# DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion

arXiv: https://arxiv.org/abs/2311.03780 · HTML: https://mlsanity.com/paper/2311.03780/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 7 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [CoDEx: A Comprehensive Knowledge Graph Completion Benchmark](https://mlsanity.com/paper/2009.07810/) (2020)
- [HittER: Hierarchical Transformers for Knowledge Graph Embeddings](https://mlsanity.com/paper/2008.12813/) (2020)
- [Learning-to-Rank with BERT in TF-Ranking](https://mlsanity.com/paper/2004.08476/) (2020)
- [Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols](https://mlsanity.com/paper/2005.05035/) (2020)

## Built on by (most cited first, 1 of 1)

- [KGMark: A Diffusion Watermark for Knowledge Graphs](https://mlsanity.com/paper/2505.23873/) (2025)

## Abstract (arXiv)

We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connectivity structure of the Knowledge Graph (KG). Preliminary experiments show that these approaches have complementary strengths: structure-based models perform exceptionally well when the gold answer is easily reachable from the query head in the KG, while textual models exploit descriptions to give good performance even when the gold answer is not easily reachable. In response, we propose DynaSemble, a novel method for learning query-dependent ensemble weights to combine these approaches by using the distributions of scores assigned by the models in the ensemble to all candidate entities. DynaSemble achieves state-of-the-art results on three standard KGC datasets, with up to 6.8 pt MRR and 8.3 pt Hits@1 gains over the best baseline model for the WN18RR dataset.