# Elastic Weight Consolidation for Knowledge Graph Continual Learning: An Empirical Evaluation

arXiv: https://arxiv.org/abs/2512.01890 · HTML: https://mlsanity.com/paper/2512.01890/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 8 of 8)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [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)
- [A Survey on Knowledge Graph-Based Recommender Systems](https://mlsanity.com/paper/2003.00911/) (2020)
- [Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation](https://mlsanity.com/paper/1901.08907/) (2019)
- [Continual Learning of Knowledge Graph Embeddings](https://mlsanity.com/paper/2101.05850/) (2021)
- [Knowledge Graphs and Knowledge Networks: The Story in Brief](https://mlsanity.com/paper/2003.03623/) (2020)

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

- [PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs](https://mlsanity.com/paper/2605.10529/) (2026)

## Abstract (arXiv)

Knowledge graphs (KGs) require continual updates as new information emerges, but neural embedding models suffer from catastrophic forgetting when learning new tasks sequentially. We evaluate Elastic Weight Consolidation (EWC), a regularization-based continual learning method, on KG link prediction using TransE embeddings on FB15k-237. Across multiple experiments with five random seeds, we find that EWC reduces catastrophic forgetting from 12.62% to 6.85%, a 45.7% reduction compared to naive sequential training. We observe that the task partitioning strategy affects the magnitude of forgetting: relation-based partitioning (grouping triples by relation type) exhibits 9.8 percentage points higher forgetting than randomly partitioned tasks (12.62% vs 2.81%), suggesting that task construction influences evaluation outcomes. While focused on a single embedding model and dataset, our results demonstrate that EWC effectively mitigates catastrophic forgetting in KG continual learning and highlight the importance of evaluation protocol design.