Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
2018pp. 1930–1939
Citations Over TimeTop 1% of 2018 papers
Abstract
Neural-based multi-task learning has been successfully used in many real-world large-scale applications such as recommendation systems. For example, in movie recommendations, beyond providing users movies which they tend to purchase and watch, the system might also optimize for users liking the movies afterwards. With multi-task learning, we aim to build a single model that learns these multiple goals and tasks simultaneously. However, the prediction quality of commonly used multi-task models is often sensitive to the relationships between tasks. It is therefore important to study the modeling tradeo s between task-speci c objectives and inter-task relationships.
Related Papers
- → Benchmark for Evaluating Initialization of Visual-Inertial Odometry(2023)5 cited
- → Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis(2019)14 cited
- → Attentive Task Interaction Network for Multi-Task Learning(2022)5 cited
- → Learning Task Grouping and Overlap in Multi-task Learning(2012)252 cited
- → Understanding and Improving Information Transfer in Multi-Task Learning(2020)47 cited