- Session 2: Multi-task Learning, NLP, Computer Vision, Applications -- Day 2 (Nov.18), talks: 09:00-11:00 (5th floor Hall 2), poster session: 11:00-13:30
- Poster number: Mon22
Qiang Zhou (NTU, Singapore); Yu Chen (Nanyang Technological University); Sinno Pan (NTU, Singapore)
This work focuses on distributed optimization for multi-task learning with matrix sparsity regularization. We propose a fast communication-efficient distributed optimization method for solving the problem. With the proposed method, training data of different tasks can be geo-distributed over different local machines, and the tasks can be learned jointly through the matrix sparsity regularization without a need to centralize the data. We theoretically prove that our proposed method enjoys a fast convergence rate for different types of loss functions in the distributed environment. To further reduce the communication cost during the distributed optimization procedure, we propose a data screening approach to safely filter inactive features or variables. Finally, we conduct extensive experiments on both synthetic and real-world datasets to demonstrate the effectiveness of our proposed method.