# Scalable knowledge base completion with superposition memories

arXiv: https://arxiv.org/abs/2110.12341 · HTML: https://mlsanity.com/paper/2110.12341/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 24 Oct 2021.

## Builds on (most cited first, 13 of 13)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [SimplE Embedding for Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/1802.04868/) (2018)
- [Holographic Embeddings of Knowledge Graphs](https://mlsanity.com/paper/1510.04935/) (2015)
- [A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network](https://mlsanity.com/paper/1712.02121/) (2017)
- [Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs](https://mlsanity.com/paper/1906.01195/) (2019)
- [Knowledge Base Completion: Baselines Strike Back](https://mlsanity.com/paper/1705.10744/) (2017)
- [Hypernetwork Knowledge Graph Embeddings](https://mlsanity.com/paper/1808.07018/) (2018)
- [TorusE: Knowledge Graph Embedding on a Lie Group](https://mlsanity.com/paper/1711.05435/) (2017)
- [Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations](https://mlsanity.com/paper/1811.01062/) (2018)

## Abstract (arXiv)

We present Harmonic Memory Networks (HMem), a neural architecture for knowledge base completion that models entities as weighted sums of pairwise bindings between an entity's neighbors and corresponding relations. Since entities are modeled as aggregated neighborhoods, representations of unseen entities can be generated on the fly. We demonstrate this with two new datasets: WNGen and FBGen. Experiments show that the model is SOTA on benchmarks, and flexible enough to evolve without retraining as the knowledge graph grows.