Provably Convergent Federated Trilevel Learning
Authors: Yang Jiao, Kai Yang, Tiancheng Wu, Chengtao Jian, Jianwei Huang
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80%. |
| Researcher Affiliation | Academia | Yang Jiao1, Kai Yang1,2,3*, Tiancheng Wu1, Chengtao Jian1, Jianwei Huang4,5 1Department of Computer Science and Technology, Tongji University 2 Key Laboratory of Embedded System and Service Computing Ministry of Education at Tongji University 3Shanghai Research Institute for Intelligent Autonomous Systems 4School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen 5Shenzhen Institute of Artificial Intelligence and Robotics for Society yangjiao@tongji.edu.cn, kaiyang@tongji.edu.cn, tony318@tongji.edu.cn, jct@tongji.edu.cn, jianweihuang@cuhk.edu.cn |
| Pseudocode | Yes | Algorithm 1: Asynchronous Federated Trilevel Learning |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | The experiments are carried out on the regression tasks with the following datasets: Diabetes (Dua, Graff et al. 2017), Boston (Harrison Jr and Rubinfeld 1978), Red-wine and White-wine quality (Cortez et al. 2009) datasets. To evaluate the performance of the proposed method, the multiple domain digits recognition task in (Qian et al. 2019; Wang et al. 2021) is considered. There are two benchmark datasets for this task: MNIST (Le Cun et al. 1998) and SVHN (Netzer et al. 2011). |
| Dataset Splits | No | The paper mentions 'validation datasets' but does not provide specific dataset split information (percentages, counts, or explicit methodology) needed to reproduce the data partitioning for training, validation, and testing. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments, only mentioning 'distributed systems' and 'workers'. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | We summarize the experimental setting on each dataset in Table 1. Table 1: Experimental setting in distributed robust hyperparameter optimization and distributed domain adaptation. (Table contains N, S, Stragglers, τ values for various datasets). |