# From Link Prediction to Forecasting: Addressing Challenges in Batch-based Temporal Graph Learning

arXiv: https://arxiv.org/abs/2406.04897 · HTML: https://mlsanity.com/paper/2406.04897/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 64 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Builds on (most cited first, 28 of 28)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [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)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [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)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey](https://mlsanity.com/paper/2005.07496/) (2020)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Deep Learning for Time Series Forecasting: Tutorial and Literature Survey](https://mlsanity.com/paper/2004.10240/) (2020)
- [A Survey on Session-based Recommender Systems](https://mlsanity.com/paper/1902.04864/) (2019)
- [TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning](https://mlsanity.com/paper/2105.07944/) (2021)
- [TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs](https://mlsanity.com/paper/2203.14883/) (2022)
- [Dynamic Network Embedding Survey](https://mlsanity.com/paper/2103.15447/) (2021)
- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [Laplacian Change Point Detection for Dynamic Graphs](https://mlsanity.com/paper/2007.01229/) (2020)
- [DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training](https://mlsanity.com/paper/2307.07649/) (2023)
- [De Bruijn goes Neural: Causality-Aware Graph Neural Networks for Time Series Data on Dynamic Graphs](https://mlsanity.com/paper/2209.08311/) (2022)
- [PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks](https://mlsanity.com/paper/2402.04284/) (2024)
- [The Physics of Financial Networks](https://mlsanity.com/paper/2103.05623/) (2021)
- [Evolution of Conversations in the Age of Email Overload](https://mlsanity.com/paper/1504.00704/) (2015)
- [Effect of Choosing Loss Function when Using T-batching for Representation Learning on Dynamic Networks](https://mlsanity.com/paper/2308.06862/) (2023)
- [Leveraging Temporal Graph Networks Using Module Decoupling](https://mlsanity.com/paper/2310.02721/) (2023)

## Built on by (most cited first, 3 of 3)

- [What Do Temporal Graph Learning Models Learn?](https://mlsanity.com/paper/2510.09416/) (2025)
- [Stochastic Event Prediction via Temporal Motif Transitions](https://mlsanity.com/paper/2603.05874/) (2026)
- [Do Temporal Link Predictors Need Learned Memory? A Smoothed-Count Baseline with a Handful of Parameters](https://mlsanity.com/paper/2609.35364/) (2026)

## Abstract (arXiv)

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.