# Future Link Prediction Without Memory or Aggregation

arXiv: https://arxiv.org/abs/2505.19408 · HTML: https://mlsanity.com/paper/2505.19408/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [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)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [What graph neural networks cannot learn: depth vs width](https://mlsanity.com/paper/1907.03199/) (2019)
- [The Surprising Power of Graph Neural Networks with Random Node Initialization](https://mlsanity.com/paper/2010.01179/) (2020)
- [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)
- [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)
- [Streaming Graph Neural Networks](https://mlsanity.com/paper/1810.10627/) (2018)
- [TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning](https://mlsanity.com/paper/2105.07944/) (2021)
- [Neighborhood-aware Scalable Temporal Network Representation Learning](https://mlsanity.com/paper/2209.01084/) (2022)
- [TREND: TempoRal Event and Node Dynamics for Graph Representation Learning](https://mlsanity.com/paper/2203.14303/) (2022)
- [Revisiting Link Prediction: A Data Perspective](https://mlsanity.com/paper/2310.00793/) (2023)
- [A survey of dynamic graph neural networks](https://mlsanity.com/paper/2404.18211/) (2024)
- [On the Feasibility of Simple Transformer for Dynamic Graph Modeling](https://mlsanity.com/paper/2401.14009/) (2024)
- [TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics](https://mlsanity.com/paper/2502.02975/) (2025)
- [Stream Graphs and Link Streams for the Modeling of Interactions over Time](https://mlsanity.com/paper/1710.04073/) (2017)
- [Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions](https://mlsanity.com/paper/1909.10367/) (2019)
- [HOT: Higher-Order Dynamic Graph Representation Learning with Efficient Transformers](https://mlsanity.com/paper/2311.18526/) (2023)
- [An Empirical Evaluation of Temporal Graph Benchmark](https://mlsanity.com/paper/2307.12510/) (2023)
- [Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)](https://mlsanity.com/paper/2312.08520/) (2023)
- [Machine Learning on Dynamic Graphs: A Survey on Applications](https://mlsanity.com/paper/2401.08147/) (2024)

## Built on by (most cited first, 5 of 5)

- [Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph](https://mlsanity.com/paper/2601.23233/) (2026)
- [Where Does Neural Advantage Arise in Continuous-Time Dynamic Graph Prediction?](https://mlsanity.com/paper/2608.06765/) (2026)
- [What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation](https://mlsanity.com/paper/2607.22781/) (2026)
- [Back to All-Entity Ranking: Sampler-Dependent Evaluation in Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2607.27861/) (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)

Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize effectively across both types of edges. However, existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges. In this paper, we revisit the architecture of existing temporal graph models and identify two essential but overlooked modeling requirements for future link prediction: representing nodes with unique identifiers and performing target-aware matching between source and destination nodes. To this end, we propose Cross-Attention based Future Link Predictor on Temporal Graphs (CRAFT), a simple yet effective architecture that discards memory and aggregation modules and instead builds on two components: learnable node embeddings and cross-attention between the destination and the source's recent interactions. This design provides strong expressive power and enables target-aware modeling of the compatibility between candidate destinations and the source's interaction patterns. Extensive experiments on diverse datasets demonstrate that CRAFT consistently achieves superior performance with high efficiency, making it well-suited for large-scale real-world applications.