Constraining Latent Space to Improve Deep Self Supervised e Commerce Products Embeddings for Downstream Tasks

The representation of products in a e-commerce marketplace is a key aspect to be exploited when trying to improve the user experience on the site . This work proposes a novel deep encoder model for learning product embeddings to be applied in several downstream tasks . The model uses pairs of products that appear together in a browsing session of the users and adds a proximity constraint to the final latent space in order to project the embeddeddings of similar products close to each other . This has a regularization effect which gives better features representations to use across multiple downstream tasks, we explore such effect in our experimentation by assessing its impact on the performance of the tasks . Our experiments show effectiveness in transfer learning scenarios comparable to several industrial baselines. Our experiments showed effectiveness in transferring learning scenarios. Our experiments were comparable to those of the models. The model was tested by the authors of the authors. The authors are published on Tuesday, October 4, at the Open Daybreak. For more information, visit http://www.openDaybreak.com/dailybreakbreakbreakthrough/news/newsbreakbreakdown.com . Back to the page you came from the page or contact us on our page or click here.com for more information. Please contact us at www.breakthrough.

Links: PDF - Abstract

Code :

None

Keywords : products - tasks - experiments - authors - downstream -

Leave a Reply

Your email address will not be published. Required fields are marked *