Timezone: »
Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades the performance. In this paper, we first identify the main causes of this phenomenon by theoretically and empirically analyzing the mixup algorithm. To resolve this, we propose GenLabel, a simple yet effective relabeling algorithm designed for mixup. In particular, GenLabel helps the mixup algorithm correctly label mixup samples by learning the class-conditional data distribution using generative models. Via theoretical and empirical analysis, we show that mixup, when used together with GenLabel, can effectively resolve the aforementioned phenomenon, improving the accuracy of mixup-trained model.
Author Information
Jy yong Sohn (University of Wisconsin-Madison)
Liang Shang (University of Wisconsin-Madison)
Hongxu Chen (University of Wisconsin-Madison)
Jaekyun Moon (KAIST)
Dimitris Papailiopoulos (University of Wisconsin-Madison)
Kangwook Lee (UW Madison)
I am an Assistant Professor at the Electrical and Computer Engineering department and the Computer Sciences department (by courtesy) at the University of Wisconsin-Madison. Previously, I was a Research Assistant Professor at Information and Electronics Research Institute of KAIST, working with Prof. Changho Suh. Before that, I was a postdoctoral scholar at the same institute. I received my PhD in May 2016 from the Electrical Engineering and Computer Science department at UC Berkeley and my Master of Science degree from the same department in December 2012, both under the supervision of Prof. Kannan Ramchandran. I was a member of Berkeley Laboratory of Information and System Sciences (BLISS, aka Wireless Foundation) and BASiCS Group. I received my Bachelor of Science degree in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST) in May 2010.
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: GenLabel: Mixup Relabeling using Generative Models »
Wed. Jul 20th through Thu the 21st Room Hall E #525
More from the Same Authors
-
2021 : Empirical Study on the Effective VC Dimension of Low-rank Neural Networks »
Daewon Seo · Hongyi Wang · Dimitris Papailiopoulos · Kangwook Lee -
2022 : Style Balancing and Test-Time Style Shifting for Domain Generalization »
Jungwuk Park · Dong-Jun Han · Soyeong Kim · Jaekyun Moon -
2023 : Teaching Arithmetic to Small Transformers »
Nayoung Lee · Kartik Sreenivasan · Jason Lee · Kangwook Lee · Dimitris Papailiopoulos -
2023 : Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding »
Seongjun Yang · Gibbeum Lee · Jaewoong Cho · Dimitris Papailiopoulos · Kangwook Lee -
2023 : Looped Transformers are Better at Learning Learning Algorithms »
Liu Yang · Kangwook Lee · Robert Nowak · Dimitris Papailiopoulos -
2023 Poster: Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization »
Jungwuk Park · Dong-Jun Han · Soyeong Kim · Jaekyun Moon -
2023 Poster: Looped Transformers as Programmable Computers »
Angeliki Giannou · Shashank Rajput · Jy-yong Sohn · Kangwook Lee · Jason Lee · Dimitris Papailiopoulos -
2023 Poster: Transformers as Algorithms: Generalization and Stability in In-context Learning »
Yingcong Li · Muhammed Ildiz · Dimitris Papailiopoulos · Samet Oymak -
2022 : Locally Supervised Learning with Periodic Global Guidance »
Hasnain Irshad Bhatti · Jaekyun Moon -
2021 : Dreaming of Federated Robustness: Inherent Barriers and Unavoidable Tradeoffs »
Dimitris Papailiopoulos -
2021 Poster: Coded-InvNet for Resilient Prediction Serving Systems »
Tuan Dinh · Kangwook Lee -
2021 Oral: Coded-InvNet for Resilient Prediction Serving Systems »
Tuan Dinh · Kangwook Lee -
2021 Poster: Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information »
Changhun Jo · Kangwook Lee -
2021 Spotlight: Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information »
Changhun Jo · Kangwook Lee -
2020 Poster: FR-Train: A Mutual Information-Based Approach to Fair and Robust Training »
Yuji Roh · Kangwook Lee · Steven Whang · Changho Suh -
2020 Poster: XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning »
Sung Whan Yoon · Do-Yeon Kim · Jun Seo · Jaekyun Moon -
2020 Poster: Closing the convergence gap of SGD without replacement »
Shashank Rajput · Anant Gupta · Dimitris Papailiopoulos -
2019 Workshop: Coding Theory For Large-scale Machine Learning »
Viveck Cadambe · Pulkit Grover · Dimitris Papailiopoulos · Gauri Joshi -
2019 Poster: Does Data Augmentation Lead to Positive Margin? »
Shashank Rajput · Zhili Feng · Zachary Charles · Po-Ling Loh · Dimitris Papailiopoulos -
2019 Oral: Does Data Augmentation Lead to Positive Margin? »
Shashank Rajput · Zhili Feng · Zachary Charles · Po-Ling Loh · Dimitris Papailiopoulos -
2019 Poster: TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning »
Sung Whan Yoon · Jun Seo · Jaekyun Moon -
2019 Oral: TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning »
Sung Whan Yoon · Jun Seo · Jaekyun Moon -
2018 Poster: DRACO: Byzantine-resilient Distributed Training via Redundant Gradients »
Lingjiao Chen · Hongyi Wang · Zachary Charles · Dimitris Papailiopoulos -
2018 Oral: DRACO: Byzantine-resilient Distributed Training via Redundant Gradients »
Lingjiao Chen · Hongyi Wang · Zachary Charles · Dimitris Papailiopoulos -
2018 Poster: Stability and Generalization of Learning Algorithms that Converge to Global Optima »
Zachary Charles · Dimitris Papailiopoulos -
2018 Oral: Stability and Generalization of Learning Algorithms that Converge to Global Optima »
Zachary Charles · Dimitris Papailiopoulos