# Repeat-Aware Neighbor Sampling for Dynamic Graph Learning

arXiv: https://arxiv.org/abs/2405.17473 · HTML: https://mlsanity.com/paper/2405.17473/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [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)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [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)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries](https://mlsanity.com/paper/2206.11140/) (2022)
- [TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning](https://mlsanity.com/paper/2105.07944/) (2021)
- [Sampling methods for efficient training of graph convolutional networks: A survey](https://mlsanity.com/paper/2103.05872/) (2021)
- [A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models](https://mlsanity.com/paper/2107.13045/) (2021)
- [Modeling Personalized Item Frequency Information for Next-basket Recommendation](https://mlsanity.com/paper/2006.00556/) (2020)
- [DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph](https://mlsanity.com/paper/2210.10592/) (2022)
- [Motif Prediction with Graph Neural Networks](https://mlsanity.com/paper/2106.00761/) (2021)
- [Instant Graph Neural Networks for Dynamic Graphs](https://mlsanity.com/paper/2206.01379/) (2022)
- [CLARE: A Semi-supervised Community Detection Algorithm](https://mlsanity.com/paper/2210.08274/) (2022)
- [An Empirical Evaluation of Temporal Graph Benchmark](https://mlsanity.com/paper/2307.12510/) (2023)
- [Continuous-Time User Preference Modelling for Temporal Sets Prediction](https://mlsanity.com/paper/2204.05490/) (2022)
- [Representation Learning in Continuous-Time Dynamic Signed Networks](https://mlsanity.com/paper/2207.03408/) (2022)
- [Event-based Dynamic Graph Representation Learning for Patent Application Trend Prediction](https://mlsanity.com/paper/2308.09780/) (2023)
- [Predicting Music Relistening Behavior Using the ACT-R Framework](https://mlsanity.com/paper/2108.02138/) (2021)

## Built on by (most cited first, 11 of 11)

- [Efficient Neural Common Neighbor for Temporal Graph Link Prediction](https://mlsanity.com/paper/2406.07926/) (2024)
- [Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models](https://mlsanity.com/paper/2503.14411/) (2025)
- [TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer](https://mlsanity.com/paper/2506.00431/) (2025)
- [A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2505.04461/) (2025)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models](https://mlsanity.com/paper/2605.13540/) (2026)
- [FLASH: Flexible Learning of Adaptive Sampling from History in Temporal Graph Neural Networks](https://mlsanity.com/paper/2504.07337/) (2025)
- [Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction](https://mlsanity.com/paper/2511.12442/) (2025)
- [Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix](https://mlsanity.com/paper/2605.16112/) (2026)
- [ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability](https://mlsanity.com/paper/2605.19822/) (2026)
- [Back to All-Entity Ranking: Sampler-Dependent Evaluation in Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2607.27861/) (2026)

## Abstract (arXiv)

Dynamic graph learning equips the edges with time attributes and allows multiple links between two nodes, which is a crucial technology for understanding evolving data scenarios like traffic prediction and recommendation systems. Existing works obtain the evolving patterns mainly depending on the most recent neighbor sequences. However, we argue that whether two nodes will have interaction with each other in the future is highly correlated with the same interaction that happened in the past. Only considering the recent neighbors overlooks the phenomenon of repeat behavior and fails to accurately capture the temporal evolution of interactions. To fill this gap, this paper presents RepeatMixer, which considers evolving patterns of first and high-order repeat behavior in the neighbor sampling strategy and temporal information learning. Firstly, we define the first-order repeat-aware nodes of the source node as the destination nodes that have interacted historically and extend this concept to high orders as nodes in the destination node's high-order neighbors. Then, we extract neighbors of the source node that interacted before the appearance of repeat-aware nodes with a slide window strategy as its neighbor sequence. Next, we leverage both the first and high-order neighbor sequences of source and destination nodes to learn temporal patterns of interactions via an MLP-based encoder. Furthermore, considering the varying temporal patterns on different orders, we introduce a time-aware aggregation mechanism that adaptively aggregates the temporal representations from different orders based on the significance of their interaction time sequences. Experimental results demonstrate the superiority of RepeatMixer over state-of-the-art models in link prediction tasks, underscoring the effectiveness of the proposed repeat-aware neighbor sampling strategy.