Changho Suh

Improving Fair Training under Correlation Shifts

Feb 05, 2023
Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh

Figure 2 for Improving Fair Training under Correlation Shifts

Figure 3 for Improving Fair Training under Correlation Shifts

Figure 4 for Improving Fair Training under Correlation Shifts

Access Paper or Ask Questions

Equal Experience in Recommender Systems

Oct 12, 2022
Jaewoong Cho, Moonseok Choi, Changho Suh

Figure 2 for Equal Experience in Recommender Systems

Figure 3 for Equal Experience in Recommender Systems

Figure 4 for Equal Experience in Recommender Systems

* 18 pages, 9 figures

Access Paper or Ask Questions

Matrix Completion with Hierarchical Graph Side Information

Jan 02, 2022
Adel Elmahdy, Junhyung Ahn, Changho Suh, Soheil Mohajer

Figure 2 for Matrix Completion with Hierarchical Graph Side Information

Figure 3 for Matrix Completion with Hierarchical Graph Side Information

* Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
* 53 pages, 3 figures, 1 table. Published in NeurIPS 2020. The first two authors contributed equally to this work. In this revision, achievability proof technique is updated and typos are corrected. arXiv admin note: substantial text overlap with arXiv:2109.05408

Access Paper or Ask Questions

Sample Selection for Fair and Robust Training

Oct 27, 2021
Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh

Figure 2 for Sample Selection for Fair and Robust Training

Figure 3 for Sample Selection for Fair and Robust Training

Figure 4 for Sample Selection for Fair and Robust Training

* Accepted to 35th Conference on Neural Information Processing Systems (NeurIPS), 2021

Access Paper or Ask Questions

On the Fundamental Limits of Matrix Completion: Leveraging Hierarchical Similarity Graphs

Sep 12, 2021
Junhyung Ahn, Adel Elmahdy, Soheil Mohajer, Changho Suh

* The first two authors contributed equally to this work. A preliminary version of this work was presented at the 2020 Advances in Neural Information Processing Systems Conference (NeurIPS 2020)

Access Paper or Ask Questions