# Knowledge Graph Embedding with Atrous Convolution and Residual Learning

arXiv: https://arxiv.org/abs/2010.12121 · HTML: https://mlsanity.com/paper/2010.12121/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network](https://mlsanity.com/paper/2108.09628/) (2021)
- [UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training](https://mlsanity.com/paper/2302.06891/) (2023)
- [HyCubE: Efficient Knowledge Hypergraph 3D Circular Convolutional Embedding](https://mlsanity.com/paper/2402.08961/) (2024)
- [Knowledge Graph Embedding with 3D Compound Geometric Transformations](https://mlsanity.com/paper/2304.00378/) (2023)
- [ConvD: Attention Enhanced Dynamic Convolutional Embeddings for Knowledge Graph Completion](https://mlsanity.com/paper/2312.07589/) (2023)
- [A Benchmark for Fairness-Aware Graph Learning](https://mlsanity.com/paper/2407.12112/) (2024)
- [Separate-and-Aggregate: A Transformer-based Patch Refinement Model for Knowledge Graph Completion](https://mlsanity.com/paper/2307.05627/) (2023)
- [Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding](https://mlsanity.com/paper/2206.02963/) (2022)
- [DeepE: a deep neural network for knowledge graph embedding](https://mlsanity.com/paper/2211.04620/) (2022)
- [Fast Knowledge Graph Completion using Graphics Processing Units](https://mlsanity.com/paper/2307.12059/) (2023)

## Abstract (arXiv)

Knowledge graph embedding is an important task and it will benefit lots of downstream applications. Currently, deep neural networks based methods achieve state-of-the-art performance. However, most of these existing methods are very complex and need much time for training and inference. To address this issue, we propose a simple but effective atrous convolution based knowledge graph embedding method. Compared with existing state-of-the-art methods, our method has following main characteristics. First, it effectively increases feature interactions by using atrous convolutions. Second, to address the original information forgotten issue and vanishing/exploding gradient issue, it uses the residual learning method. Third, it has simpler structure but much higher parameter efficiency. We evaluate our method on six benchmark datasets with different evaluation metrics. Extensive experiments show that our model is very effective. On these diverse datasets, it achieves better results than the compared state-of-the-art methods on most of evaluation metrics. The source codes of our model could be found at https://github.com/neukg/AcrE.