Erik Schultheis
Doctoral Researcher
Doctoral Researcher
T313 Dept. Computer Science
Full researcher profile
https://research.aalto.fi/...
Email
[email protected]
Honors and awards
NeurIPS 2021 Outstanding Reviewer Award
Award or honor granted for a specific work
School common, SCI
Oct 2021
Publications
Generalized test utilities for long-tail performance in extreme multi-label classification
Erik Schultheis, Marek Wydmuch, Wojciech Kotlowski, Rohit Babbar, Krzysztof Dembczynski
2024
Advances in Neural Information Processing Systems 36 (NeurIPS 2023)
Extreme Multicore Classification
Erik Schultheis, Rohit Babbar
2023
Machine Learning under Resource Constraints
Towards Memory-Efficient Training for Extremely Large Output Spaces : Learning with 670k Labels on a Single Commodity GPU
Erik Schultheis, Rohit Babbar
2023
Machine Learning and Knowledge Discovery in Databases
CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification
Siddhant Kharbanda, Atmadeep Banerjee, Erik Schultheis, Rohit Babbar
2022
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
Beyond Standard Performance Measures in Extreme Multi-label Classification
Erik Schultheis, Marek Wydmuch, Rohit Babbar, Krzysztof Dembczynski
2022
CascadeXML : Rethinking Transformers for End-to-end Multi-resolution Extreme Multi-label Classification
Erik Schultheis
2022
On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification
Erik Schultheis, Rohit Babbar, Marek Wydmuch, Krzysztof Dembczynski
2022
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Speeding-up one-versus-all training for extreme classification via mean-separating initialization
Erik Schultheis, Rohit Babbar
2022
Convex Surrogates for Unbiased Loss Functions in Extreme Classification With Missing Labels
Mohammadreza Mohammadnia Qaraei, Erik Schultheis, Priyanshu Gupta, Rohit Babbar
2021
The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021
Speeding-up One-vs-All Training for Extreme Classification via Smart Initialization
Erik Schultheis, Rohit Babbar
2021