164 citations · 305 across the 20 of their papers we have counts for
10 papers · 1 filter
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
Ouail Kitouni, Niklas Nolte, Diane Bouchacourt +3
Today's best language models still struggle with hallucinations: factually incorrect generations, which impede their ability to reliably retrieve information seen during training.…
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
Cian Eastwood, Julius von Kügelgen, Linus Ericsson +4
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown…
Discovering environments with XRM
Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim +3
Environment annotations are essential for the success of many out-of-distribution (OOD) generalization methods. Unfortunately, these are costly to obtain and often limited by human…
A Cookbook of Self-Supervised Learning
Randall Balestriero, Mark Ibrahim, Vlad Sobal +16
Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art wi…
Disentanglement of Correlated Factors via Hausdorff Factorized Support
Karsten Roth, Mark Ibrahim, Zeynep Akata +2
A grand goal in deep learning research is to learn representations capable of generalizing across distribution shifts. Disentanglement is one promising direction aimed at aligning…
CrypTen: Secure Multi-Party Computation Meets Machine Learning
Brian Knott, Shobha Venkataraman, Awni Hannun +3
Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applic…
Addressing the Topological Defects of Disentanglement via Distributed Operators
Diane Bouchacourt, Mark Ibrahim, Stéphane Deny
A core challenge in Machine Learning is to learn to disentangle natural factors of variation in data (e.g. object shape vs. pose). A popular approach to disentanglement consists in…
Global Explanations of Neural Networks: Mapping the Landscape of Predictions
Mark Ibrahim, Melissa Louie, Ceena Modarres +1
A barrier to the wider adoption of neural networks is their lack of interpretability. While local explanation methods exist for one prediction, most global attributions still reduc…
Mixed Membership Recurrent Neural Networks
Ghazal Fazelnia, Mark Ibrahim, Ceena Modarres +2
Models for sequential data such as the recurrent neural network (RNN) often implicitly model a sequence as having a fixed time interval between observations and do not account for…
Towards Explainable Deep Learning for Credit Lending: A Case Study
Ceena Modarres, Mark Ibrahim, Melissa Louie +1
Deep learning adoption in the financial services industry has been limited due to a lack of model interpretability. However, several techniques have been proposed to explain predic…