Timezone: »
We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Based on this view, we design a deep causal manipulation augmented model (deep CAMA) which explicitly models possible manipulations on certain causes leading to changes in the observed effect. We further develop data augmentation and test-time fine-tuning methods to improve deep CAMA's robustness. When compared with discriminative deep neural networks, our proposed model shows superior robustness against unseen manipulations. As a by-product, our model achieves disentangled representation which separates the representation of manipulations from those of other latent causes.
Author Information
Cheng Zhang (Microsoft Research, Cambridge, UK)
Cheng Zhang is a principal researcher at Microsoft Research Cambridge, UK. She leads the Data Efficient Decision Making (Project Azua) team in Microsoft. Before joining Microsoft, she was with the statistical machine learning group of Disney Research Pittsburgh, located at Carnegie Mellon University. She received her Ph.D. from the KTH Royal Institute of Technology. She is interested in advancing machine learning methods, including variational inference, deep generative models, and sequential decision-making under uncertainty; and adapting machine learning to social impactful applications such as education and healthcare. She co-organized the Symposium on Advances in Approximate Bayesian Inference from 2017 to 2019.
Kun Zhang (CMU)
Yingzhen Li (Microsoft Research Cambridge)
More from the Same Authors
-
2020 Workshop: Causal Discovery and Causality-Inspired Machine Learning »
Biwei Huang · Sara Magliacane · Kun Zhang · Danielle Belgrave · Elias Bareinboim · Daniel Malinsky · Thomas Richardson · Christopher Meek · Peter Spirtes · Bernhard Schölkopf -
2020 Poster: On the Role of Sparsity and DAG Constraints for Learning Linear DAGs »
Ignavier Ng · AmirEmad Ghassami · Kun Zhang -
2020 Poster: VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data »
Chao Ma · Sebastian Tschiatschek · Richard Turner · José Miguel Hernández-Lobato · Cheng Zhang -
2020 Session: Orals & Spotlights Track 27: Unsupervised/Probabilistic »
Marina Meila · Kun Zhang -
2020 Poster: How do fair decisions fare in long-term qualification? »
Xueru Zhang · Ruibo Tu · Yang Liu · Mingyan Liu · Hedvig Kjellstrom · Kun Zhang · Cheng Zhang -
2020 Poster: Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs »
Feng Xie · Ruichu Cai · Biwei Huang · Clark Glymour · Zhifeng Hao · Kun Zhang -
2020 Spotlight: Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs »
Feng Xie · Ruichu Cai · Biwei Huang · Clark Glymour · Zhifeng Hao · Kun Zhang -
2020 Tutorial: (Track1) Advances in Approximate Inference Q&A »
Yingzhen Li · Cheng Zhang -
2020 Poster: Domain Adaptation as a Problem of Inference on Graphical Models »
Kun Zhang · Mingming Gong · Petar Stojanov · Biwei Huang · QINGSONG LIU · Clark Glymour -
2020 Tutorial: (Track1) Advances in Approximate Inference »
Yingzhen Li · Cheng Zhang -
2019 Poster: Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck »
Maximilian Igl · Kamil Ciosek · Yingzhen Li · Sebastian Tschiatschek · Cheng Zhang · Sam Devlin · Katja Hofmann -
2019 Poster: Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation »
Ruibo Tu · Kun Zhang · Bo Bertilson · Hedvig Kjellstrom · Cheng Zhang -
2019 Poster: Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model »
Wenbo Gong · Sebastian Tschiatschek · Sebastian Nowozin · Richard Turner · José Miguel Hernández-Lobato · Cheng Zhang -
2019 Poster: Triad Constraints for Learning Causal Structure of Latent Variables »
Ruichu Cai · Feng Xie · Clark Glymour · Zhifeng Hao · Kun Zhang -
2019 Poster: Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering »
Biwei Huang · Kun Zhang · Pengtao Xie · Mingming Gong · Eric Xing · Clark Glymour -
2019 Poster: Twin Auxilary Classifiers GAN »
Mingming Gong · Yanwu Xu · Chunyuan Li · Kun Zhang · Kayhan Batmanghelich -
2019 Spotlight: Twin Auxilary Classifiers GAN »
Mingming Gong · Yanwu Xu · Chunyuan Li · Kun Zhang · Kayhan Batmanghelich -
2019 Poster: Likelihood-Free Overcomplete ICA and Applications In Causal Discovery »
Chenwei DING · Mingming Gong · Kun Zhang · Dacheng Tao -
2019 Spotlight: Likelihood-Free Overcomplete ICA and Applications In Causal Discovery »
Chenwei DING · Mingming Gong · Kun Zhang · Dacheng Tao -
2018 Poster: Multi-domain Causal Structure Learning in Linear Systems »
AmirEmad Ghassami · Negar Kiyavash · Biwei Huang · Kun Zhang -
2018 Poster: Causal Discovery from Discrete Data using Hidden Compact Representation »
Ruichu Cai · Jie Qiao · Kun Zhang · Zhenjie Zhang · Zhifeng Hao -
2018 Poster: Modeling Dynamic Missingness of Implicit Feedback for Recommendation »
Menghan Wang · Mingming Gong · Xiaolin Zheng · Kun Zhang -
2017 Poster: Learning Causal Structures Using Regression Invariance »
AmirEmad Ghassami · Saber Salehkaleybar · Negar Kiyavash · Kun Zhang