Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning
Dec 6, 2021
Speakers
Weishen Pan
Speaker · 0 followers
Jian Liang
Speaker · 0 followers
Changshui Zhang
Speaker · 0 followers
About
Federated learning (FL) has gain growing interests for its capability of learning from distributed data sources collectively without the need of accessing the raw data samples across different sources. So far FL research has mostly focused on improving the performance, how the algorithmic disparity will be impacted for the model learned from FL and the impact of algorithmic disparity on the utility inconsistency are largely unexplored. In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources). We derive our framework from a constrained multi-objective optimization perspective, in which we learn a model satisfying fairness constraints on all clients with consistent performance. Specifically, we treat the algorithm prediction loss at each local client as an objective and maximize the worst-performing client with fairness constraints through optimizing a surrogate maximum function with all objectives involved. A gradient-based procedure is employed to achieve the Pareto optimality of this optimization problem. Theoretical analysis is provided to prove that our method can converge to a Pareto solution that achieves the min-max performance with fairness constraints on all clients. Comprehensive experiments on synthetic and real-world datasets demonstrate the superiority that our approach over baselines and its effectiveness in achieving both fairness and consistency across all local clients.Federated learning (FL) has gain growing interests for its capability of learning from distributed data sources collectively without the need of accessing the raw data samples across different sources. So far FL research has mostly focused on improving the performance, how the algorithmic disparity will be impacted for the model learned from FL and the impact of algorithmic disparity on the utility inconsistency are largely unexplored. In this paper, we propose an FL framework to jointly conside…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
A Data-Centric Image Classification Benchmark
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Embedding temporal error propagation on CNN for unsteady flow simulations
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Temporally Abstract Partial Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Residual Pathway Priors for Soft Equivariance Constraints
Watch later
Marc Finzi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Opening Remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction
Watch later
Ard Kastrati, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%