Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 670k Labels on a Single Commodity GPU

Erik Schultheis, Rohit Babbar. Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 670k Labels on a Single Commodity GPU. In Danai Koutra, Claudia Plant, Manuel Gomez-Rodriguez, Elena Baralis, Francesco Bonchi, editors, Machine Learning and Knowledge Discovery in Databases: Research Track - European Conference, ECML PKDD 2023, Turin, Italy, September 18-22, 2023, Proceedings, Part III. Volume 14171 of Lecture Notes in Computer Science, pages 689-704, Springer, 2023. [doi]

Authors

Erik Schultheis

This author has not been identified. Look up 'Erik Schultheis' in Google

Rohit Babbar

This author has not been identified. Look up 'Rohit Babbar' in Google