# Improving Continual Learning of Knowledge Graph Embeddings via Informed Initialization Source: [Improving Continual Learning of Knowledge Graph Embeddings via Informed Initialization]() Collection index: [llms.txt]() Data updated: 2026-05-30T05:00:11.986Z Authors: Gerard Pons, Besim Bilalli, Anna Queralt Published: 2025-11-14T09:48:24.000Z ## Abstract Many Knowledege Graphs (KGs) are frequently updated, forcing their Knowledge Graph Embeddings (KGEs) to adapt to these changes. To address this problem, continual learning techniques for KGEs incorporate embeddings for new entities while updating the old ones. One necessary step in these methods is the initialization of the embeddings, as an input to the KGE learning process, which can have an important impact in the accuracy of the final embeddings, as well as in the time required to train them. This is especially relevant for relatively small and frequent updates. We propose a novel informed embedding initialization strategy, which can be seamlessly integrated into existing continual learning methods for KGE, that enhances the acquisition of new knowledge while reducing catastrophic forgetting. Specifically, the KG schema and the previously learned embeddings are utilized to obtain initial representations for the new entities, based on the classes the entities belong to. Our extensive experimental analysis shows that the proposed initialization strategy improves the predictive performance of the resulting KGEs, while also enhancing knowledge retention. Furthermore, our approach accelerates knowledge acquisition, reducing the number of epochs, and therefore time, required to incrementally learn new embeddings. Finally, its benefits across various types of KGE learning models are demonstrated. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Link Prediction on FBinc S](): Link Prediction; FBinc S; MRR: 31.5. - [Link Prediction on FBinc-M](): Link Prediction; FBinc-M; MRR: 0.316. - [Link Prediction on FBinc-L](): Link Prediction; FBinc-L; MRR: 0.308. ## Original sources and implementation [Original paper]() [PDF]()