Timezone: »
Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised or reinforcement learning tasks, and often assumes full knowledge of task labels and boundaries. In this work, we propose an approach (CURL) to tackle a more general problem that we will refer to as unsupervised continual learning. The focus is on learning representations without any knowledge about task identity, and we explore scenarios when there are abrupt changes between tasks, smooth transitions from one task to another, or even when the data is shuffled. The proposed approach performs task inference directly within the model, is able to dynamically expand to capture new concepts over its lifetime, and incorporates additional rehearsal-based techniques to deal with catastrophic forgetting. We demonstrate the efficacy of CURL in an unsupervised learning setting with MNIST and Omniglot, where the lack of labels ensures no information is leaked about the task. Further, we demonstrate strong performance compared to prior art in an i.i.d setting, or when adapting the technique to supervised tasks such as incremental class learning.
Author Information
Dushyant Rao (DeepMind)
Francesco Visin (DeepMind)
Andrei A Rusu (DeepMind)
Razvan Pascanu (Google DeepMind)
Yee Whye Teh (University of Oxford, DeepMind)
I am a Professor of Statistical Machine Learning at the Department of Statistics, University of Oxford and a Research Scientist at DeepMind. I am also an Alan Turing Institute Fellow and a European Research Council Consolidator Fellow. I obtained my Ph.D. at the University of Toronto (working with Geoffrey Hinton), and did postdoctoral work at the University of California at Berkeley (with Michael Jordan) and National University of Singapore (as Lee Kuan Yew Postdoctoral Fellow). I was a Lecturer then a Reader at the Gatsby Computational Neuroscience Unit, UCL, and a tutorial fellow at University College Oxford, prior to my current appointment. I am interested in the statistical and computational foundations of intelligence, and works on scalable machine learning, probabilistic models, Bayesian nonparametrics and deep learning. I was programme co-chair of ICML 2017 and AISTATS 2010.
Raia Hadsell (DeepMind)
More from the Same Authors
-
2021 : LiRo: Benchmark and leaderboard for Romanian language tasks »
Stefan Dumitrescu · Petru Rebeja · Beata Lorincz · Mihaela Gaman · Andrei Avram · Mihai Ilie · Andrei Pruteanu · Adriana Stan · Lorena Rosia · Cristina Iacobescu · Luciana Morogan · George Dima · Gabriel Marchidan · Traian Rebedea · Madalina Chitez · Dani Yogatama · Sebastian Ruder · Radu Tudor Ionescu · Razvan Pascanu · Viorica Patraucean -
2021 : Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies »
Dushyant Rao · Fereshteh Sadeghi · Leonard Hasenclever · Markus Wulfmeier · Martina Zambelli · Giulia Vezzani · Dhruva Tirumala · Yusuf Aytar · Josh Merel · Nicolas Heess · Raia Hadsell -
2021 : Uncertainty Quantification in End-to-End Implicit Neural Representations for Medical Imaging »
Bobby He · Francisca Vasconcelos · Yee Whye Teh -
2021 : Uncertainty Quantification in End-to-End Implicit Neural Representations for Medical Imaging »
Francisca Vasconcelos · Bobby He · Yee Teh -
2022 : Pre-training via Denoising for Molecular Property Prediction »
Sheheryar Zaidi · Michael Schaarschmidt · James Martens · Hyunjik Kim · Yee Whye Teh · Alvaro Sanchez Gonzalez · Peter Battaglia · Razvan Pascanu · Jonathan Godwin -
2022 : Learning to Look by Self-Prediction »
Matthew Grimes · Joseph Modayil · Piotr Mirowski · Dushyant Rao · Raia Hadsell -
2022 : When Does Re-initialization Work? »
Sheheryar Zaidi · Tudor Berariu · Hyunjik Kim · Jorg Bornschein · Claudia Clopath · Yee Whye Teh · Razvan Pascanu -
2022 Spotlight: Lightning Talks 1A-4 »
Siwei Wang · Jing Liu · Nianqiao Ju · Shiqian Li · Eloïse Berthier · Muhammad Faaiz Taufiq · Arsene Fansi Tchango · Chen Liang · Chulin Xie · Jordan Awan · Jean-Francois Ton · Ziad Kobeissi · Wenguan Wang · Xinwang Liu · Kewen Wu · Rishab Goel · Jiaxu Miao · Suyuan Liu · Julien Martel · Ruobin Gong · Francis Bach · Chi Zhang · Rob Cornish · Sanmi Koyejo · Zhi Wen · Yee Whye Teh · Yi Yang · Jiaqi Jin · Bo Li · Yixin Zhu · Vinayak Rao · Wenxuan Tu · Gaetan Marceau Caron · Arnaud Doucet · Xinzhong Zhu · Joumana Ghosn · En Zhu -
2022 Spotlight: Conformal Off-Policy Prediction in Contextual Bandits »
Muhammad Faaiz Taufiq · Jean-Francois Ton · Rob Cornish · Yee Whye Teh · Arnaud Doucet -
2022 Poster: Disentangling Transfer in Continual Reinforcement Learning »
Maciej Wolczyk · Michał Zając · Razvan Pascanu · Łukasz Kuciński · Piotr Miłoś -
2022 Poster: Tractable Function-Space Variational Inference in Bayesian Neural Networks »
Tim G. J. Rudner · Zonghao Chen · Yee Whye Teh · Yarin Gal -
2022 Poster: Conformal Off-Policy Prediction in Contextual Bandits »
Muhammad Faaiz Taufiq · Jean-Francois Ton · Rob Cornish · Yee Whye Teh · Arnaud Doucet -
2022 Poster: Riemannian Score-Based Generative Modelling »
Valentin De Bortoli · Emile Mathieu · Michael Hutchinson · James Thornton · Yee Whye Teh · Arnaud Doucet -
2021 Poster: On Contrastive Representations of Stochastic Processes »
Emile Mathieu · Adam Foster · Yee Teh -
2021 Poster: Group Equivariant Subsampling »
Jin Xu · Hyunjik Kim · Thomas Rainforth · Yee Teh -
2021 Poster: Powerpropagation: A sparsity inducing weight reparameterisation »
Jonathan Richard Schwarz · Siddhant Jayakumar · Razvan Pascanu · Peter E Latham · Yee Teh -
2021 Poster: Continual World: A Robotic Benchmark For Continual Reinforcement Learning »
Maciej Wołczyk · Michał Zając · Razvan Pascanu · Łukasz Kuciński · Piotr Miłoś -
2021 Poster: On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations »
Tim G. J. Rudner · Cong Lu · Michael A Osborne · Yarin Gal · Yee Teh -
2021 Poster: On the Role of Optimization in Double Descent: A Least Squares Study »
Ilja Kuzborskij · Csaba Szepesvari · Omar Rivasplata · Amal Rannen-Triki · Razvan Pascanu -
2021 Poster: Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels »
Michael Hutchinson · Alexander Terenin · Viacheslav Borovitskiy · So Takao · Yee Teh · Marc Deisenroth -
2021 Poster: BayesIMP: Uncertainty Quantification for Causal Data Fusion »
Siu Lun Chau · Jean-Francois Ton · Javier González · Yee Teh · Dino Sejdinovic -
2021 Poster: Neural Ensemble Search for Uncertainty Estimation and Dataset Shift »
Sheheryar Zaidi · Arber Zela · Thomas Elsken · Chris C Holmes · Frank Hutter · Yee Teh -
2020 : Introduction for invited speaker, Luisa Zintgraf »
Francesco Visin -
2020 Workshop: Meta-Learning »
Jane Wang · Joaquin Vanschoren · Erin Grant · Jonathan Richard Schwarz · Francesco Visin · Jeff Clune · Roberto Calandra -
2020 Poster: Top-KAST: Top-K Always Sparse Training »
Siddhant Jayakumar · Razvan Pascanu · Jack Rae · Simon Osindero · Erich Elsen -
2020 Poster: Bayesian Deep Ensembles via the Neural Tangent Kernel »
Bobby He · Balaji Lakshminarayanan · Yee Whye Teh -
2020 Poster: Bootstrapping neural processes »
Juho Lee · Yoonho Lee · Jungtaek Kim · Eunho Yang · Sung Ju Hwang · Yee Whye Teh -
2020 Poster: Pointer Graph Networks »
Petar Veličković · Lars Buesing · Matthew Overlan · Razvan Pascanu · Oriol Vinyals · Charles Blundell -
2020 Spotlight: Pointer Graph Networks »
Petar Veličković · Lars Buesing · Matthew Overlan · Razvan Pascanu · Oriol Vinyals · Charles Blundell -
2020 Poster: Understanding the Role of Training Regimes in Continual Learning »
Seyed Iman Mirzadeh · Mehrdad Farajtabar · Razvan Pascanu · Hassan Ghasemzadeh -
2020 Poster: How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19? »
Mrinank Sharma · Sören Mindermann · Jan Brauner · Gavin Leech · Anna Stephenson · Tomáš Gavenčiak · Jan Kulveit · Yee Whye Teh · Leonid Chindelevitch · Yarin Gal -
2020 Spotlight: How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19? »
Mrinank Sharma · Sören Mindermann · Jan Brauner · Gavin Leech · Anna Stephenson · Tomáš Gavenčiak · Jan Kulveit · Yee Whye Teh · Leonid Chindelevitch · Yarin Gal -
2019 : Coffee Break & Poster Session 2 »
Juho Lee · Yoonho Lee · Yee Whye Teh · Raymond A. Yeh · Yuan-Ting Hu · Alex Schwing · Sara Ahmadian · Alessandro Epasto · Marina Knittel · Ravi Kumar · Mohammad Mahdian · Christian Bueno · Aditya Sanghi · Pradeep Kumar Jayaraman · Ignacio Arroyo-Fernández · Andrew Hryniowski · Vinayak Mathur · Sanjay Singh · Shahrzad Haddadan · Vasco Portilheiro · Luna Zhang · Mert Yuksekgonul · Jhosimar Arias Figueroa · Deepak Maurya · Balaraman Ravindran · Frank NIELSEN · Philip Pham · Justin Payan · Andrew McCallum · Jinesh Mehta · Ke SUN -
2019 : Invited Talk - Raia Hadsell »
Raia Hadsell -
2019 : Contributed Talk - Towards deep amortized clustering »
Juho Lee · Yoonho Lee · Yee Whye Teh -
2019 : Challenges of Deep RL in Complex Environments »
Raia Hadsell -
2019 : Scalable Meta-Learning »
Raia Hadsell -
2019 : Raia Hadsell »
Raia Hadsell -
2019 : Opening session - Competition track »
Hugo Jair Escalante · Raia Hadsell -
2019 Poster: Stacked Capsule Autoencoders »
Adam Kosiorek · Sara Sabour · Yee Whye Teh · Geoffrey E Hinton -
2019 Poster: Random Tessellation Forests »
Shufei Ge · Shijia Wang · Yee Whye Teh · Liangliang Wang · Lloyd Elliott -
2019 Poster: Variational Bayesian Optimal Experimental Design »
Adam Foster · Martin Jankowiak · Elias Bingham · Paul Horsfall · Yee Whye Teh · Thomas Rainforth · Noah Goodman -
2019 Spotlight: Variational Bayesian Optimal Experimental Design »
Adam Foster · Martin Jankowiak · Elias Bingham · Paul Horsfall · Yee Whye Teh · Thomas Rainforth · Noah Goodman -
2019 Poster: Augmented Neural ODEs »
Emilien Dupont · Arnaud Doucet · Yee Whye Teh -
2019 Poster: Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders »
Emile Mathieu · Charline Le Lan · Chris Maddison · Ryota Tomioka · Yee Whye Teh -
2018 : Meta-Learning with Latent Embedding Optimization »
Andrei A Rusu -
2018 : Invited Speaker #2 Raia Hadsell »
Raia Hadsell -
2018 : Introduction of the workshop »
Razvan Pascanu · Yee Teh · Mark Ring · Marc Pickett -
2018 Workshop: Continual Learning »
Razvan Pascanu · Yee Teh · Marc Pickett · Mark Ring -
2018 Workshop: Critiquing and Correcting Trends in Machine Learning »
Thomas Rainforth · Matt Kusner · Benjamin Bloem-Reddy · Brooks Paige · Rich Caruana · Yee Whye Teh -
2018 Poster: Faithful Inversion of Generative Models for Effective Amortized Inference »
Stefan Webb · Adam Golinski · Rob Zinkov · Siddharth N · Thomas Rainforth · Yee Whye Teh · Frank Wood -
2018 Poster: Causal Inference via Kernel Deviance Measures »
Jovana Mitrovic · Dino Sejdinovic · Yee Whye Teh -
2018 Spotlight: Causal Inference via Kernel Deviance Measures »
Jovana Mitrovic · Dino Sejdinovic · Yee Whye Teh -
2018 Poster: Learning to Navigate in Cities Without a Map »
Piotr Mirowski · Matt Grimes · Mateusz Malinowski · Karl Moritz Hermann · Keith Anderson · Denis Teplyashin · Karen Simonyan · koray kavukcuoglu · Andrew Zisserman · Raia Hadsell -
2018 Poster: Stochastic Expectation Maximization with Variance Reduction »
Jianfei Chen · Jun Zhu · Yee Whye Teh · Tong Zhang -
2018 Poster: Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects »
Adam Kosiorek · Hyunjik Kim · Yee Whye Teh · Ingmar Posner -
2018 Spotlight: Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects »
Adam Kosiorek · Hyunjik Kim · Yee Whye Teh · Ingmar Posner -
2018 Poster: Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction data »
Xenia Miscouridou · Francois Caron · Yee Whye Teh -
2018 Poster: Relational recurrent neural networks »
Adam Santoro · Ryan Faulkner · David Raposo · Jack Rae · Mike Chrzanowski · Theophane Weber · Daan Wierstra · Oriol Vinyals · Razvan Pascanu · Timothy Lillicrap -
2017 : Panel Session »
Neil Lawrence · Finale Doshi-Velez · Zoubin Ghahramani · Yann LeCun · Max Welling · Yee Whye Teh · Ole Winther -
2017 Workshop: Acting and Interacting in the Real World: Challenges in Robot Learning »
Ingmar Posner · Raia Hadsell · Martin Riedmiller · Markus Wulfmeier · Rohan Paul -
2017 Invited Talk: On Bayesian Deep Learning and Deep Bayesian Learning »
Yee Whye Teh -
2017 Poster: Distral: Robust multitask reinforcement learning »
Yee Teh · Victor Bapst · Wojciech Czarnecki · John Quan · James Kirkpatrick · Raia Hadsell · Nicolas Heess · Razvan Pascanu -
2017 Poster: A simple neural network module for relational reasoning »
Adam Santoro · David Raposo · David Barrett · Mateusz Malinowski · Razvan Pascanu · Peter Battaglia · Timothy Lillicrap -
2017 Poster: Imagination-Augmented Agents for Deep Reinforcement Learning »
Sébastien Racanière · Theophane Weber · David Reichert · Lars Buesing · Arthur Guez · Danilo Jimenez Rezende · Adrià Puigdomènech Badia · Oriol Vinyals · Nicolas Heess · Yujia Li · Razvan Pascanu · Peter Battaglia · Demis Hassabis · David Silver · Daan Wierstra -
2017 Spotlight: A simple neural network module for relational reasoning »
Adam Santoro · David Raposo · David Barrett · Mateusz Malinowski · Razvan Pascanu · Peter Battaglia · Timothy Lillicrap -
2017 Oral: Imagination-Augmented Agents for Deep Reinforcement Learning »
Sébastien Racanière · Theophane Weber · David Reichert · Lars Buesing · Arthur Guez · Danilo Jimenez Rezende · Adrià Puigdomènech Badia · Oriol Vinyals · Nicolas Heess · Yujia Li · Razvan Pascanu · Peter Battaglia · Demis Hassabis · David Silver · Daan Wierstra -
2017 Poster: Visual Interaction Networks: Learning a Physics Simulator from Video »
Nicholas Watters · Daniel Zoran · Theophane Weber · Peter Battaglia · Razvan Pascanu · Andrea Tacchetti -
2017 Poster: Filtering Variational Objectives »
Chris Maddison · John Lawson · George Tucker · Nicolas Heess · Mohammad Norouzi · Andriy Mnih · Arnaud Doucet · Yee Teh -
2017 Poster: Sobolev Training for Neural Networks »
Wojciech Czarnecki · Simon Osindero · Max Jaderberg · Grzegorz Swirszcz · Razvan Pascanu -
2016 Workshop: Continual Learning and Deep Networks »
Razvan Pascanu · Mark Ring · Tom Schaul -
2016 Poster: Gaussian Processes for Survival Analysis »
Tamara Fernandez · Nicolas Rivera · Yee Whye Teh -
2016 Poster: Interaction Networks for Learning about Objects, Relations and Physics »
Peter Battaglia · Razvan Pascanu · Matthew Lai · Danilo Jimenez Rezende · koray kavukcuoglu -
2015 Workshop: Scalable Monte Carlo Methods for Bayesian Analysis of Big Data »
Babak Shahbaba · Yee Whye Teh · Max Welling · Arnaud Doucet · Christophe Andrieu · Sebastian J. Vollmer · Pierre Jacob -
2015 : Random Tensor Decompositions for Regression and Collaborative Filtering »
Yee Whye Teh -
2015 Poster: Natural Neural Networks »
Guillaume Desjardins · Karen Simonyan · Razvan Pascanu · koray kavukcuoglu -
2015 Poster: A hybrid sampler for Poisson-Kingman mixture models »
Maria Lomeli · Stefano Favaro · Yee Whye Teh -
2015 Poster: Expectation Particle Belief Propagation »
Thibaut Lienart · Yee Whye Teh · Arnaud Doucet -
2014 Poster: Distributed Bayesian Posterior Sampling via Moment Sharing »
Minjie Xu · Balaji Lakshminarayanan · Yee Whye Teh · Jun Zhu · Bo Zhang -
2014 Poster: Asynchronous Anytime Sequential Monte Carlo »
Brooks Paige · Frank Wood · Arnaud Doucet · Yee Whye Teh -
2014 Poster: Identifying and attacking the saddle point problem in high-dimensional non-convex optimization »
Yann N Dauphin · Razvan Pascanu · Caglar Gulcehre · Kyunghyun Cho · Surya Ganguli · Yoshua Bengio -
2014 Oral: Asynchronous Anytime Sequential Monte Carlo »
Brooks Paige · Frank Wood · Arnaud Doucet · Yee Whye Teh -
2014 Poster: On the Number of Linear Regions of Deep Neural Networks »
Guido F Montufar · Razvan Pascanu · Kyunghyun Cho · Yoshua Bengio -
2014 Poster: Mondrian Forests: Efficient Online Random Forests »
Balaji Lakshminarayanan · Daniel Roy · Yee Whye Teh -
2013 Poster: Learning with Invariance via Linear Functionals on Reproducing Kernel Hilbert Space »
Xinhua Zhang · Wee Sun Lee · Yee Whye Teh -
2013 Spotlight: Learning with Invariance via Linear Functionals on Reproducing Kernel Hilbert Space »
Xinhua Zhang · Wee Sun Lee · Yee Whye Teh -
2013 Poster: Bayesian Hierarchical Community Discovery »
Charles Blundell · Yee Whye Teh -
2013 Poster: Stochastic Gradient Riemannian Langevin Dynamics on the Probability Simplex »
Sam Patterson · Yee Whye Teh -
2013 Spotlight: Stochastic Gradient Riemannian Langevin Dynamics on the Probability Simplex »
Sam Patterson · Yee Whye Teh -
2012 Poster: Searching for objects driven by context »
Bogdan Alexe · Nicolas Heess · Yee Whye Teh · Vittorio Ferrari -
2012 Poster: Learning Label Trees for Probabilistic Modelling of Implicit Feedback »
Andriy Mnih · Yee Whye Teh -
2012 Poster: MCMC for continuous-time discrete-state systems »
Vinayak Rao · Yee Whye Teh -
2012 Poster: Bayesian nonparametric models for ranked data »
Francois Caron · Yee Whye Teh -
2012 Spotlight: Searching for objects driven by context »
Bogdan Alexe · Nicolas Heess · Yee Whye Teh · Vittorio Ferrari -
2012 Poster: Scalable imputation of genetic data with a discrete fragmentation-coagulation process »
Lloyd T Elliott · Yee Whye Teh -
2011 Poster: Modelling Genetic Variations using Fragmentation-Coagulation Processes »
Yee Whye Teh · Charles Blundell · Lloyd T Elliott -
2011 Oral: Modelling Genetic Variations using Fragmentation-Coagulation Processes »
Yee Whye Teh · Charles Blundell · Lloyd T Elliott -
2011 Poster: Gaussian process modulated renewal processes »
Vinayak Rao · Yee Whye Teh -
2011 Tutorial: Modern Bayesian Nonparametrics »
Peter Orbanz · Yee Whye Teh -
2010 Poster: Improvements to the Sequence Memoizer »
Jan Gasthaus · Yee Whye Teh -
2009 Workshop: Nonparametric Bayes »
Dilan Gorur · Francois Caron · Yee Whye Teh · David B Dunson · Zoubin Ghahramani · Michael Jordan -
2009 Workshop: Grammar Induction, Representation of Language and Language Learning »
Alex Clark · Dorota Glowacka · John Shawe-Taylor · Yee Whye Teh · Chris J Watkins -
2009 Poster: Indian Buffet Processes with Power-law Behavior »
Yee Whye Teh · Dilan Gorur -
2009 Spotlight: Indian Buffet Processes with Power-law Behavior »
Yee Whye Teh · Dilan Gorur -
2009 Poster: Spatial Normalized Gamma Processes »
Vinayak Rao · Yee Whye Teh -
2009 Spotlight: Spatial Normalized Gamma Processes »
Vinayak Rao · Yee Whye Teh -
2008 Oral: The Mondrian Process »
Daniel Roy · Yee Whye Teh -
2008 Poster: The Infinite Factorial Hidden Markov Model »
Jurgen Van Gael · Yee Whye Teh · Zoubin Ghahramani -
2008 Poster: The Mondrian Process »
Daniel Roy · Yee Whye Teh -
2008 Spotlight: The Infinite Factorial Hidden Markov Model »
Jurgen Van Gael · Yee Whye Teh · Zoubin Ghahramani -
2008 Poster: A mixture model for the evolution of gene expression in non-homogeneous datasets »
Gerald Quon · Yee Whye Teh · Esther Chan · Michael Brudno · Tim Hughes · Quaid Morris -
2008 Poster: Dependent Dirichlet Process Spike Sorting »
Jan Gasthaus · Frank Wood · Dilan Gorur · Yee Whye Teh -
2008 Poster: An Efficient Sequential Monte Carlo Algorithm for Coalescent Clustering »
Dilan Gorur · Yee Whye Teh -
2007 Poster: Bayesian Agglomerative Clustering with Coalescents »
Yee Whye Teh · Hal Daumé III · Daniel Roy -
2007 Poster: Cooled and Relaxed Survey Propagation for MRFs »
Hai Leong Chieu · Wee Sun Lee · Yee Whye Teh -
2007 Session: Session 5: Probabilistic Representations and Learning »
Yee Whye Teh -
2007 Spotlight: Cooled and Relaxed Survey Propagation for MRFs »
Hai Leong Chieu · Wee Sun Lee · Yee Whye Teh -
2007 Oral: Bayesian Agglomerative Clustering with Coalescents »
Yee Whye Teh · Hal Daumé III · Daniel Roy -
2007 Spotlight: Collapsed Variational Inference for HDP »
Yee Whye Teh · Kenichi Kurihara · Max Welling -
2007 Poster: Collapsed Variational Inference for HDP »
Yee Whye Teh · Kenichi Kurihara · Max Welling -
2006 Poster: A Collapsed Variational Bayesian Inference Algorithm for Latent Dirichlet Allocation »
Yee Whye Teh · David Newman · Max Welling