Research output per year
Research output per year
Personal profile
Education/Academic qualification
Master of Science in Physics, Georg-August-Universität Göttingen
Award Date: 13 Sept 2019
Fingerprint
Dive into the research topics where Erik Schultheis is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
Beyond Standard Performance Measures in Extreme Multi-label Classification
Schultheis, E., Wydmuch, M., Babbar, R. & Dembczynski, K., Aug 2022. 11 p.Research output: Contribution to conference › Paper › Scientific › peer-review
Open Access -
CascadeXML : Rethinking Transformers for End-to-end Multi-resolution Extreme Multi-label Classification
Schultheis, E., 1 Dec 2022.Research output: Contribution to conference › Poster › Scientific › peer-review
-
CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification
Kharbanda, S., Banerjee, A., Schultheis, E. & Babbar, R., 2022, Advances in Neural Information Processing Systems 35 (NeurIPS 2022). Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K. & Oh, A. (eds.). Morgan Kaufmann Publishers, 14 p. (Advances in Neural Information Processing Systems; vol. 35).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Open Access2 Citations (Scopus) -
On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification
Schultheis, E., Babbar, R., Wydmuch, M. & Dembczynski, K., Aug 2022, Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM, p. 1547–1557 11 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Open AccessFile4 Citations (Scopus)31 Downloads (Pure) -
Speeding-up one-versus-all training for extreme classification via mean-separating initialization
Schultheis, E. & Babbar, R., Nov 2022, In: Machine Learning. 111, 11, p. 3953-3976Research output: Contribution to journal › Conference article › Scientific › peer-review
Open AccessFile1 Citation (Scopus)28 Downloads (Pure)
Datasets
-
Dismec++
Schultheis, E. (Creator) & Babbar, R. (Supervisor), Zenodo, 2022
DOI: 10.5281/zenodo.6699586, https://zenodo.org/record/6699587
Dataset: Software or code
Prizes
-
NeurIPS 2021 Outstanding Reviewer Award
Schultheis, Erik (Recipient), 15 Oct 2021
Prize: Award or honor granted for a specific work
-
Speeding-up one-versus-all training for extreme classification via mean-separating initialization
Erik Schultheis (Speaker)
21 Sept 2022Activity: Talk or presentation types › Conference presentation
-
On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification
Erik Schultheis (Speaker)
16 Aug 2022Activity: Talk or presentation types › Conference presentation
-
Conference on Neural Information Processing Systems (Event)
Erik Schultheis (Reviewer)
4 Jun 2021 → 28 Sept 2021Activity: Publication peer-review and editorial work types › Reviewer of conference article
-
Convex Surrogates for Unbiased Loss Functions in Extreme Classification With Missing Labels
Mohammadreza Mohammadnia Qaraei (Speaker), Erik Schultheis (Contributor) & Rohit Babbar (Contributor)
4 Nov 2021Activity: Talk or presentation types › Invited academic talk
-
International Conference on Machine Learning (Event)
Erik Schultheis (Reviewer)
11 Feb 2021 → 8 May 2021Activity: Publication peer-review and editorial work types › Reviewer of conference article