Timezone: »
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device. Traditional outsourcing requires uploading device data to the cloud server, which can be infeasible in many real-world applications due to the often sensitive nature of the collected data and the limited communication bandwidth. To tackle these challenges, we propose to leverage widely available open-source data, which is a massive dataset collected from public and heterogeneous sources (e.g., Internet images). We develop a novel strategy called Efficient Collaborative Open-source Sampling (ECOS) to construct a proximal proxy dataset from open-source data for cloud training, in lieu of client data. ECOS probes open-source data on the cloud server to sense the distribution of client data via a communication- and computation-efficient sampling process, which only communicates a few compressed public features and client scalar responses. Extensive empirical studies show that the proposed ECOS improves the quality of automated client labeling, model compression, and label outsourcing when applied in various learning scenarios. Source codes will be released.
Author Information
Junyuan Hong (Michigan State University)
Lingjuan Lyu (Sony AI)
Jiayu Zhou (Michigan State University)
Michael Spranger (Sony)
More from the Same Authors
-
2022 Poster: CalFAT: Calibrated Federated Adversarial Training with Label Skewness »
Chen Chen · Yuchen Liu · Xingjun Ma · Lingjuan Lyu -
2022 : The Emergence of Abstract and Episodic Neurons in Episodic Meta-RL »
Badr AlKhamissi · Muhammad ElNokrashy · Michael Spranger -
2022 : MocoSFL: enabling cross-client collaborative self-supervised learning »
Jingtao Li · Lingjuan Lyu · Daisuke Iso · Chaitali Chakrabarti · Michael Spranger -
2022 : Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints »
Homayun Afrabandpey · Michael Spranger -
2022 : The Emergence of Abstract and Episodic Neurons in Episodic Meta-RL »
Badr AlKhamissi · Muhammad ElNokrashy · Michael Spranger -
2022 Poster: Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork »
Haotao Wang · Junyuan Hong · Aston Zhang · Jiayu Zhou · Zhangyang Wang -
2022 Poster: Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization »
Zijie Zhang · Yang Zhou · Xin Zhao · Tianshi Che · Lingjuan Lyu -
2022 Poster: CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks »
Xuanli He · Qiongkai Xu · Yi Zeng · Lingjuan Lyu · Fangzhao Wu · Jiwei Li · Ruoxi Jia -
2022 Poster: FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning »
Tao Qi · Fangzhao Wu · Chuhan Wu · Lingjuan Lyu · Tong Xu · Hao Liao · Zhongliang Yang · Yongfeng Huang · Xing Xie -
2022 Poster: DENSE: Data-Free One-Shot Federated Learning »
Jie Zhang · Chen Chen · Bo Li · Lingjuan Lyu · Shuang Wu · Shouhong Ding · Chunhua Shen · Chao Wu -
2021 Poster: Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning »
Xinyi Xu · Lingjuan Lyu · Xingjun Ma · Chenglin Miao · Chuan Sheng Foo · Bryan Kian Hsiang Low -
2021 Poster: Anti-Backdoor Learning: Training Clean Models on Poisoned Data »
Yige Li · Xixiang Lyu · Nodens Koren · Lingjuan Lyu · Bo Li · Xingjun Ma -
2021 Poster: Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation »
Jinming Cui · Chaochao Chen · Lingjuan Lyu · Carl Yang · Wang Li -
2020 Poster: Assessing SATNet's Ability to Solve the Symbol Grounding Problem »
Oscar Chang · Lampros Flokas · Hod Lipson · Michael Spranger -
2020 Expo Talk Panel: Hypotheses Generation for Applications in Biomedicine and Gastronomy »
Michael Spranger · Kosuke Aoki -
2018 Poster: Boosted Sparse and Low-Rank Tensor Regression »
Jun Yu · Kun Chen · Wanwan Xu · Jiayu Zhou · Fei Wang