activity
20192022
most citedInducing a hierarchy for multi-class classification problems

1 citations · 2 across the 6 of their papers we have counts for

collaborators

7 papers

cs.LG2022

Deep Learning with Label Noise: A Hierarchical Approach

Li Chen, Ningyuan Huang, Cong Mu +4

Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the net…

eess.SP2022

Mental State Classification Using Multi-graph Features

Guodong Chen, Hayden S. Helm, Kate Lytvynets +2

We consider the problem of extracting features from passive, multi-channel electroencephalogram (EEG) devices for downstream inference tasks related to high-level mental states suc…

cs.LG2021

Leveraging semantically similar queries for ranking via combining representations

Hayden S. Helm, Marah Abdin, Benjamin D. Pedigo +8

In modern ranking problems, different and disparate representations of the items to be ranked are often available. It is sensible, then, to try to combine these representations to…

stat.ML20211 cited

Inducing a hierarchy for multi-class classification problems

Hayden S. Helm, Weiwei Yang, Sujeeth Bharadwaj +5

In applications where categorical labels follow a natural hierarchy, classification methods that exploit the label structure often outperform those that do not. Un-fortunately, the…

stat.ML20201 cited

A partition-based similarity for classification distributions

Hayden S. Helm, Ronak D. Mehta, Brandon Duderstadt +5

Herein we define a measure of similarity between classification distributions that is both principled from the perspective of statistical pattern recognition and useful from the pe…

stat.ML2019

Vertex Classification on Weighted Networks

Hayden Helm, Joshua Vogelstein, Carey Priebe

This paper proposes a discrimination technique for vertices in a weighted network. We assume that the edge weights and adjacencies in the network are conditionally independent and…