# Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction

arXiv: https://arxiv.org/abs/2105.13975 · HTML: https://mlsanity.com/paper/2105.13975/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 28 May 2021.

## Builds on (most cited first, 18 of 18)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Modeling polypharmacy side effects with graph convolutional networks](https://mlsanity.com/paper/1802.00543/) (2018)
- [Learning Discrete Structures for Graph Neural Networks](https://mlsanity.com/paper/1903.11960/) (2019)
- [Adaptive Sampling Towards Fast Graph Representation Learning](https://mlsanity.com/paper/1809.05343/) (2018)
- [End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion](https://mlsanity.com/paper/1811.04441/) (2018)
- [MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions](https://mlsanity.com/paper/1905.09558/) (2019)
- [CASTER: Predicting Drug Interactions with Chemical Substructure Representation](https://mlsanity.com/paper/1911.06446/) (2019)
- [Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning](https://mlsanity.com/paper/1909.11334/) (2019)
- [Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders](https://mlsanity.com/paper/1804.10850/) (2018)
- [GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks](https://mlsanity.com/paper/1910.02107/) (2019)

## Built on by (most cited first, 6 of 6)

- [A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs](https://mlsanity.com/paper/2206.04798/) (2022)
- [AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning](https://mlsanity.com/paper/2205.15319/) (2022)
- [A Unified View of Relational Deep Learning for Drug Pair Scoring](https://mlsanity.com/paper/2111.02916/) (2021)
- [Knowledge Graph Completion based on Tensor Decomposition for Disease Gene Prediction](https://mlsanity.com/paper/2302.09335/) (2023)
- [Multi-View Substructure Learning for Drug-Drug Interaction Prediction](https://mlsanity.com/paper/2203.14513/) (2022)
- [Scalable GNN-based Knowledge Graph Representation Learning with Efficient Message Passing](https://mlsanity.com/paper/2609.34499/) (2026)

## Abstract (arXiv)

Sampling is an established technique to scale graph neural networks to large graphs. Current approaches however assume the graphs to be homogeneous in terms of relations and ignore relation types, critically important in biomedical graphs. Multi-relational graphs contain various types of relations that usually come with variable frequency and have different importance for the problem at hand. We propose an approach to modeling the importance of relation types for neighborhood sampling in graph neural networks and show that we can learn the right balance: relation-type probabilities that reflect both frequency and importance. Our experiments on drug-drug interaction prediction show that state-of-the-art graph neural networks profit from relation-dependent sampling in terms of both accuracy and efficiency.