When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP
Multi-task learning (MTL) aims at achieving a better model by leveraging data and knowledge from multiple tasks. However, MTL does not always work -- sometimes negative transfer occurs between tasks, especially when aggregating loosely related skills, leaving it an open question when MTL works. Previous studies show that MTL performance can be improved by algorithmic tricks. However, what tasks and skills should be included is less well explored. In this work, we conduct a case study in Financial NLP where multiple datasets exist for skills relevant to the domain, such as numeric reasoning and sentiment analysis. Due to the task difficulty and data scarcity in the Financial NLP domain, we explore when aggregating such diverse skills from multiple datasets with MTL can work. Our findings suggest that the key to MTL success lies in skill diversity, relatedness between tasks, and choice of aggregation size and shared capacity. Specifically, MTL works well when tasks are diverse but related, and when the size of the task aggregation and the shared capacity of the model are balanced to avoid overwhelming certain tasks.
Code (2)
Tasks
DiversityMulti-Task LearningOpen-Ended Question AnsweringSentiment AnalysisSimilar Papers 제목 키워드 기반
Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation
Learning cooperative multi-agent policy from offline multi-task data that can generalize to unseen tasks with varying numbers of agents and targets is an attractive problem in many scenarios. Although aggregating general…
MuJoCoSMACSMAC+VideoMix: Aggregating How-To Videos for Task-Oriented Learning
Tutorial videos are a valuable resource for people looking to learn new tasks. People often learn these skills by viewing multiple tutorial videos to get an overall understanding of a task by looking at different approac…
NavigateHierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning
Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a n…
Minecraftreinforcement-learningReinforcement LearningReinforcement Learning (RL)Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents
Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable with experience. In practice, induced skills may transfer unreliably and can even harm the agent that ret…
A simple method for joint evaluation of skill in directional forecasts of multiple variables
Forecasts for key macroeconomic variables are almost always made simultaneously by the same organizations, presented together, and used together in policy analyses and decision-makings. It is therefore important to know …