The field of knowledge graph embeddings and contrastive learning is rapidly evolving, with a focus on developing more efficient and effective methods for representing complex relationships and structures in data. Recent research has explored the use of scale-aware gradual evolution frameworks for continual knowledge graph embedding, which can adapt to changing graph structures and scales. Additionally, novel contrastive learning approaches have been proposed, such as center-oriented prototype contrastive clustering and adaptive distribution calibration, which can improve the discriminative power of representations and mitigate the risk of overfitting. Noteworthy papers in this area include SAGE, which proposes a scale-aware gradual evolution framework for continual knowledge graph embedding, and Center-Oriented Prototype Contrastive Clustering, which introduces a soft prototype contrastive module and a dual consistency learning module to improve clustering performance. Overall, these advancements have the potential to significantly improve the performance and efficiency of knowledge graph embedding and contrastive learning methods, with applications in a wide range of domains.