Timezone: »
Poster
On Learning Invariant Representations for Domain Adaptation
Han Zhao · Remi Tachet des Combes · Kun Zhang · Geoff Gordon
Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small error on the source domain. The hope is that the learnt representation, together with the hypothesis learnt from the source domain, can generalize to the target domain. In this paper, we first construct a simple counterexample showing that, contrary to common belief, the above conditions are not sufficient to guarantee successful domain adaptation. In particular, the counterexample exhibits \emph{conditional shift}: the class-conditional distributions of input features change between source and target domains. To give a sufficient condition for domain adaptation, we propose a natural and interpretable generalization upper bound that explicitly takes into account the aforementioned shift. Moreover, we shed new light on the problem by proving an information-theoretic lower bound on the joint error of \emph{any} domain adaptation method that attempts to learn invariant representations. Our result characterizes a fundamental tradeoff between learning invariant representations and achieving small joint error on both domains when the marginal label distributions differ from source to target. Finally, we conduct experiments on real-world datasets that corroborate our theoretical findings. We believe these insights are helpful in guiding the future design of domain adaptation and representation learning algorithms.
Author Information
Han Zhao (Carnegie Mellon University)
PhD@CMU
Remi Tachet des Combes (Microsoft Research Montreal)
Kun Zhang (Carnegie Mellon University)
Geoff Gordon (Carnegie Mellon University)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: On Learning Invariant Representations for Domain Adaptation »
Tue. Jun 11th 09:00 -- 09:20 PM Room Grand Ballroom
More from the Same Authors
-
2021 : Optimal transport for causal discovery »
Ruibo Tu · Kun Zhang · Hedvig Kjellström · Cheng Zhang -
2022 : Causal Balancing for Domain Generalization »
Xinyi Wang · Michael Saxon · Jiachen Li · Hongyang Zhang · Kun Zhang · William Wang -
2023 : Counterfactual Generation with Identifiability Guarantees »
Hanqi Yan · Lingjing Kong · Lin Gui · Yuejie Chi · Eric Xing · Yulan He · Kun Zhang -
2023 : Identification of Nonlinear Latent Hierarchical Causal Models »
Lingjing Kong · Biwei Huang · Feng Xie · Eric Xing · Yuejie Chi · Kun Zhang -
2023 : Advancing Counterfactual Inference through Quantile Regression »
Shaoan Xie · Biwei Huang · Bin Gu · Tongliang Liu · Kun Zhang -
2023 : Natural Counterfactuals With Necessary Backtracking »
Guangyuan Hao · Jiji Zhang · Hao Wang · Kun Zhang -
2023 : Natural Counterfactuals With Necessary Backtracking »
Guangyuan Hao · Jiji Zhang · Hao Wang · Kun Zhang -
2023 Poster: Identifiability of Label Noise Transition Matrix »
Yang Liu · Hao Cheng · Kun Zhang -
2023 Poster: Causal Discovery with Latent Confounders Based on Higher-Order Cumulants »
Ruichu Cai · Zhiyi Huang · Wei Chen · Zhifeng Hao · Kun Zhang -
2023 Poster: Feature Expansion for Graph Neural Networks »
Jiaqi Sun · Lin Zhang · Guangyi Chen · Peng XU · Kun Zhang · Yujiu Yang -
2023 Poster: Model Transferability with Responsive Decision Subjects »
Yatong Chen · Zeyu Tang · Kun Zhang · Yang Liu -
2023 Poster: Evolving Semantic Prototype Improves Generative Zero-Shot Learning »
Shiming Chen · Wenjin Hou · Ziming Hong · Xiaohan Ding · Yibing Song · Xinge You · Tongliang Liu · Kun Zhang -
2023 Poster: Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise? »
Yu Yao · Mingming Gong · Yuxuan Du · Jun Yu · Bo Han · Kun Zhang · Tongliang Liu -
2022 : Model Transferability With Responsive Decision Subjects »
Yang Liu · Yatong Chen · Zeyu Tang · Kun Zhang -
2022 Poster: Identification of Linear Non-Gaussian Latent Hierarchical Structure »
Feng Xie · Biwei Huang · Zhengming Chen · Yangbo He · zhi geng · Kun Zhang -
2022 Poster: Action-Sufficient State Representation Learning for Control with Structural Constraints »
Biwei Huang · Chaochao Lu · Liu Leqi · Jose Miguel Hernandez-Lobato · Clark Glymour · Bernhard Schölkopf · Kun Zhang -
2022 Spotlight: Action-Sufficient State Representation Learning for Control with Structural Constraints »
Biwei Huang · Chaochao Lu · Liu Leqi · Jose Miguel Hernandez-Lobato · Clark Glymour · Bernhard Schölkopf · Kun Zhang -
2022 Spotlight: Identification of Linear Non-Gaussian Latent Hierarchical Structure »
Feng Xie · Biwei Huang · Zhengming Chen · Yangbo He · zhi geng · Kun Zhang -
2022 Poster: Partial disentanglement for domain adaptation »
Lingjing Kong · Shaoan Xie · Weiran Yao · Yujia Zheng · Guangyi Chen · Petar Stojanov · Victor Akinwande · Kun Zhang -
2022 Spotlight: Partial disentanglement for domain adaptation »
Lingjing Kong · Shaoan Xie · Weiran Yao · Yujia Zheng · Guangyi Chen · Petar Stojanov · Victor Akinwande · Kun Zhang -
2021 Poster: Decomposed Mutual Information Estimation for Contrastive Representation Learning »
Alessandro Sordoni · Nouha Dziri · Hannes Schulz · Geoff Gordon · Philip Bachman · Remi Tachet des Combes -
2021 Poster: Understanding and Mitigating Accuracy Disparity in Regression »
Jianfeng Chi · Yuan Tian · Geoff Gordon · Han Zhao -
2021 Spotlight: Understanding and Mitigating Accuracy Disparity in Regression »
Jianfeng Chi · Yuan Tian · Geoff Gordon · Han Zhao -
2021 Spotlight: Decomposed Mutual Information Estimation for Contrastive Representation Learning »
Alessandro Sordoni · Nouha Dziri · Hannes Schulz · Geoff Gordon · Philip Bachman · Remi Tachet des Combes -
2021 Poster: Information Obfuscation of Graph Neural Networks »
Peiyuan Liao · Han Zhao · Keyulu Xu · Tommi Jaakkola · Geoff Gordon · Stefanie Jegelka · Ruslan Salakhutdinov -
2021 Spotlight: Information Obfuscation of Graph Neural Networks »
Peiyuan Liao · Han Zhao · Keyulu Xu · Tommi Jaakkola · Geoff Gordon · Stefanie Jegelka · Ruslan Salakhutdinov -
2020 Poster: Label-Noise Robust Domain Adaptation »
Xiyu Yu · Tongliang Liu · Mingming Gong · Kun Zhang · Kayhan Batmanghelich · Dacheng Tao -
2020 Poster: On Learning Language-Invariant Representations for Universal Machine Translation »
Han Zhao · Junjie Hu · Andrej Risteski -
2020 Poster: LTF: A Label Transformation Framework for Correcting Label Shift »
Jiaxian Guo · Mingming Gong · Tongliang Liu · Kun Zhang · Dacheng Tao -
2020 Poster: Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs »
AmirEmad Ghassami · Alan Yang · Negar Kiyavash · Kun Zhang -
2019 Poster: Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models »
Biwei Huang · Kun Zhang · Mingming Gong · Clark Glymour -
2019 Oral: Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models »
Biwei Huang · Kun Zhang · Mingming Gong · Clark Glymour -
2018 Poster: Recurrent Predictive State Policy Networks »
Ahmed Hefny · Zita Marinho · Wen Sun · Siddhartha Srinivasa · Geoff Gordon -
2018 Oral: Recurrent Predictive State Policy Networks »
Ahmed Hefny · Zita Marinho · Wen Sun · Siddhartha Srinivasa · Geoff Gordon -
2017 Poster: Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction »
Wen Sun · Arun Venkatraman · Geoff Gordon · Byron Boots · Drew Bagnell -
2017 Talk: Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction »
Wen Sun · Arun Venkatraman · Geoff Gordon · Byron Boots · Drew Bagnell