activity
20172022
most citedWeight Poisoning Attacks on Pre-trained Models

49 citations · 85 across the 10 of their papers we have counts for

collaborators

14 papers

cs.MA20223 cited

Emergent Communication: Generalization and Overfitting in Lewis Games

Mathieu Rita, Corentin Tallec, Paul Michel +4

Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order…

cs.LG20222 cited

Distributionally Robust Models with Parametric Likelihood Ratios

Paul Michel, Tatsunori Hashimoto, Graham Neubig

As machine learning models are deployed ever more broadly, it becomes increasingly important that they are not only able to perform well on their training distribution, but also yi…

cs.LG2021

Balancing Average and Worst-case Accuracy in Multitask Learning

Paul Michel, Sebastian Ruder, Dani Yogatama

When training and evaluating machine learning models on a large number of tasks, it is important to not only look at average task accuracy -- which may be biased by easy or redunda…

cs.CL20211 cited

Learning Neural Models for Natural Language Processing in the Face of Distributional Shift

Paul Michel

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg…

cs.LG20213 cited

Examining and Combating Spurious Features under Distribution Shift

Chunting Zhou, Xuezhe Ma, Paul Michel +1

A central goal of machine learning is to learn robust representations that capture the causal relationship between inputs features and output labels. However, minimizing empirical…

cs.LG20213 cited

Modeling the Second Player in Distributionally Robust Optimization

Paul Michel, Tatsunori Hashimoto, Graham Neubig

Distributionally robust optimization (DRO) provides a framework for training machine learning models that are able to perform well on a collection of related data distributions (th…