Timezone: »
A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled datapoints, implicitly accepting that these points may, in reality, actually have the same label. Perhaps unsurprisingly, we observe that sampling negative examples from truly different labels improves performance, in a synthetic setting where labels are available. Motivated by this observation, we develop a debiased contrastive objective that corrects for the sampling of same-label datapoints, even without knowledge of the true labels. Empirically, the proposed objective consistently outperforms the state-of-the-art for representation learning in vision, language, and reinforcement learning benchmarks. Theoretically, we establish generalization bounds for the downstream classification task.
Author Information
Ching-Yao Chuang (MIT)
Joshua Robinson (MIT)
Yen-Chen Lin (MIT)
Antonio Torralba (MIT)
Stefanie Jegelka (MIT)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Spotlight: Debiased Contrastive Learning »
Tue. Dec 8th 04:00 -- 04:10 AM Room Orals & Spotlights: Representation/Relational
More from the Same Authors
-
2021 Spotlight: Measuring Generalization with Optimal Transport »
Ching-Yao Chuang · Youssef Mroueh · Kristjan Greenewald · Antonio Torralba · Stefanie Jegelka -
2023 Poster: Limits, approximation and size transferability for GNNs on sparse graphs via graphops »
Thien Le · Stefanie Jegelka -
2023 Poster: Expressive Sign Equivariant Networks for Spectral Geometric Learning »
Derek Lim · Joshua Robinson · Stefanie Jegelka · Haggai Maron -
2023 Poster: 3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes »
Haotian Xue · Antonio Torralba · Josh Tenenbaum · Dan Yamins · Yunzhu Li · Hsiao-Yu Tung -
2023 Poster: Structure from Duplicates: Neural Inverse Graphics from a Single Image »
Tianhang Cheng · Wei-Chiu Ma · Kaiyu Guan · Antonio Torralba · Shenlong Wang -
2023 Poster: The Exact Sample Complexity Gain from Invariances for Kernel Regression »
Behrooz Tahmasebi · Stefanie Jegelka -
2023 Poster: What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models »
Khashayar Gatmiry · Zhiyuan Li · Tengyu Ma · Sashank Reddi · Stefanie Jegelka · Ching-Yao Chuang -
2023 Workshop: Heavy Tails in ML: Structure, Stability, Dynamics »
Mert Gurbuzbalaban · Stefanie Jegelka · Michael Mahoney · Umut Simsekli -
2022 : Panel »
Roman Garnett · José Miguel Hernández-Lobato · Eytan Bakshy · Syrine Belakaria · Stefanie Jegelka -
2022 Workshop: New Frontiers in Graph Learning »
Jiaxuan You · Marinka Zitnik · Rex Ying · Yizhou Sun · Hanjun Dai · Stefanie Jegelka -
2022 Poster: Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks »
Ching-Yao Chuang · Stefanie Jegelka -
2022 Poster: Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions »
Nikolaos Karalias · Joshua Robinson · Andreas Loukas · Stefanie Jegelka -
2022 Poster: On the generalization of learning algorithms that do not converge »
Nisha Chandramoorthy · Andreas Loukas · Khashayar Gatmiry · Stefanie Jegelka -
2022 Poster: Procedural Image Programs for Representation Learning »
Manel Baradad · Richard Chen · Jonas Wulff · Tongzhou Wang · Rogerio Feris · Antonio Torralba · Phillip Isola -
2022 Poster: Learning Neural Acoustic Fields »
Andrew Luo · Yilun Du · Michael Tarr · Josh Tenenbaum · Antonio Torralba · Chuang Gan -
2022 Poster: Pre-Trained Language Models for Interactive Decision-Making »
Shuang Li · Xavier Puig · Chris Paxton · Yilun Du · Clinton Wang · Linxi Fan · Tao Chen · De-An Huang · Ekin Akyürek · Anima Anandkumar · Jacob Andreas · Igor Mordatch · Antonio Torralba · Yuke Zhu -
2022 Poster: ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment »
Joseph DelPreto · Chao Liu · Yiyue Luo · Michael Foshey · Yunzhu Li · Antonio Torralba · Wojciech Matusik · Daniela Rus -
2021 Poster: Can contrastive learning avoid shortcut solutions? »
Joshua Robinson · Li Sun · Ke Yu · Kayhan Batmanghelich · Stefanie Jegelka · Suvrit Sra -
2021 Poster: Measuring Generalization with Optimal Transport »
Ching-Yao Chuang · Youssef Mroueh · Kristjan Greenewald · Antonio Torralba · Stefanie Jegelka -
2020 Poster: Adaptive Sampling for Stochastic Risk-Averse Learning »
Sebastian Curi · Kfir Y. Levy · Stefanie Jegelka · Andreas Krause -
2019 Workshop: Graph Representation Learning »
Will Hamilton · Rianne van den Berg · Michael Bronstein · Stefanie Jegelka · Thomas Kipf · Jure Leskovec · Renjie Liao · Yizhou Sun · Petar Veličković -
2019 Poster: Flexible Modeling of Diversity with Strongly Log-Concave Distributions »
Joshua Robinson · Suvrit Sra · Stefanie Jegelka -
2018 : Panel Discussion »
Antonio Torralba · Douwe Kiela · Barbara Landau · Angeliki Lazaridou · Joyce Chai · Christopher Manning · Stevan Harnad · Roozbeh Mottaghi -
2018 : Antonio Torralba - Learning to See and Hear »
Antonio Torralba -
2018 Poster: Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding »
Kexin Yi · Jiajun Wu · Chuang Gan · Antonio Torralba · Pushmeet Kohli · Josh Tenenbaum -
2018 Poster: 3D-Aware Scene Manipulation via Inverse Graphics »
Shunyu Yao · Tzu Ming Hsu · Jun-Yan Zhu · Jiajun Wu · Antonio Torralba · Bill Freeman · Josh Tenenbaum -
2018 Spotlight: Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding »
Kexin Yi · Jiajun Wu · Chuang Gan · Antonio Torralba · Pushmeet Kohli · Josh Tenenbaum -
2016 Poster: Generating Videos with Scene Dynamics »
Carl Vondrick · Hamed Pirsiavash · Antonio Torralba -
2016 Poster: SoundNet: Learning Sound Representations from Unlabeled Video »
Yusuf Aytar · Carl Vondrick · Antonio Torralba -
2015 Poster: Skip-Thought Vectors »
Jamie Kiros · Yukun Zhu · Russ Salakhutdinov · Richard Zemel · Raquel Urtasun · Antonio Torralba · Sanja Fidler -
2015 Poster: Where are they looking? »
Adria Recasens · Aditya Khosla · Carl Vondrick · Antonio Torralba -
2015 Spotlight: Where are they looking? »
Adria Recasens · Aditya Khosla · Carl Vondrick · Antonio Torralba -
2015 Poster: Learning visual biases from human imagination »
Carl Vondrick · Hamed Pirsiavash · Aude Oliva · Antonio Torralba