Alex Lamb

Recurrent Independent Mechanisms

Sergey Levine

Bernhard Schölkopf

Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which … (see more)only affect a few of the underlying causes. We propose Recurrent Independent Mechanisms (RIMs), a new recurrent architecture in which multiple groups of recurrent cells operate with nearly independent transition dynamics, communicate only sparingly through the bottleneck of attention, and are only updated at time steps where they are most relevant. We show that this leads to specialization amongst the RIMs, which in turn allows for dramatically improved generalization on tasks where some factors of variation differ systematically between training and evaluation.

2021-01-11

ICLR.cc/2021/Conference (spotlight)

doi.org

openreview.net

Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments

Anirudh Goyal

Alex Lamb

Phanideep Gampa

Philippe Beaudoin

Charles Blundell

Sergey Levine

Yoshua Bengio

Michael Mozer

2020-12-31

ICLR (published)

openreview.net

GraphMix: Improved Training of GNNs for Semi-Supervised Learning

Juho Kannala

We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to tra… (see more)in a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization. Further, we provide a theoretical analysis of how GraphMix improves the generalization bounds of the underlying graph neural network, without making any assumptions about the "aggregation" layer or the depth of the graph neural networks. We experimentally validate this analysis by applying GraphMix to various architectures such as Graph Convolutional Networks, Graph Attention Networks and Graph-U-Net. Despite its simplicity, we demonstrate that GraphMix can consistently improve or closely match state-of-the-art performance using even simpler architectures such as Graph Convolutional Networks, across three established graph benchmarks: Cora, Citeseer and Pubmed citation network datasets, as well as three newly proposed datasets: Cora-Full, Co-author-CS and Co-author-Physics.

2020-10-10

AAAI Conference on Artificial Intelligence (published)

doi.org

arxiv.org

Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems

Anirudh Goyal

Alex Lamb

Phanideep Gampa

Philippe Beaudoin

Sergey Levine

Charles Blundell

Yoshua Bengio

Michael Curtis Mozer

2020-06-28

ArXiv (preprint)

arxiv.org

GraphMix: Improved Training of Graph Neural Networks for Semi-Supervised Learning

Juho Kannala

We present GraphMix , a regularized training scheme for Graph Neural Network based semi-supervised object classiﬁcation, leveraging the re… (see more)cent advances in the regularization of classical deep neural networks. Speciﬁcally, we pro-pose a uniﬁed approach in which we train a fully-connected network jointly with the graph neural network via parameter sharing, interpolation-based regularization and self-predicted-targets. Our proposed method is architecture agnostic in the sense that it can be applied to any variant of graph neural networks which applies a parametric transformation to the features of the graph nodes. Despite its simplicity, with GraphMix we can consistently improve results and achieve or closely match state-of-the-art performance using even simpler architectures such as Graph Convolutional Networks, across three established graph benchmarks: Cora, Citeseer and Pubmed citation network datasets, as well as three newly proposed datasets :Cora-Full, Co-author-CS and Co-author-Physics.

2019-12-31

(published)

www.semanticscholar.org

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules

Murray Shanahan

Michael Mozer

Robust perception relies on both bottom-up and top-down signals. Bottom-up signals consist of what's directly observed through sensation. To… (see more)p-down signals consist of beliefs and expectations based on past experience and short-term memory, such as how the phrase `peanut butter and~...' will be completed. The optimal combination of bottom-up and top-down information remains an open question, but the manner of combination must be dynamic and both context and task dependent. To effectively utilize the wealth of potential top-down information available, and to prevent the cacophony of intermixed signals in a bidirectional architecture, mechanisms are needed to restrict information flow. We explore deep recurrent neural net architectures in which bottom-up and top-down signals are dynamically combined using attention. Modularity of the architecture further restricts the sharing and communication of information. Together, attention and modularity direct information flow, which leads to reliable performance improvements in perceptual and language tasks, and in particular improves robustness to distractions and noisy data. We demonstrate on a variety of benchmarks in language modeling, sequential image classification, video prediction and reinforcement learning that the \emph{bidirectional} information flow can improve results over strong baselines.

2019-12-31

ICML (published)

doi.org

proceedings.mlr.press

Interpolation Consistency Training for Semi-Supervised Learning

Juho Kannala

David Lopez-Paz

Arno Solin

2019-08-09

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (published)

doi.org

arxiv.org

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations

Denis Kazakov

Michael Mozer

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches … (see more)is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recurrent sequence-processing nets to stay on track without teacher forcing. We introduce a method, which we refer to as \emph{state reification}, that involves modeling the distribution of hidden states over the training data and then projecting hidden states observed during testing toward this distribution. Our intuition is that if the network can remain in a familiar manifold of hidden space, subsequent layers of the net should be well trained to respond appropriately. We show that this state-reification method helps neural nets to generalize better, especially when labeled data are sparse, and also helps overcome the challenge of achieving robust generalization with adversarial training.

2019-05-23

Proceedings of the 36th International Conference on Machine Learning (published)

doi.org

proceedings.mlr.press

On Adversarial Mixup Resynthesis

R Devon Hjelm

Christopher Pal

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore mo… (see more)dels that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.

2018-12-31

NeurIPS (published)

dblp.uni-trier.de

Adversarial Mixup Resynthesizers

R Devon Hjelm

Christopher Pal

In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders. We explore mod… (see more)els that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.

2018-12-31

DGS@ICLR (published)

openreview.net

Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Accuracy

Alex Lamb

Vikas Verma

Juho Kannala

Yoshua Bengio

Adversarial robustness has become a central goal in deep learning, both in theory and practice. However, successful methods to improve adver… (see more)sarial robustness (such as adversarial training) greatly hurt generalization performance on the clean data. This could have a major impact on how adversarial robustness affects real world systems (i.e. many may opt to forego robustness if it can improve performance on the clean data). We propose Interpolated Adversarial Training, which employs recently proposed interpolation based training methods in the framework of adversarial training. On CIFAR-10, adversarial training increases clean test error from 5.8% to 16.7%, whereas with our Interpolated adversarial training we retain adversarial robustness while achieving a clean test error of only 6.5%. With our technique, the relative error increase for the robust model is reduced from 187.9% to just 12.1%.

2018-12-31

arXiv.org (preprint)

dblp.uni-trier.de

Manifold Mixup: Better Representations by Interpolating Hidden States

Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly d… (see more)ifferent test examples. This includes distribution shifts, outliers, and adversarial examples. To address these issues, we propose Manifold Mixup, a simple regularizer that encourages neural networks to predict less confidently on interpolations of hidden representations. Manifold Mixup leverages semantic interpolations as additional training signal, obtaining neural networks with smoother decision boundaries at multiple levels of representation. As a result, neural networks trained with Manifold Mixup learn class-representations with fewer directions of variance. We prove theory on why this flattening happens under ideal conditions, validate it on practical situations, and connect it to previous works on information theory and generalization. In spite of incurring no significant computation and being implemented in a few lines of code, Manifold Mixup improves strong baselines in supervised learning, robustness to single-step adversarial attacks, and test log-likelihood.

2018-06-12

arXiv.org (preprint)

doi.org

arxiv.org

Mila Techaide 2026

Venture Scientist Bootcamp

AI Advantage: Productivity in Public Service

Publications

Mila Techaide 2026

Venture Scientist Bootcamp

AI Advantage: Productivity in Public Service

Popular keywords:

Alex Lamb

Publications