David Scott Krueger

Sara Hooker

Modern machine learning research relies on relatively few carefully curated datasets. Even in these datasets, and typically in `untidy' or r… (voir plus)aw data, practitioners are faced with significant issues of data quality and diversity which can be prohibitively labor intensive to address. Existing methods for dealing with these challenges tend to make strong assumptions about the particular issues at play, and often require a priori knowledge or metadata such as domain labels. Our work is orthogonal to these methods: we instead focus on providing a unified and efficient framework for Metadata Archaeology -- uncovering and inferring metadata of examples in a dataset. We curate different subsets of data that might exist in a dataset (e.g. mislabeled, atypical, or out-of-distribution examples) using simple transformations, and leverage differences in learning dynamics between these probe suites to infer metadata of interest. Our method is on par with far more sophisticated mitigation methods across different tasks: identifying and correcting mislabeled examples, classifying minority-group samples, prioritizing points relevant for training and enabling scalable human auditing of relevant examples.

2023-02-01

ICLR.cc/2023/Conference (notable)

doi.org

Mechanistic Mode Connectivity

Ekdeep Singh Lubana

Eric J Bigelow

Robert P. Dick

Hidenori Tanaka

We study neural network loss landscapes through the lens of mode connectivity, the observation that minimizers of neural networks retrieved … (voir plus)via training on a dataset are connected via simple paths of low loss. Specifically, we ask the following question: are minimizers that rely on different mechanisms for making their predictions connected via simple paths of low loss? We provide a definition of mechanistic similarity as shared invariances to input transformations and demonstrate that lack of linear connectivity between two models implies they use dissimilar mechanisms for making their predictions. Relevant to practice, this result helps us demonstrate that naive fine-tuning on a downstream dataset can fail to alter a model's mechanisms, e.g., fine-tuning can fail to eliminate a model's reliance on spurious attributes. Our analysis also motivates a method for targeted alteration of a model's mechanisms, named connectivity-based fine-tuning (CBFT), which we analyze using several synthetic datasets for the task of reducing a model's reliance on spurious attributes.

2023-01-01

ICML (publié)

doi.org

Noisy Pairing and Partial Supervision for Stylized Opinion Summarization

Reinald Kim

Mirella Lapata. 2020

Un-611

Maxinder S. Kan-620

Asja Fischer

Somnath Basu

Roy Chowdhury

Chao Zhao

Tanya Goyal

Junyi Jiacheng Xu

Jessy Li

Ivor W. Tsang

James T. Kwok

Neil Houlsby

Andrei Giurgiu

Stanisław Jastrzębski … (voir 22 de plus)

Bruna Morrone

Quentin de Laroussilhe

Mona Gesmundo

Attariyan Sylvain

Gelly

Thomas Wolf

Lysandre Debut

Julien Victor Sanh

Clement Chaumond

Anthony Delangue

Pier-339 Moi

Tim ric Cistac

R´emi Rault

Morgan Louf

Funtow-900 Joe

Sam Davison

Patrick Shleifer

Von Platen

Clara Ma

Yacine Jernite

Julien Plu

Canwen Xu

Opinion summarization research has primar-001 ily focused on generating summaries reflect-002 ing important opinions from customer reviews 0… (voir plus)03 without paying much attention to the writing 004 style. In this paper, we propose the stylized 005 opinion summarization task, which aims to 006 generate a summary of customer reviews in 007 the desired (e.g., professional) writing style. 008 To tackle the difficulty in collecting customer 009 and professional review pairs, we develop a 010 non-parallel training framework, Noisy Pair-011 ing and Partial Supervision ( NAPA ), which 012 trains a stylized opinion summarization sys-013 tem from non-parallel customer and profes-014 sional review sets. We create a benchmark P RO - 015 S UM by collecting customer and professional 016 reviews from Yelp and Michelin. Experimental 017 results on P RO S UM and FewSum demonstrate 018 that our non-parallel training framework con-019 sistently improves both automatic and human 020 evaluations, successfully building a stylized 021 opinion summarization model that can gener-022 ate professionally-written summaries from cus-023 tomer reviews. 024

2023-01-01

(publié)

www.semanticscholar.org

On The Fragility of Learned Reward Functions

Lev E McKinney

Yawen Duan

Adam Gleave

Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer … (voir plus)reward functions from human feedback and preferences. Prior works on reward learning have mainly focused on the performance of policies trained alongside the reward function. This practice, however, may fail to detect learned rewards that are not capable of training new policies from scratch and thus do not capture the intended behavior. Our work focuses on demonstrating and studying the causes of these relearning failures in the domain of preference-based reward learning. We demonstrate with experiments in tabular and continuous control environments that the severity of relearning failures can be sensitive to changes in reward model design and the trajectory dataset composition. Based on our findings, we emphasize the need for more retraining-based evaluations in the literature.

2022-12-09

NeurIPS.cc/2022/Workshop/DeepRL (inconnu)

doi.org

Training Equilibria in Reinforcement Learning

Lauro Langosco

Adam Gleave

In partially observable environments, reinforcement learning algorithms such as policy gradient and Q-learning may have multiple equilibria-… (voir plus)--policies that are stable under further training---and can converge to equilibria that are strictly suboptimal. Prior work blames insufficient exploration, but suboptimal equilibria can arise despite full exploration and other favorable circumstances like a flexible policy parametrization. We show theoretically that the core problem is that in partially observed environments, an agent's past actions induce a distribution on hidden states. Equipping the policy with memory helps it model the hidden state and leads to convergence to a higher reward equilibrium, \emph{even when there exists a memoryless optimal policy}. Experiments show that policies with insufficient memory tend to learn to use the environment as auxiliary memory, and parameter noise helps policies escape suboptimal equilibria.

2022-12-09

NeurIPS.cc/2022/Workshop/DeepRL (inconnu)

Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models

Enoch Amoatey Tetteh

Joseph D Viviano

Yoshua Bengio

Joseph Paul Cohen

Learning models that generalize under different distribution shifts in medical imaging has been a long-standing research challenge. There ha… (voir plus)ve been several proposals for efficient and robust visual representation learning among vision research practitioners, especially in the sensitive and critical biomedical domain. In this paper, we propose an idea for out-of-distribution generalization of chest X-ray pathologies that uses a simple balanced batch sampling technique. We observed that balanced sampling between the multiple training datasets improves the performance over baseline models trained without balancing.

2021-12-27

ArXiv (prépublication)

Multi-Domain Balanced Sampling Improves Out-of-Generalization of Chest X-ray Pathology Prediction Models

Enoch Amoatey Tetteh

Joseph D Viviano

Yoshua Bengio

Joseph Paul Cohen

Learning models that generalize under different distribution shifts in medical imaging has been a long-standing research challenge. There ha… (voir plus)ve been several proposals for efﬁcient and robust visual representation learning among vision research practitioners, especially in the sensitive and critical biomedical domain. In this paper, we propose an idea for out-of-distribution generalization of chest X-ray pathologies that uses a simple balanced batch sampling technique. We observed that balanced sampling between the multiple training datasets improves the performance over baseline models trained without balancing. Code for this work is available on Github. 1

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

Miles Brundage

Shahar Avin

Jasmine Wang

Haydn Belfield

Gretchen Krueger

Gillian K. Hadfield

Heidy Khlaaf

Jingying Yang

H. Toner

Ruth Catherine Fong

Tegan Maharaj

Pang Wei Koh

Sara Hooker

Jade Leung

Andrew John Trask

Emma Bluemke

Jonathan Lebensbold

Cullen C. O'keefe

Mark Koren

Th'eo Ryffel … (voir 39 de plus)

JB Rubinovitz

Tamay Besiroglu

Federica Carugati

Jack Clark

Peter Eckersley

Sarah de Haas

Maritza L. Johnson

Ben Laurie

Alex Ingerman

Igor Krawczuk

Amanda Askell

Rosario Cammarota

A. Lohn

Charlotte Stix

Peter Mark Henderson

Logan Graham

Carina E. A. Prunkl

Bianca Martin

Elizabeth Seger

Noa Zilberman

Sean O hEigeartaigh

Frens Kroeger

Girish Sastry

R. Kagan

Adrian Weller

Brian Shek-kam Tse

Elizabeth Barnes

Allan Dafoe

Paul D. Scharre

Ariel Herbert-Voss

Martijn Rasser

Shagun Sodhani

Carrick Flynn

Thomas Krendl Gilbert

Lisa Dyer

Saif M. Khan

Yoshua Bengio

Markus Anderljung

2020-04-15

ArXiv (prépublication)

Out-of-Distribution Generalization via Risk Extrapolation (REx)

Ethan Caballero

Joern-Henrik Jacobsen

Amy Zhang

Jonathan Binas

Rémi LE PRIOL

Aaron Courville

Generalizing outside of the training distribution is an open challenge for current machine learning systems. A weak form of out-of-distribut… (voir plus)ion (OoD) generalization is the ability to successfully interpolate between multiple observed distributions. One way to achieve this is through robust optimization, which seeks to minimize the worst-case risk over convex combinations of the training distributions. However, a much stronger form of OoD generalization is the ability of models to extrapolate beyond the distributions observed during training. In pursuit of strong OoD generalization, we introduce the principle of Risk Extrapolation (REx). REx can be viewed as encouraging robustness over affine combinations of training risks, by encouraging strict equality between training risks. We show conceptually how this principle enables extrapolation, and demonstrate the effectiveness and scalability of instantiations of REx on various OoD generalization tasks. Our code can be found at this https URL.

2020-03-02

ArXiv (prépublication)

Neural Autoregressive Flows

Chin-Wei Huang

Alexandre Lacoste

Aaron Courville

Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via M… (voir plus)asked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify and generalize these approaches, replacing the (conditionally) affine univariate transformations of MAF/IAF with a more general class of invertible univariate transformations expressed as monotonic neural networks. We demonstrate that the proposed neural autoregressive flows (NAF) are universal approximators for continuous probability distributions, and their greater expressivity allows them to better capture multimodal target distributions. Experimentally, NAF yields state-of-the-art performance on a suite of density estimation tasks and outperforms IAF in variational autoencoders trained on binarized MNIST.

2018-07-03

Proceedings of the 35th International Conference on Machine Learning (publié)

proceedings.mlr.press

Neural Autoregressive Flows

Chin-Wei Huang

Alexandre Lacoste

Aaron Courville

2018-04-03

ArXiv (prépublication)