no code implementations • 9 Nov 2023 • Ruijie Jiang, Thuan Nguyen, Shuchin Aeron, Prakash Ishwar
For a widely-studied data model and general loss and sample-hardening functions we prove that the Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised Contrastive Learning (UCL) risks are minimized by representations that exhibit Neural Collapse (NC), i. e., the class means form an Equianglular Tight Frame (ETF) and data from the same class are mapped to the same representation.
1 code implementation • 18 Jul 2023 • Zhe Huang, Ruijie Jiang, Shuchin Aeron, Michael C. Hughes
Yet past benchmarks do not focus on medical tasks and rarely compare self- and semi- methods together on an equal footing.
1 code implementation • 31 Aug 2022 • Ruijie Jiang, Thuan Nguyen, Prakash Ishwar, Shuchin Aeron
In this paper, motivated by the effectiveness of hard-negative sampling strategies in H-UCL and the usefulness of label information in SCL, we propose a contrastive learning framework called hard-negative supervised contrastive learning (H-SCL).
1 code implementation • 28 Jan 2022 • Matthew Werenski, Ruijie Jiang, Abiy Tasissa, Shuchin Aeron, James M. Murphy
Our first main result leverages the Riemannian geometry of Wasserstein-2 space to provide a procedure for recovering the barycentric coordinates as the solution to a quadratic optimization problem assuming access to the true reference measures.
2 code implementations • 4 Nov 2021 • Ruijie Jiang, Prakash Ishwar, Shuchin Aeron
We study the problem of designing hard negative sampling distributions for unsupervised contrastive representation learning.
1 code implementation • 1 Nov 2021 • Ruijie Jiang, Julia Gouvea, Eric Miller, David Hammer, Shuchin Aeron
This paper shows that a popular approach to the supervised embedding of documents for classification, namely, contrastive Word Mover's Embedding, can be significantly enhanced by adding interpretability.
no code implementations • 26 Nov 2020 • Ruijie Jiang, Julia Gouvea, David Hammer, Eric Miller, Shuchin Aeron
This work is a step towards building a statistical machine learning (ML) method for achieving an automated support for qualitative analyses of students' writing, here specifically in score laboratory reports in introductory biology for sophistication of argumentation and reasoning.