# LowFER: Low-rank Bilinear Pooling for Link Prediction

arXiv: https://arxiv.org/abs/2008.10858 · HTML: https://mlsanity.com/paper/2008.10858/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2020.

## Built on by (most cited first, 20 of 20)

- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Neural-Symbolic Models for Logical Queries on Knowledge Graphs](https://mlsanity.com/paper/2205.10128/) (2022)
- [Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces](https://mlsanity.com/paper/2211.03536/) (2022)
- [Rethinking Graph Convolutional Networks in Knowledge Graph Completion](https://mlsanity.com/paper/2202.05679/) (2022)
- [Toward Degree Bias in Embedding-Based Knowledge Graph Completion](https://mlsanity.com/paper/2302.05044/) (2023)
- [A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2308.02457/) (2023)
- [Adapting Neural Link Predictors for Data-Efficient Complex Query Answering](https://mlsanity.com/paper/2301.12313/) (2023)
- [Knowledge Graph Completion with Counterfactual Augmentation](https://mlsanity.com/paper/2302.13083/) (2023)
- [Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning](https://mlsanity.com/paper/2405.16851/) (2024)
- [PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph Embedding Reasoning](https://mlsanity.com/paper/2204.13957/) (2022)
- [MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation](https://mlsanity.com/paper/2108.07505/) (2021)
- [MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction](https://mlsanity.com/paper/2204.04779/) (2022)
- [Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations](https://mlsanity.com/paper/2204.04783/) (2022)
- [FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion](https://mlsanity.com/paper/2302.04088/) (2023)
- [Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods](https://mlsanity.com/paper/2506.05626/) (2025)
- [Causal Discovery in Knowledge Graphs by Exploiting Asymmetric Properties of Non-Gaussian Distributions](https://mlsanity.com/paper/2106.01043/) (2021)
- [Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding](https://mlsanity.com/paper/2206.02963/) (2022)
- [Joint embedding in Hierarchical distance and semantic representation learning for link prediction](https://mlsanity.com/paper/2303.15655/) (2023)
- [Neural Probabilistic Logic Learning for Knowledge Graph Reasoning](https://mlsanity.com/paper/2407.03704/) (2024)

## Abstract (arXiv)

Knowledge graphs are incomplete by nature, with only a limited number of observed facts from the world knowledge being represented as structured relations between entities. To partly address this issue, an important task in statistical relational learning is that of link prediction or knowledge graph completion. Both linear and non-linear models have been proposed to solve the problem. Bilinear models, while expressive, are prone to overfitting and lead to quadratic growth of parameters in number of relations. Simpler models have become more standard, with certain constraints on bilinear map as relation parameters. In this work, we propose a factorized bilinear pooling model, commonly used in multi-modal learning, for better fusion of entities and relations, leading to an efficient and constraint-free model. We prove that our model is fully expressive, providing bounds on the embedding dimensionality and factorization rank. Our model naturally generalizes Tucker decomposition based TuckER model, which has been shown to generalize other models, as efficient low-rank approximation without substantially compromising the performance. Due to low-rank approximation, the model complexity can be controlled by the factorization rank, avoiding the possible cubic growth of TuckER. Empirically, we evaluate on real-world datasets, reaching on par or state-of-the-art performance. At extreme low-ranks, model preserves the performance while staying parameter efficient.