# Multi-Relational Graph Neural Network for Out-of-Domain Link Prediction

arXiv: https://arxiv.org/abs/2403.11292 · HTML: https://mlsanity.com/paper/2403.11292/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 17 Mar 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications](https://mlsanity.com/paper/1709.07604/) (2017)
- [Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs](https://mlsanity.com/paper/1803.08035/) (2018)
- [A Gentle Introduction to Deep Learning for Graphs](https://mlsanity.com/paper/1912.12693/) (2019)
- [Graph Meta Network for Multi-Behavior Recommendation](https://mlsanity.com/paper/2110.03969/) (2021)
- [An Attention-based Collaboration Framework for Multi-View Network Representation Learning](https://mlsanity.com/paper/1709.06636/) (2017)
- [M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems](https://mlsanity.com/paper/2005.10110/) (2020)
- [Lightweight Compositional Embeddings for Incremental Streaming Recommendation](https://mlsanity.com/paper/2202.02427/) (2022)

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

- [Real-time and personalized product recommendations for large e-commerce platforms](https://mlsanity.com/paper/2506.21368/) (2025)

## Abstract (arXiv)

Dynamic multi-relational graphs are an expressive relational representation for data enclosing entities and relations of different types, and where relationships are allowed to vary in time. Addressing predictive tasks over such data requires the ability to find structure embeddings that capture the diversity of the relationships involved, as well as their dynamic evolution. In this work, we establish a novel class of challenging tasks for dynamic multi-relational graphs involving out-of-domain link prediction, where the relationship being predicted is not available in the input graph. We then introduce a novel Graph Neural Network model, named GOOD, designed specifically to tackle the out-of-domain generalization problem. GOOD introduces a novel design concept for multi-relation embedding aggregation, based on the idea that good representations are such when it is possible to disentangle the mixing proportions of the different relational embeddings that have produced it. We also propose five benchmarks based on two retail domains, where we show that GOOD can effectively generalize predictions out of known relationship types and achieve state-of-the-art results. Most importantly, we provide insights into problems where out-of-domain prediction might be preferred to an in-domain formulation, that is, where the relationship to be predicted has very few positive examples.