Towards Lifelong Learning Embeddings: An Algorithmic Approach to Dynamically Extend Embeddings
This addresses the challenge of dynamic product updates in e-commerce for companies seeking efficient personalization, but it is incremental as it builds on existing embedding methods.
The paper tackles the problem of embeddings in e-commerce requiring fixed dimensions and periodic retraining due to frequent new product introductions, by introducing a modular algorithm that dynamically extends embedding input size while preserving learned knowledge and mitigating cold start issues, with initial experiments showing it outperforms traditional embeddings.
The rapid evolution of technology has transformed business operations and customer interactions worldwide, with personalization emerging as a key opportunity for e-commerce companies to engage customers more effectively. The application of machine learning, particularly that of deep learning models, has gained significant traction due to its ability to rapidly recognize patterns in large datasets, thereby offering numerous possibilities for personalization. These models use embeddings to map discrete information, such as product IDs, into a latent vector space, a method increasingly popular in recent years. However, e-commerce's dynamic nature, characterized by frequent new product introductions, poses challenges for these embeddings, which typically require fixed dimensions and inputs, leading to the need for periodic retraining from scratch. This paper introduces a modular algorithm that extends embedding input size while preserving learned knowledge, addressing the challenges posed by e-commerce's dynamism. The proposed algorithm also incorporates strategies to mitigate the cold start problem associated with new products. The results of initial experiments suggest that this method outperforms traditional embeddings.