Multi-task Learning
By Christopher Fifty, Ehsan Amid, Zhe Zhao, Tianhe Yu, Rohan Anil, Chelsea Finn. 2020
Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naı̈ve formulations often degrade performance and in particular, identifying the tasks that would benefit from cotraining remains a challenging design question. In this paper, we analyze the dynamics of information transfer, or transference, across tasks throughout training. Specifically, we develop a similarity measure that can quantify transference among tasks and use this quantity to both better understand the optimization dynamics of multi-task learning as well as improve overall learning performance. In the latter case, we propose two methods to leverage our transference metric. The first operates at a macro-level by selecting which tasks should train together while the second functions at a micro-level by determining how to combine task gradients at each training step. We find these methods can lead to significant improvement over prior work on three supervised multi-task learning benchmarks and one multi-task reinforcement learning paradigm.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Kun Zhang
- Biwei Huang
- Clark Glymour
- Bernhard Schölkopf
- Mingming Gong
- Eric P. Xing
- Rameswar Panda
- Rogério Schmidt Feris
Citations in the corpus
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning (2019, background): “Multi-task learning has been studied from multiple perspectives [7, 50, 43].”
- Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering (2019, background): “This reasoning is motivated by multi-task learning [1], where multiple learning tasks are solved jointly in a principled way, thus exploiting their commonalities while at the same time preserving useful information for each individual task.”