On learning latent models with multi-instance weak supervision

K Wang, E Tsamoura, D Roth - Advances in Neural …, 2023‏ - proceedings.neurips.cc
We consider a weakly supervised learning scenario where the supervision signal is
generated by a transition function $\sigma $ of labels associated with multiple input …

Discrete latent structure in neural networks

V Niculae, CF Corro, N Nangia, T Mihaylova… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Many types of data from fields including natural language processing, computer vision, and
bioinformatics, are well represented by discrete, compositional structures such as trees …

On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning

K Wang, E Tsamoura, D Roth - arxiv preprint arxiv:2407.10000, 2024‏ - arxiv.org
* Multi-Instance Partial Label Learning*(MI-PLL) is a weakly-supervised learning setting
encompassing* partial label learning*,* latent structural learning*, and* neurosymbolic …

Moment distributionally robust tree structured prediction

Y Li, D Saeed, X Zhang, B Ziebart… - Advances in neural …, 2022‏ - proceedings.neurips.cc
Structured prediction of tree-shaped objects is heavily studied under the name of syntactic
dependency parsing. Current practice based on maximum likelihood or margin is either …

Learning Structured Models with Weak Supervision

K Wang - 2024‏ - repository.upenn.edu
Over the past decade, the remarkable success of machine learning in various fields has
highlighted the critical role of substantial quantities of training data, thereby bringing both the …

[ספר][B] From Enormous Structured Models to On-device Federated Learning: Robustness, Heterogeneity and Optimization

K Pillutla - 2022‏ - search.proquest.com
Artificial intelligence has been shaped by three revolutions in recent years:(1) differentiable
programming, the practice of writing programs by chaining parameterized modules and …