mlsanityData to 7 Oct 2026

Scalable knowledge base completion with superposition memories

arXiv 2110.12341 ↗First posted 24 Oct 2021cs.CLcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 30 references that are in the map. First posted on arXiv 24 Oct 2021.

Builds on

13 of 30 references.

References · 13

  1. 2017Graph Attention Networkscited by 8,854
  2. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  3. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  4. 2016Complex Embeddings for Simple Link Predictioncited by 897
  5. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  6. 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
  7. 2015Holographic Embeddings of Knowledge Graphscited by 181
  8. 2017A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Networkcited by 143
  9. 2019Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphscited by 125
  10. 2017Knowledge Base Completion: Baselines Strike Backcited by 39
  11. 2018Hypernetwork Knowledge Graph Embeddingscited by 38
  12. 2017TorusE: Knowledge Graph Embedding on a Lie Groupcited by 36
1 more
  1. 2018Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representationscited by 2

Built on by

Not cited yet.