Improving Continual Learning of Knowledge Graph Embeddings via Informed Initialization

The paper presents SEPAL, a Scalable Embedding Propagation Algorithm aimed at improving the use of large knowledge graphs in machine learning. Current models face limitations in optimizing for link prediction and require extensive engineering for large graphs due to GPU memory constraints. SEPAL addresses these issues by ensuring global embedding consistency through localized optimization and message passing, evaluated across seven large-scale knowledge graphs for various downstream tasks.

This research combines Transformer-based relation extraction with knowledge graph matching to enhance the answering of multiple-choice questions (MCQs). Knowledge graphs, which represent factual knowledge through entities and relations, have traditionally been static due to high construction costs. However, the advent of Transformer-based methods allows for dynamic generation of these graphs from natural language texts, enabling more accurate representation of input meanings. The study emphasizes the importance of truthfulness in the generated knowledge graphs.

The paper titled 'KGQuest: Template-Driven QA Generation from Knowledge Graphs with LLM-Based Refinement' addresses the challenges of generating questions and answers from knowledge graphs (KGs). It proposes a scalable pipeline that clusters KG triplets and creates reusable templates, which are refined using large language models (LLMs) to enhance linguistic quality. The method aims to improve clarity, coherence, and factual accuracy in educational platforms and testing tools.