MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective

no code implementations • 23 May 2024 • Yizhuo Chen, Chun-Fu Chen, Hsiang Hsu, Shaohan Hu, Marco Pistoia, Tarek Abdelzaher

The growing richness of large-scale datasets has been crucial in driving the rapid advancement and wide adoption of machine learning technologies.

On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study

no code implementations • 3 Apr 2024 • Tomoyoshi Kimura, Jinyang Li, Tianshi Wang, Denizhan Kara, Yizhuo Chen, Yigong Hu, Ruijie Wang, Maggie Wigness, Shengzhong Liu, Mani Srivastava, Suhas Diggavi, Tarek Abdelzaher

This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a class of) IoT applications.

Rethinking Controllable Variational Autoencoders

no code implementations • CVPR 2022 • Huajie Shao, Yifei Yang, Haohong Lin, Longzhong Lin, Yizhuo Chen, Qinmin Yang, Han Zhao

It has shown success in a variety of applications, such as image generation, disentangled representation learning, and language modeling.

Disentanglement Image Generation +1

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models

no code implementations • CVPR 2023 • Yizhuo Chen, Kaizhao Liang, Zhe Zeng, Yifei Yang, Shuochao Yao, Huajie Shao

Moreover, our method achieves good performance for discriminative deep DGMs compression.

Continual Learning Federated Learning +2