416 citations · 545 across the 35 of their papers we have counts for
9 papers · 1 filter
Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language
Zhenlin Xu, Marc Niethammer, Colin Raffel
Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling…
On Measuring Excess Capacity in Neural Networks
Florian Graf, Sebastian Zeng, Bastian Rieck +2
We study the excess capacity of deep networks in the context of supervised classification. That is, given a capacity measure of the underlying hypothesis class - in our case, empir…
The Fairness-Accuracy Pareto Front
Susan Wei, Marc Niethammer
Algorithmic fairness seeks to identify and correct sources of bias in machine learning algorithms. Confoundingly, ensuring fairness often comes at the cost of accuracy. We provide…
Deep Goal-Oriented Clustering
Yifeng Shi, Christopher M. Bender, Junier B. Oliva +1
Clustering and prediction are two primary tasks in the fields of unsupervised and supervised learning, respectively. Although much of the recent advances in machine learning have b…
Topologically Densified Distributions
Christoph D. Hofer, Florian Graf, Marc Niethammer +1
We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift focus from architectural properties, such as no…
Deep Message Passing on Sets
Yifeng Shi, Junier Oliva, Marc Niethammer
Modern methods for learning over graph input data have shown the fruitfulness of accounting for relationships among elements in a collection. However, most methods that learn over…