# Are Message Passing Neural Networks Really Helpful for Knowledge Graph Completion?

arXiv: https://arxiv.org/abs/2205.10652 · HTML: https://mlsanity.com/paper/2205.10652/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 21 May 2022.

## Builds on (most cited first, 21 of 21)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (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)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Pay Attention to MLPs](https://mlsanity.com/paper/2105.08050/) (2021)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness](https://mlsanity.com/paper/2110.03753/) (2021)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [Graph Condensation for Graph Neural Networks](https://mlsanity.com/paper/2110.07580/) (2021)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs](https://mlsanity.com/paper/1906.01195/) (2019)
- [A Unified View on Graph Neural Networks as Graph Signal Denoising](https://mlsanity.com/paper/2010.01777/) (2020)
- [Knowledge Graph Reasoning with Relational Digraph](https://mlsanity.com/paper/2108.06040/) (2021)
- [A Re-evaluation of Knowledge Graph Completion Methods](https://mlsanity.com/paper/1911.03903/) (2019)
- [Rethinking Graph Convolutional Networks in Knowledge Graph Completion](https://mlsanity.com/paper/2202.05679/) (2022)

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

- [Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning](https://mlsanity.com/paper/2406.16321/) (2024)
- [RulE: Knowledge Graph Reasoning with Rule Embedding](https://mlsanity.com/paper/2210.14905/) (2022)
- [Node Duplication Improves Cold-start Link Prediction](https://mlsanity.com/paper/2402.09711/) (2024)
- [Deep Sparse Latent Feature Models for Knowledge Graph Completion](https://mlsanity.com/paper/2411.15694/) (2024)
- [Enhancing Knowledge Graph Completion with GNN Distillation and Probabilistic Interaction Modeling](https://mlsanity.com/paper/2505.12272/) (2025)
- [Pattern Over-Generalization of Knowledge Graph Embedding](https://mlsanity.com/paper/2609.03487/) (2026)

## Abstract (arXiv)

Knowledge graphs (KGs) facilitate a wide variety of applications. Despite great efforts in creation and maintenance, even the largest KGs are far from complete. Hence, KG completion (KGC) has become one of the most crucial tasks for KG research. Recently, considerable literature in this space has centered around the use of Message Passing (Graph) Neural Networks (MPNNs), to learn powerful embeddings. The success of these methods is naturally attributed to the use of MPNNs over simpler multi-layer perceptron (MLP) models, given their additional message passing (MP) component. In this work, we find that surprisingly, simple MLP models are able to achieve comparable performance to MPNNs, suggesting that MP may not be as crucial as previously believed. With further exploration, we show careful scoring function and loss function design has a much stronger influence on KGC model performance. This suggests a conflation of scoring function design, loss function design, and MP in prior work, with promising insights regarding the scalability of state-of-the-art KGC methods today, as well as careful attention to more suitable MP designs for KGC tasks tomorrow. Our codes are publicly available at: https://github.com/Juanhui28/Are_MPNNs_helpful.