Research map / Federated learning and privacy / Communication-efficient FL
Communication-efficient Distributed Statistical Inference for Massive Data with Heterogeneous Auxiliary Information
Miaomiao Yu, Zhongfeng Jiang, Jiaxuan Li, Yong Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add heterogeneous external summary statistics | Individual method · Linear regression simulation | empirical SE of beta1: 0.2009 -> 0.0860 | Improved |
| add external info to distributed CEASE algorithm | CEASE · Logistic regression simulation (m=20) | squared estimation error after iteration 1: 0.139612 -> 0.025974 | Improved |
| add external info to distributed CEASE algorithm | CEASE · Logistic regression simulation (m=20) | final squared estimation error: 0.003142 -> 0.000894 | Improved |
| use CD product framework instead of Liu's meta-analysis | Liu's CD · Linear regression simulation | empirical SE of beta1: 0.0866 -> 0.0860 | No clear effect |
| link mapping omits one covariate effect (Scenario II) (ablation) | Proposed CD · Link misspecification simulation | SEE of beta1: 0.1009 -> 0.1939 | Hurt |
| link mapping misdefines beta1 as alpha1+beta1 (Scenario III) (ablation) | Proposed CD · Link misspecification simulation | Mean of beta1 (true 1): 1.0006 -> 0.4488 | Hurt |
| link mapping misspecified, correct dimensions (ablation) | Proposed CD · Link misspecification simulation | SEE of beta3: 0.0983 -> 0.0529 | Improved |
| add external summary info | Individual method · Asthma test set | accuracy: 0.7 -> 0.75 | Improved |
| use Liu's CD method | Proposed CD · Asthma case | accuracy: 0.75 -> 0.5 | Hurt |
| increase iterations S of proposed method | Proposed method · Climate case | adjusted R2: 0.05 -> 0.65 -> 0.69 | Improved |
| use proposed method instead of CDS at S=5 | CDS · Climate case | adjusted R2: 0.59 -> 0.69 | Improved |
| add external info to CDS at same S in Cox model | CDS · Censored birth-interval case | SE of beta1 (x10^-3): 3.6829 -> 3.6686 | Improved |
Closest papers by meaning
- Distributed Statistical Inference under Heterogeneity (JMLR 2023 · similarity 0.87)
- Nonparametric Bayesian Aggregation for Massive Data (JMLR 2019 · similarity 0.86)
- Communication-Efficient Distributed Learning of Discrete Distributions (NeurIPS 2017 · similarity 0.84)
- Simultaneous Inference for Massive Data: Distributed Bootstrap (ICML 2020 · similarity 0.84)
- Heterogeneity-aware Clustered Distributed Learning for Multi-source Data Analysis (JMLR 2024 · similarity 0.84)
- Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
