://mlsanity.com/paper/2302.01018/) (2023)
- [Neighborhood-aware Scalable Temporal Network Representation Learning](https://mlsanity.com/paper/2209.01084/) (2022)
- [Evaluating Link Prediction Methods](https://mlsanity.com/paper/1505.04094/) (2015)
- [Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach](https://mlsanity.com/paper/2011.13085/) (2020)
- [Contact patterns among high school students](https://mlsanity.com/paper/1409.5318/) (2014)
- [Stream Graphs and Link Streams for the Modeling of Interactions over Time](https://mlsanity.com/paper/1710.04073/) (2017)
- [Evaluating Link Prediction Accuracy on Dynamic Networks with Added and Removed Edges](https://mlsanity.com/paper/1607.07330/) (2016)
- [Stochastic Block Transition Models for Dynamic Networks](https://mlsanity.com/paper/1411.5404/) (2014)
- [Temporal graph models fail to capture global temporal dynamics](https://mlsanity.com/paper/2309.15730/) (2023)
- [Nonparametric Multi-group Membership Model for Dynamic Networks](https://mlsanity.com/paper/1311.2079/) (2013)
- [EvalNE: A Framework for Evaluating Network Embeddings on Link Prediction](https://mlsanity.com/paper/1901.09691/) (2019)

## Built on by (most cited first, 1 of 1)

- [Where Does Neural Advantage Arise in Continuous-Time Dynamic Graph Prediction?](https://mlsanity.com/paper/2608.06765/) (2026)

## Abstract (arXiv)

Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. Importantly, common evaluation pipelines usually calculate ranking or binary classification metrics, where the scores of observed interactions (positives) are compared with those of randomly generated ones (negatives). However, a single metric is not sufficient to fully capture the differences between DLP algorithms, and is prone to overly optimistic performance evaluation. Instead, an in-depth evaluation should reflect performance variations across different nodes, edges, and time segments. In this work, we contribute tools to perform such a comprehensive evaluation. (1) We propose Birth-Death diagrams, a simple but powerful visualization technique that illustrates the effect of time-based train-test splitting on the difficulty of DLP on a given dataset. (2) We describe an exhaustive taxonomy of negative sampling methods that can be used at evaluation time. (3) We carry out an empirical study of the effect of the different negative sampling strategies. Our comparison between heuristics and state-of-the-art memory-based methods on various real-world datasets confirms a strong effect of using different negative sampling strategies on the test Area Under the Curve (AUC). Moreover, we conduct a visual exploration of the prediction, with additional insights on which different types of errors are prominent over time.